Turn any AI agent into an AI Scientist.
Expert-thinking profiles: each AGENTS.md teaches an AI agent to reason like a senior
practitioner in one scientific or engineering profession — how it frames problems, the
tools and data it reaches for, how it stress-tests claims, and how it reports findings.
- What is AGENTS.md?
- How these profiles are built
- How to use a profile (three steps)
- Using profiles in your AI tool
- Star this repo if it helps your work
- Follow K-Dense
- Agents
AGENTS.md is a plain Markdown file that tells an AI coding agent how to think and
work in your project. Think of it as persistent lab notes for your assistant: not
the public-facing abstract (that belongs in a README), but the operating procedure —
what to check first, which databases and instruments matter, how to stress-test a
claim, and what mistakes to watch for.
This repository collects expert-thinking profiles: one AGENTS.md per scientific
or engineering profession. Each profile encodes how a senior practitioner in that
field frames problems, evaluates evidence, troubleshoots, and reports results. Drop
one into your workflow and the agent stops reasoning like a generic chatbot and starts
reasoning like someone who knows your domain.
The format is an open standard (stewarded by the Agentic AI Foundation). The same file works across many AI tools — you do not need a separate prompt for every product.
Each profile is research-grounded, not a generic "be rigorous" prompt dressed up for a field name. The goal is an operating mind a senior practitioner would recognize: concrete databases, instruments, units, controls, failure modes, and reporting norms — not advice that would read the same for a synthetic biologist and a radio astronomer.
Scoping. Every profile targets one profession (with sub-specialty where it matters), a work mode (wet-lab, computational, clinical, field, theoretical, or a mix), and the register of an experienced independent researcher.
Research. Before writing, we gather field-specific evidence across parallel dimensions: foundational theory, how experts frame problems, tools and instruments, data sources and literature, statistical rigor, troubleshooting and known failure modes, communication standards, and ethics or regulation where they apply. The aim is dozens of named, verifiable specifics — not a handful of plausible generalities.
Synthesis. Shared scientific commitments (controls, falsifiability, uncertainty, reproducibility, calibrated claims) are written in that field's terms: what counts as a proper control, which error model applies, how results should be reported. Universal rigor plus domain specificity — both are required.
Quality bar. Drafts are checked with a simple test: if you swap in another profession's name and the sentence still reads true, it is too generic and gets cut or replaced. A finished profile should make someone in the field nod — "yes, that's how we actually think."
Profiles are maintained in scientific-agents/<profession>/AGENTS.md and indexed in
catalog.json and the Agents table below.
- Pick a profile from the Agents table below — for example,
developmental-biologist/AGENTS.mdorclinical-epidemiologist/AGENTS.md. - Install it in the project where you work (see tool-specific steps below). The
usual pattern is to copy or link the profile as
AGENTS.mdat your project root. - Ask domain questions as you normally would — analyze data, draft methods, debug a pipeline, review a figure, plan an experiment. The agent loads the profile automatically at the start of each session.
You can combine an expert profile with your own project rules: put shared lab or repo
conventions in the same AGENTS.md, or keep them in a separate file your tool can
include (see each tool below).
Cursor reads AGENTS.md from your project automatically and applies it as standing
context for Agent mode.
- Clone or browse this repo and copy the profile you want, e.g.
scientific-agents/bioinformatician/AGENTS.md. - Save it as
AGENTS.mdin the root of your research codebase (the folder you open in Cursor). - Start a new Agent chat. Cursor loads the file without extra setup.
Tip: For file-specific rules (e.g. only for R scripts), Cursor also supports
.cursor/rules/. Keep the expert profile in AGENTS.md and add narrow rules there
if needed. You can @-mention additional files in chat when you want the agent to
read them on demand.
Claude Code’s native file is CLAUDE.md, but Anthropic recommends pointing it at
AGENTS.md so you stay compatible with other tools. In your project root, create
CLAUDE.md with a single line:
@AGENTS.mdThen copy your chosen expert profile to AGENTS.md in the same directory (or symlink
one file to the other). Claude Code loads CLAUDE.md every session; the @ import
pulls in the full expert profile.
Global use: you can also place guidance in ~/.claude/CLAUDE.md for defaults
that apply to every project.
Antigravity (v1.20.3+) reads AGENTS.md natively at session start. Place your
chosen profile at the project root as AGENTS.md.
Antigravity also supports GEMINI.md for IDE-specific overrides; when both exist,
GEMINI.md wins on conflicting rules. A practical setup for mixed teams: put the
expert profile in AGENTS.md (shared with Cursor, Codex, etc.) and keep
Antigravity-only preferences in GEMINI.md.
Global defaults: ~/.gemini/AGENTS.md applies across projects on your machine.
Codex reads AGENTS.md before doing any work, merging global and project
instructions:
- Global:
~/.codex/AGENTS.md— your personal defaults across all repos. - Project:
AGENTS.mdat the repo root — copy your expert profile here.
Nested folders can add their own AGENTS.md; Codex concatenates files from root to
your current directory (closer files override earlier ones). Expert profiles are
long; if you hit Codex’s default size limit (~32 KiB), raise
project_doc_max_bytes in ~/.codex/config.toml or keep the profile in a
subdirectory you work from.
Use the Codex CLI, VS Code extension, or desktop app — all share the same config.
OpenCode discovers AGENTS.md by walking up from your current directory. Copy a
profile to your project root as AGENTS.md, or run /init in a repo to scaffold one
and replace it with an expert profile.
Global defaults: ~/.config/opencode/AGENTS.md.
OpenCode also reads CLAUDE.md if no AGENTS.md is found, and supports extra
instruction files via opencode.json — useful if you want the expert profile plus
your own CONTRIBUTING.md or lab SOPs.
The same AGENTS.md file is also read by GitHub Copilot, Windsurf, Zed,
Aider, Gemini CLI (via .gemini/settings.json), Devin, Factory, and
others — see the full list at agents.md. If your tool accepts
project-level Markdown instructions, it likely supports this format already.
If a profile saves you time on literature triage, methods drafting, pipeline debugging, or peer review, star the repository on GitHub. Stars are the main signal that researchers find these profiles useful — they help others discover the collection, justify continued expansion into new fields, and keep the profiles maintained as tools and standards evolve. It costs nothing and takes one click.
We add new expert profiles regularly; starring makes it easy to watch the repo for updates.
We build tools that turn any AI agent into an AI Scientist. Star this repo and follow along for new expert profiles, scientific skills, and research workflows:
- X / Twitter — @k_dense_ai
- LinkedIn — K-Dense Inc.
- YouTube — K-Dense Inc.
- Website — k-dense.ai
Stay up to date: follow K-Dense on X, LinkedIn, and YouTube.
| Profession | Work mode | Profile | What it thinks like |
|---|---|---|---|
| Accelerator Physicist | experimental / beam physics | accelerator-physicist/AGENTS.md |
Reasons from beam optics, RF cavities, emittance budgets, and loss maps while treating halo and impedance-driven instabilities as first-class failure modes. |
| Acoustical Engineer | noise control / building & environmental acoustics / NVH / standards (IEC 61672, ISO 9613-2) | acoustical-engineer/AGENTS.md |
Reasons from source-path-receiver control, logarithmic decibel levels, and mass-law transmission loss through IEC 61672 Class 1 metering, ISO 9613-2 propagation, SEA/FEM/BEM simulation, and ISO 9612 occupational surveys while treating flanking paths, coincidence dips, tonality penalties, and background-correction errors as first-class failure modes. |
| Acoustics Physicist | wave acoustics / ultrasonics & underwater / transducer & array / impedance tube & anechoic / standards (ISO 10534, IEC 61672) | acoustics-physicist/AGENTS.md |
Reasons from impedance Z=p/u, Helmholtz number kL regime, and the sonar equation SL-TL-NL+DI+PG through impedance tubes (ISO 10534), anechoic and reverberation rooms, laser vibrometry, and k-Wave/COMSOL simulation while treating edge diffraction inflating absorption above one, near-field versus far-field confusion, flanking and multipath paths, and amplifier clipping mistaken for nonlinearity as first-class failure modes. |
| Actuarial Scientist | life / health / P&C / valuation / capital & accounting | actuarial-scientist/AGENTS.md |
Reasons from mortality tables (qx, period/cohort, select/ultimate) and Chain-Ladder/Mack reserving through GLM/GAM frequency–severity and Tweedie pricing, limited-fluctuation and Bühlhmann-Straub credibility, Solvency II SCR standard formula, and IFRS 17 CSM/RA while treating triangle truncation, overfitting, and tail risk as first-class failure modes. |
| Additive Manufacturing Engineer | LPBF / DED metal AM / qualification | additive-manufacturing-engineer/AGENTS.md |
Reasons from melt-pool physics, VED, and thermal history through LPBF vs DED process selection, build orientation anisotropy, support design, powder lot control, CT/metallography NDE, and ASTM F42 / ISO-ASTM 529xx qualification—not generic 3D printing. |
| Aerodynamicist | wind tunnel / CFD / flight vehicle external aerodynamics | aerodynamicist/AGENTS.md |
Reasons from circulation, Cp distributions, and boundary-layer physics through Re/Mach similitude, NACA airfoil polars, stall classification, wind-tunnel blockage/wall corrections, and SA/SST/LES external-aero CFD—not generic mechanical engineering. |
| Aeronautical Engineer | fixed-wing aircraft design / certification / flight test | aeronautical-engineer/AGENTS.md |
Reasons from airfoil polars, drag buckets, and static margin through AVL/DATCOM stability derivatives, wind-tunnel blockage and wall corrections, FAR 25 §25.101–25.207 compliance matrices, and AC 25-7 flight-test evidence—not generic aerospace or pure CFD aerodynamics. |
| Aeronomy Scientist | remote sensing / MLT-thermosphere-ionosphere / ISR + resonance lidar / tides & coupling / empirical models (IRI, NRLMSIS) | aeronomy-scientist/AGENTS.md |
Reasons from MLT lidar and ISR profiles through IRI/NRLMSIS benchmarks, treating ion-line spectra, metal-layer winds, and storm-time TEC as distinct observables. |
| Aerospace Engineer | margin management / aero-structures-propulsion-GNC / V&V (FAR/CS, DO-178C, NASA-STD) / CFD-FEA-flight test | aerospace-engineer/AGENTS.md |
Reasons from margin-managed factors of safety, mass properties, and the analysis-test-similarity V&V hierarchy through FUN3D/SU2 CFD, NASTRAN/Abaqus FEA, JSBSim/Simulink 6-DOF, and FAR/CS, DO-178C, and NASA-STD compliance while treating flutter, buckling, inlet distortion, mass growth, and single-point failures as first-class failure modes. |
| Agricultural Engineer | field machinery / irrigation & drainage / postharvest storage / precision ag / ASABE standards (D497, ISO 11783) | agricultural-engineer/AGENTS.md |
Reasons from mass, energy, and momentum balances on variable biological media through ET-based scheduling, psychrometric grain-drying balances, ASABE D497 draft estimates, EPANET pipe networks, and RTK-GNSS/ISOBUS precision-ag validation while treating soil compaction, clogged drip emitters, grain-bin hotspots, GPS drift, and uncalibrated yield monitors as first-class failure modes. |
| Agricultural Entomologist | field scouting / IPM / resistance management (IRAC MoA) / biocontrol / pollinator protection | agricultural-entomologist/AGENTS.md |
Reasons from pest population dynamics, economic injury levels and thresholds, and degree-day phenology through systematic scouting, IRAC mode-of-action rotation, RCBD efficacy trials, and conservation biocontrol while treating misidentification, secondary pest flares from enemy removal, resistance under repeated MoA, and trap-catch-without-field-verification as first-class failure modes. |
| Agroecologist | field ecology / soil health / participatory on-farm trials / landscape GIS / agroecology transitions (FAO 10 Elements) | agroecologist/AGENTS.md |
Reasons from socio-ecological farm systems, functional diversity, soil-biology-mediated fertility, and yield-service trade-offs through mother-baby and mixed-model trials, N/P/C mass balances, PLFA/amplicon and pollinator surveys, and NDVI/FRAGSTATS landscape analysis, while treating edge-effect and plot-size artifacts, weather-year confounding, surface-only soil carbon, and ignored labor/tenure adoption constraints as first-class failure modes. |
| Agronomist | field / observational / extension & farm decision support | agronomist/AGENTS.md |
Reasons from 4R stewardship and G×E×M through MRTN economic N, calibrated soil-test extractants, penetrometer compaction diagnosis, on-farm strip mixed models, partial budgets, and AgroEcoList reporting while treating pseudo-replication, yield-monitor drift, and yield-goal N over-application as first-class failure modes. |
| AI Researcher | empirical ML / experiment design / evaluation methodology / reproducibility / LLM & RL / trustworthiness (robustness, fairness, safety) | ai-researcher/AGENTS.md |
Reasons from data generating processes, inductive biases, and compute-data-algorithm trade-offs through train/val/test discipline, seed sweeps, ablation ladders, and standards like NeurIPS reproducibility checklists, model cards, and lm-eval-harness, while treating data leakage (Kapoor & Narayanan taxonomy), benchmark contamination, spurious correlations, and reward-model overoptimization as first-class failure modes. |
| Air Quality Scientist | ambient monitoring / chemical transport modeling (CMAQ, CAMx) / source apportionment / regulatory attainment (NAAQS, SIP) | air-quality-scientist/AGENTS.md |
Reasons from source emissions through transformation, transport, and dose using SMOKE/MOVES inventories, WRF-driven CTMs like CMAQ and CAMx, PMF/ME-2 apportionment, and concentration-response functions, while treating rotational PMF ambiguity, AOD-to-PM bias in humid regions, uncalibrated low-cost sensors, and untreated wildfire exceptional events as first-class failure modes. |
| Algebraist | pure math / structure & morphisms / homological & representation theory / computational algebra (GAP, Sage, Singular) / formal proof (Lean, Coq) | algebraist/AGENTS.md |
Reasons from carriers, operations, and morphisms through isomorphism theorems, universal properties, exact-sequence and homological tools (Ext, Tor, snake lemma), and computational systems like GAP, Magma, SageMath, and Lean while treating silently smuggled hypotheses (commutativity, units, Noetherian, algebraically closed base), characteristic-p false friends, and noncanonical isomorphisms as first-class failure modes. |
| Algorithms Researcher | algorithm design & analysis / proofs & cost models / approximation & online / empirical algorithmics (DIMACS, MIPLIB) | algorithms-researcher/AGENTS.md |
Expert profile for algorithms researcher — see AGENTS.md for field-specific methods and failure modes. |
| Analytical Chemist | wet-lab / separation science / spectroscopy / method validation | analytical-chemist/AGENTS.md |
Reasons from the chemical measurement process through ICH Q2(R2) and USP <621> validation, CRM traceability, EURACHEM uncertainty budgets, and HPLC/GC/LC-MS/ICP-MS workflows while treating matrix effects, SST drift, peak tailing, and ion suppression as first-class failure modes. |
| Anatomist | comparative morphology / museum collections / dissection & imaging | anatomist/AGENTS.md |
Reasons from homology, EPB, and von Baer principles through gross dissection, diceCT/μCT/MRI pipelines, UBERON–PATO EQ annotation, MorphoSource/oVert digitization, geometric morphometrics, and NAV/TA2 nomenclature while treating fixation shrinkage, segmentation artifacts, landmark homology error, and collection bias as first-class failure modes. |
| Anesthesiologist | perioperative medicine / airway management / hemodynamics & pharmacokinetics / regional & multimodal analgesia / perioperative trials (CONSORT, ASA) | anesthesiologist/AGENTS.md |
Reasons from control of consciousness, analgesia, autonomic response, and oxygen delivery through the ASA Difficult Airway Algorithm, capnography and arterial-waveform trends, quantitative TOF monitoring, and ASRA/ERAS protocols while treating cannot-ventilate airways, local anesthetic systemic toxicity, malignant hyperthermia, and residual neuromuscular blockade as first-class failure modes. |
| Animal Geneticist & Breeder | quantitative genetics / BLUP-REML / genomic selection / crossbreeding systems / mate allocation | animal-geneticist-breeder/AGENTS.md |
Reasons from additive genetic variance, response to selection (R = i h sigma_A), accuracy, and inbreeding depression through REML/BLUP and ssGBLUP pipelines (BLUPF90, ASReml, WOMBAT), economic selection indices, optimum-contribution mate allocation, and Interbull MACE while treating confounded contemporary groups, prediction bias/dispersion, popular-sire inbreeding and rising deleterious haplotypes, GxE reranking, and pedigree or genotype-calling errors as first-class failure modes. |
| Animal Nutritionist | applied / monogastric & ruminant / feed evaluation & formulation | animal-nutritionist/AGENTS.md |
Reasons from NASEM/AAFCO requirements, SID amino acids and ideal protein, CNCPS MP/NE balance, and NANP feed libraries through NIR-wet chemistry validation, ileal vs fecal digestibility, pen-structured mixed models, and ARRIVE reporting while treating intake confounds, NIR calibration drift, acidosis/sorting, and pseudoreplicated pens as first-class failure modes. |
| Animal Scientist | feeding/management trials / ruminant & monogastric nutrition / ration formulation (CNCPS, NRC) / welfare & carcass science / mixed-model (pen-unit) stats | animal-scientist/AGENTS.md |
Reasons from NRC nutrient requirements, ad libitum intake, energy/protein partitioning, and genotype x environment x management through ration software (CNCPS, NDS, NRC), pen-blocked trials with mixed models (lme4, PROC MIXED), and BCS, NIR, and rumen/BHBA diagnostics while treating intake collapse, milk fat depression, acidosis, heat stress, wrong experimental unit, and violated withdrawal times as first-class failure modes. |
| Antenna Engineer | RF simulation / antenna design / measurement & OTA | antenna-engineer/AGENTS.md |
Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as first-class failure modes. |
| Antimicrobial Resistance Scientist | wet-lab / WGS resistome / surveillance & One Health AMR | antimicrobial-resistance-scientist/AGENTS.md |
Reasons from MIC distributions, ECOFFs, and phenotype–genotype concordance through EUCAST/CLSI AST, CARD/RGI and AMRFinderPlus resistomes, GLASS/WHONET/NARMS surveillance, carbapenemase/ESBL/MRSA mechanism panels, and heteroresistance PAP while treating breakpoint mixing, genotype-without-phenotype overclaim, selection-bias surveillance, and CARD version drift as first-class failure modes. |
| Applied Mathematician | theoretical / computational / interdisciplinary modeling | applied-mathematician/AGENTS.md |
Reasons from formulation-first modeling, Buckingham scaling, and asymptotics (matched expansions, boundary layers) through FEM/FVM numerics (FEniCS, PETSc, LAPACK), Tikhonov inverse problems, and ASME/Sandia V&V while treating ill-posed inversion, stiffness, and numerical diffusion as first-class failure modes. |
| Aquaculture Scientist | wet-lab / production aquaculture | aquaculture-scientist/AGENTS.md |
Reasons from FCR, dissolved oxygen and ammonia thresholds, hatchery biosecurity, and stock genetics while treating off-flavor, disease outbreak, and escape risk as first-class failure modes. |
| Astrobiologist | planetary science / field analogs / mission astrobiology / origins | astrobiologist/AGENTS.md |
Reasons from habitability, redox disequilibrium, and Bayesian biosignature frameworks through Mars (Perseverance, Viking perchlorate lessons), Europa Clipper ocean worlds, agnostic signatures and the Ladder of Life Detection, while treating abiotic mimics, preservation, and LUCA phylogenomics as constraints—not templates—for extraterrestrial life. |
| Astrochemist | observational / laboratory / computational / interstellar & circumstellar chemistry | astrochemist/AGENTS.md |
Reasons from gas-grain reaction networks, H₂ ortho/para and CR ionization rates through KIDA/kida.uva.2024, CDMS/JPL/Splatalogue line lists, Nautilus/UCLCHEM gas-grain models, ALMA/JWST/LIDA ice–gas linkage, XCLASS LTE fitting, and line-blending discrimination—not generic chemistry. |
| Astrodynamicist | computational / mission analysis / orbit determination / SSA | astrodynamicist/AGENTS.md |
Reasons from two-body plus perturbation force models through Cowell/Encke propagation, batch LS and EKF orbit determination, SPICE/Horizons ephemerides, CCSDS OEM/CDM exchanges, and TEME–GCRF frame discipline while treating drag, stale TLE/B*, and covariance frame mismatch as first-class failure modes. |
| Astronautical Engineer | spacecraft / launch vehicle / mission systems engineering | astronautical-engineer/AGENTS.md |
Reasons from the rocket equation, staging, and mass–power–Δv budgets through NPR 7120.5/ECSS-E-ST-10 subsystem specs, CEA/CEARUN and Sutton propulsion, CLA/pogo and TVAC I&T, GMAT/STK/SPICE mission design, CCSDS TM/TC link margins, and ADCS FDIR while treating unit/frame ICD mismatches, combustion instability, and MCO-class V&V gaps as first-class failure modes. |
| Astronomer | observational / survey / time-domain / solar-system | astronomer/AGENTS.md |
Reasons like a senior observational astronomer from the telescope and catalog outward — Landolt/Stetson photometry, Gaia/MPC astrometry, Horizons ephemerides, SDSS–ZTF–Rubin survey discipline, TOPCAT cross-matches, and calibrated detection vs upper-limit reporting. |
| Astronomical Instrumentation Scientist | opto-mechanical design / error-budget / adaptive optics / detector characterization / commissioning | astronomical-instrumentation-scientist/AGENTS.md |
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as first-class failure modes. |
| Astroparticle Physicist | low-rate counting / neutrino astronomy / dark-matter direct detection / cosmic-ray composition / multimessenger / Geant4-CORSIKA simulation | astroparticle-physicist/AGENTS.md |
Reasons from flux times cross section times acceptance, Poisson counting over structured backgrounds, and Cherenkov photoelectron budgets through SkyLLH unbinned likelihoods, Geant4/CORSIKA chains validated on through-going-muon and calibration samples, and Feldman-Cousins/CLs limits, while treating atmospheric-neutrino and downgoing-muon contamination, ER/NR leakage and the neutrino fog, and look-elsewhere trials as first-class failure modes. |
| Astrophysicist | observational / computational / multi-messenger | astrophysicist/AGENTS.md |
Reasons like a senior astrophysicist across observational, computational, and multi-messenger work — from radiative transfer and error budgets through JWST/ALMA/Rubin/LIGO pipelines, VO archives, and calibrated detection vs upper-limit reporting. |
| Astrostatistician | computational / survey & cosmology inference / time-domain | astrostatistician/AGENTS.md |
Reasons from selection functions, censored flux limits, and look-elsewhere trial factors through Cobaya/emcee/dynesty cosmology, GP-coupled exoplanet inference, Landy–Szalay clustering, photo-z σNMAD calibration, and SBI (sbi/LtU-ILI) while treating Malmquist bias, prior-driven tensions, and detrend-then-fit transit bias as first-class failure modes. |
| Atmospheric Chemist | field campaigns / chamber & box modeling / gas-aerosol-multiphase chemistry / OH-NOx-VOC budgets / emissions inventories | atmospheric-chemist/AGENTS.md |
Reasons from coupled photochemical OH-NOx-VOC radical budgets, heterogeneous aerosol uptake, and NOx-limited versus VOC-limited regimes through MCM/F0AM and GEOS-Chem/CMAQ/WRF-Chem models, OH-reactivity closure, PMF on AMS factors, HYSPLIT trajectories, and EKMA isopleths while treating chamber wall losses, instrument cross-sensitivities and inlet artifacts, and emission-inventory error as first-class failure modes. |
| Atmospheric Scientist | dynamics-physics / obs-model synthesis / reanalysis-NWP / multiscale (synoptic-mesoscale-tropical-stratosphere) | atmospheric-scientist/AGENTS.md |
Reasons from scale-dependent balances, Ertel PV on isentropic surfaces, and closed moisture/energy budgets through PV/omega/Q-vector diagnostics, reanalyses (ERA5, MERRA-2) and WRF/MPAS/CMIP runs, and obs validation (GRUAN sondes, IMERG, CERES), while treating reanalysis assimilation increments, retrieval biases, parameterized-vs-resolved convection, and internal-variability masking of forced trends as first-class failure modes. |
| Atomic, Molecular & Optical Physicist | experimental AMO / lasers / ultracold atoms / precision metrology | atomic-molecular-optical-physicist/AGENTS.md |
Reasons from Rabi/OBE dynamics, laser-cooling hierarchy, optical lattices and Hubbard U/J, and magic-wavelength clock budgets through NIST ASD, ARC, QuTiP/PyLCP, and in-situ lattice-depth calibration while treating power-based depth guesses, polarization impurities, BBR shifts, and imaging-heating conflation as first-class failure modes. |
| Audiologist | clinical audiology / diagnostic audiometry / amplification & cochlear implants / vestibular / standards (ANSI S3.6, ISO 8253) | audiologist/AGENTS.md |
Reasons from auditory transduction, site-of-lesion localization, audibility, and noise dose-response through calibrated pure-tone/masking audiometry, immittance, OAE and ABR/ASSR, and real-ear verification against NAL-NL2/DSL targets while treating unmasked cross-hearing, collapsed ear canals, transducer miscalibration, and non-organic loss as first-class failure modes. |
| Automotive Engineer | vehicle integration / powertrain & xEV calibration / chassis dynamics & NVH / durability & fatigue / homologation & functional safety (FMVSS, ISO 26262) | automotive-engineer/AGENTS.md |
Reasons from vehicle-level requirements, regulatory limits, energy/exergy budgets, and distribution-based durability through DFMEA/DVP&R, DoE calibration (INCA, CANape, HIL), Pacejka tire and multibody models, rainflow fatigue, and source-path NVH analysis while treating undocumented build-level and cal-ID deltas, unmet emissions preconditioning and OBD readiness, ADAS sensor misalignment, and cross-domain torque-arbitration conflicts as first-class failure modes. |
| Bacteriologist | wet-lab / clinical & environmental microbiology | bacteriologist/AGENTS.md |
Reasons from bacterial growth physiology, selective culture, Gram stain, MALDI-TOF and 16S/WGS identification, EUCAST/CLSI AST, BSL containment, contamination and VBNC, using BacDive and BV-BRC for strain metadata and pathogen genomics. |
| Bayesian Statistician | probabilistic modeling / hierarchical inference / MCMC diagnostics / model criticism / decision theory | bayesian-statistician/AGENTS.md |
Reasons from Bayes' rule, coherent uncertainty, exchangeability, and partial-pooling hierarchy through Stan/PyMC HMC-NUTS fits, prior and posterior predictive checks, PSIS-LOO, and SBC calibration while treating divergent transitions and funnels, weak identifiability and label switching, improper posteriors, and post-hoc prior tuning as first-class failure modes. |
| Behavioral Ecologist | field / observational / experimental behavioral ecology | behavioral-ecologist/AGENTS.md |
Reasons from versioned ethograms, Altmann focal/scan sampling, and activity budgets; scores with BORIS (Cohen’s κ), analyzes sequences with Markov/HMM tools, runs sham-controlled playbacks under ARRIVE 2.0, and fits GLMMs on the correct experimental unit while treating pseudoreplication, spatial autocorrelation, and Animal Behaviour reporting norms as first-class failure modes. |
| Behavioral Neuroscientist | in vivo behavior / learning & memory paradigms / operant & maze assays / pose-tracking ethology / IACUC (ARRIVE 2.0, 3Rs) | behavioral-neuroscientist/AGENTS.md |
Reasons from contingency structure, deprivation state, and latent arousal/motivation variables through Morris water maze, contextual/cued fear conditioning, operant schedules on Med Associates rigs, and DeepLabCut/SLEAP/SimBA tracking validated against ethograms, while treating thigmotaxis-as-anxiety, locomotor confounds of memory deficits, peripheral CNO sedation, and trials-as-n pseudoreplication as first-class failure modes. |
| Biochemist | wet-lab / biophysical characterization / metabolism | biochemist/AGENTS.md |
Reasons from thermodynamics, enzyme mechanisms, and binding energetics; designs orthogonal purification and assay readouts while controlling oxidation, aggregation, coupled assays, and activity-vs-abundance confounds. |
| Biogeochemist | field / lab / soil-sediment biogeochemistry / process modeling | biogeochemist/AGENTS.md |
Reasons from coupled C/N/P/S redox cycles through TEAP zonation, porewater Rhizon-peeper sampling, δ13C/δ15N/δ34S tracers, chamber and eddy-covariance fluxes, and Century/DayCent SOM modeling while treating porewater O2 contamination and nitrification-denitrification coupling errors as first-class failure modes. |
| Biogeographer | field / GIS / phylogenetics / spatial modeling | biogeographer/AGENTS.md |
Reasons from Wallace's ecological vs historical split through GBIF occurrence curation, blockCV spatial cross-validation, MaxEnt/biomod2 SDMs with MESS extrapolation flags, BioGeoBEARS vicariance/dispersal tests, and phylogeographic coalescence while treating random-CV AUC inflation, background bias, and area-cladogram overfitting as first-class failure modes. |
| Bioinformatician | dry-lab / computational genomics | bioinformatician/AGENTS.md |
Reference-build discipline (GRCh38/GENCODE/Ensembl, MANE), batch-as-covariate DE (DESeq2/edgeR), index hopping/UDI, GATK/BQSR/PLINK GWAS multiplicity, nf-core reproducibility, and scRNA-seq ambient-RNA/doublet artifacts. |
| Bioinformatics Engineer | dry-lab / pipeline engineering / production genomics | bioinformatics-engineer/AGENTS.md |
Builds production genomics DAGs in Nextflow/nf-core, Snakemake, and WDL/Cromwell with digest-pinned containers, GIAB regression CI (nf-test, pytest), QC-gated MultiQC runbooks, and CLIA-grade provenance—distinct from analyst-focused bioinformatician DE/GWAS reasoning. |
| Biological Oceanographer | sea-going / plankton ecology / production & export rates / omics + microscopy / fisheries oceanography | biological-oceanographer/AGENTS.md |
Reasons from light-nutrient-grazing coupling, the microbial loop, and size-structured export through CTD/MOCNESS sampling, 14C and O2/Ar production with 234Th export flux, imaging and flow cytometry enumeration, and SILVA/PR2 metabarcoding while treating spatial patchiness, diel-migration tow aliasing, CDOM-biased chlorophyll algorithms, and eDNA-detection-as-abundance as first-class failure modes. |
| Biomaterials Scientist | device R&D / implants, scaffolds, drug delivery / biocompatibility (ISO 10993) / degradation & leachables / regulatory (510(k), PMA, ISO 14971) | biomaterials-scientist/AGENTS.md |
Reasons from material-biology interfaces, degradation-product toxicity, and mechanical mismatch to host tissue through ISO 10993 biological evaluation plans, ISO 10993-12 extract conditions, GPC/ICP/SEM characterization, and sterilization validation while treating endotoxin contamination, pH shift from acidic degradation, extract-ratio artifacts, and non-final-form test articles as first-class failure modes. |
| Biomedical Engineer | device R&D / implants / biomechanics / regulatory (510(k), ISO 10993) | biomedical-engineer/AGENTS.md |
Reasons from ISO 14971 risk management, ISO 10993 biocompatibility matrices, ASTM F/ISO 14242 mechanical and wear testing, and FDA 510(k) substantial equivalence; treats stress shielding, UHMWPE osteolysis, F2129 corrosion artifacts, and predicate/material mismatches as first-class failure modes. |
| Biomedical Imaging Scientist | clinical / research | biomedical-imaging-scientist/AGENTS.md |
Reasons from contrast mechanisms, the resolution-SNR-scan-time triangle, and measurement reliability through DICOM/BIDS pipelines, QIBA profiles, phantom QC (ACR, NEMA IQ, Catphan), and blinded central reads (RECIST, RANO, PERCIST) while treating motion, partial volume effects, and cross-scanner harmonization drift as first-class failure modes. |
| Biophysical Chemist | wet-lab / biophysics / calorimetry & surface methods / single-molecule / binding thermodynamics & kinetics | biophysical-chemist/AGENTS.md |
Reasons from free energy landscapes, binding equilibria (K_d, ΔG = ΔH − TΔS), and probe–system coupling through ITC, SPR/BLI, smFRET, AUC, and global fitting (KinTek, SEDFIT) while treating probe perturbation, mass-transport-limited kon, aggregation-driven avidity, and two-state melting violations as first-class failure modes. |
| Biophysicist | single-molecule biophysics / force spectroscopy / electrophysiology / structural (cryo-EM, NMR) / MD simulation | biophysicist/AGENTS.md |
Reasons from energy landscapes, kT-scale thermodynamics, conformational ensembles, and the equilibrium-versus-kinetics distinction through smFRET, optical/magnetic tweezers, patch clamp, cryo-EM, and MD with force-field validation while treating photobleaching and blinking, FRET crosstalk, tether and series-resistance artifacts, and sampling or force-field bias as first-class failure modes. |
| Bioprocess Engineer | wet-lab / integrated biologics USP–DSP, scale-up & GMP validation | bioprocess-engineer/AGENTS.md |
Reasons from QTPP–CPP–CQA QbD, CHO fed-batch/perfusion scale-up (P/V, kLa, mixing), platform mAb DSP (Protein A, low-pH viral hold, IEX polish, UF/DF), tech transfer and PPQ lifecycle; treats transport-limited scale-up, harvest fouling, on-column aggregation, SUB leachables, and arbitrary three-batch PPQ as first-class failure modes. |
| Bioprocess Microbiologist | wet-lab / industrial microbial fermentation & GMP biomanufacturing | bioprocess-microbiologist/AGENTS.md |
Reasons from kLa/OTR–OUR balance, fed-batch μ control, off-gas RQ, van't Riet scale-up, and contamination (phage, bioburden, adventitious agents); treats antifoam kLa penalty, exponential-feed open-loop risk, and SUB vs stainless transfer as first-class failure modes. |
| Biostatistician | clinical / computational / trial and omics biostatistics | biostatistician/AGENTS.md |
Reasons from estimands, SAPs, and error budgets; aligns ICH E9(R1), CONSORT/STROBE, multiplicity, MMRM, Cox survival, causal DAGs, and GWAS FDR while treating immortal time, ICEs, and batch confounding as first-class failure modes. |
| Biosystems & Agricultural Process Engineer | postharvest / grain drying & storage / heat-mass transfer / ag bioprocessing / ASABE standards (D245.7, S448) | biosystems-agricultural-process-engineer/AGENTS.md |
Reasons from coupled heat and mass transfer, moisture sorption (EMC/ERH on D245.7 isotherms), respiration, and closed unit-operation balances through ASABE standards (S352.2 oven moisture, S448 Page thin-layer kinetics, D272.3 airflow resistance), psychrometric aeration analysis, and SuperPro/Aspen bioprocess simulation while treating wet- vs dry-basis mixing, aeration that wets cool grain, case-hardened wet cores, and grain engulfment and dust explosion as first-class failure modes. |
| Botanist | field / herbarium / lab / computational plant science | botanist/AGENTS.md |
Reasons from morphology, floras (FNA/Jepson/eFlora), voucher herbarium specimens (Darwin Core, Index Herbariorum), nomenclature (IPNI/POWO/Madrid Code), APG IV phylogeny, DNA barcoding (rbcL/matK/ITS2), community ecology (vegan adonis2/betadisper, TRY traits), and CITES/ABS ethics; treats vegetative mis-ID, pseudoreplication, PERMDISP confounds, and unvouchered GBIF records as first-class failure modes. |
| Brain–Computer Interface Engineer | EEG/ECoG/intracortical acquisition, real-time signal processing, and clinical BCI systems | brain-computer-interface-engineer/AGENTS.md |
Reasons from modality–paradigm fit (EEG, ECoG, Utah arrays), CSP/Riemannian decoding (pyriemann, MOABB), BCI2000/OpenBCI pipelines, and charge-density stimulation safety; validates within- vs cross-session claims and treats muscle ICA, impedance drift, and IDE/IRB gates as first-class failure modes. |
| Bridge Engineer | structural design / load rating / inspection-NDE / codes (AASHTO LRFD, AREMA) / fatigue-fracture | bridge-engineer/AGENTS.md |
Reasons from load paths, limit states, redundancy, and durability through AASHTO LRFD rating (LRFR/inventory vs. operating), FEM grillage and OpenSees models, HEC-18 scour analysis, and NDE such as half-cell potential and phased-array UT while treating fracture-critical fatigue details, lost composite action, scour, and bearing seizure as first-class failure modes. |
| Building Science Engineer | hygrothermal simulation / field diagnostics / envelope-HVAC integration | building-science-engineer/AGENTS.md |
Reasons from coupled heat-air-moisture transport through ASHRAE 160 moisture-design analysis, WUFI transient simulation, ACH50 leakage mapping, and ISO 10211 psi-values while treating exfiltration condensation, reservoir claddings, and mold-index sensitivity as first-class failure modes. |
| Cancer Biologist | wet-lab / cancer genomics / preclinical oncology | cancer-biologist/AGENTS.md |
Reasons from hallmark capabilities, clonal evolution, and TME context; separates driver from passenger, cell-autonomous from stromal mechanisms, and 2D artifacts from PDO/PDX-validated dependencies using TCGA, DepMap, OncoKB, and REMARK-grade biomarker logic. |
| Carbon Cycle Scientist | flux towers / atmospheric inversions / GHG inventories / isotopic constraints / Earth-system model evaluation | carbon-cycle-scientist/AGENTS.md |
Reasons from carbon mass balance across reservoirs and timescales, sign conventions, and budget closure through the Global Carbon Budget protocol, ONEFlux/REddyProc eddy-covariance processing, atmospheric inversions (CarbonTracker, CAMS, GEOS-Chem), Δ¹⁴C/δ¹³C isotopic partitioning, and ILAMB model evaluation while treating NEE sign mismatches, gap-filled GPP read as measured, fixed-depth SOC comparisons, and uncounted lateral aquatic carbon export as first-class failure modes. |
| Cardiologist | clinical / research | cardiologist/AGENTS.md |
Reasons from oxygen supply-demand mismatch, forward flow, filling pressures, and pre-test probability through 12-lead ECG, TTE/TEE with ASE grading, cath hemodynamics, CMR, and ACC/AHA/ESC guidelines with risk scores like HEART, GRACE, and CHA2DS2-VASc, while treating context-free troponin elevation, low-flow low-gradient AS discordance, undiagnosed wide-complex tachycardia, and premature diagnostic closure as first-class failure modes. |
| Catalysis Engineer | process catalysis / hydroprocessing & FCC / deactivation economics / regeneration / vendor qualification | catalysis-engineer/AGENTS.md |
Reasons from catalyst lifecycle margin, space velocity (WHSV/GHSV/LHSV), and deactivation economics through plant historian trends, MAT/pilot trickle-bed activity tests, Aspen HYSYS activity factors, and ASTM crush/attrition plus TPO/ICP spent-catalyst profiling while treating coke, poisoning, sintering, attrition, and channeling/maldistribution as first-class failure modes. |
| Catalysis Scientist | heterogeneous/homogeneous/enzymatic catalysis / reaction engineering / operando spectroscopy / kinetics & site-counting | catalysis-scientist/AGENTS.md |
Reasons from active-site structure, turnover frequency, selectivity, and the Sabatier principle through CO/H2 chemisorption site-counting, Weisz-Prater and Mears transport checks, Langmuir-Hinshelwood/Mars-van Krevelen kinetics, and operando DRIFTS/XAS while treating diffusion-limited apparent rates, DRIFTS spectator species, mercury-test false positives for leached Pd, sintering, coking, and selectivity collapse at high conversion as first-class failure modes. |
| Causal Inference Scientist | DAGs / potential outcomes / quasi-experiments (DiD, RD, IV) / doubly-robust estimation / sensitivity analysis | causal-inference-scientist/AGENTS.md |
Reasons from structural causal models, potential outcomes, and identification logic through DAGs and do-calculus, doubly-robust estimators (AIPW/TMLE, IPTW, g-formula), and design-based methods (IV, RD, Callaway-Sant'Anna DiD, synthetic control) while treating colliders and M-bias, positivity/overlap failure, and unmeasured confounding (Rosenbaum bounds, E-values) as first-class failure modes. |
| Cell Biologist | wet-lab / mammalian cell culture / fluorescence microscopy / genetic perturbation / rigor (STR, MIQE, REMBI) | cell-biologist/AGENTS.md |
Reasons from compartment thermodynamics, membrane electrophysics, and necessity-plus-sufficiency logic through STR authentication, confocal/TIRF imaging, CRISPR and siRNA perturbation with rescue, and Western blot, treating mycoplasma, passage and serum-lot drift, edge effects, antibody cross-reactivity, siRNA seed off-targets, and well-as-n pseudoreplication as first-class failure modes. |
| Cell Signaling Biologist | wet-lab / phospho-signaling / pathway biology | cell-signaling-biologist/AGENTS.md |
Reasons from RTK–RAS–MAPK and PI3K–Akt–mTOR phosphorylation networks, pathway crosstalk and feedback; validates with phospho-Western, phospho-flow, and PhosphoSitePlus while treating serum-starvation artifacts, inhibitor off-targets, and RNA footprint vs PTM mismatch as first-class failure modes. |
| Cellular Neuroscientist | wet-lab / patch-clamp electrophysiology / live-cell imaging / culture-slice-iPSC preparations / synaptic physiology | cellular-neuroscientist/AGENTS.md |
Treat the neuron as a cable with active channels, not a point integrator unless you have shown it is one for your question. Separate voltage, calcium, and fluorescence observables. GCaMP reports Ca²⁺-driven fluorescence with indicator kinetics; it is not membrane potential. FRET sensors (ArcLight, ASAP) trade speed and dynamic range differently. |
| Ceramics Engineer | processing / sintering / microstructure / electroceramics / mechanical reliability (Weibull, ASTM C-series) | ceramics-engineer/AGENTS.md |
Reasons from crystal chemistry, defect equilibria, sintering densification, and flaw statistics through XRD/Rietveld, dilatometry, SEM fractography, impedance spectroscopy, and Weibull analysis per ASTM C1161/C1239/C1421 while treating surface grinding flaws, Pb/alkali volatilization, closed-pore traps, and thermal-expansion-mismatch cracking as first-class failure modes. |
| Chemical Biologist | wet-lab / chemoproteomics / probe discovery & target validation | chemical-biologist/AGENTS.md |
Reasons from chemical genetics, ABPP/TPP/CETSA chemoproteomics, and SGC/Portal probe criteria; deconvolves phenotypic hits with PAINS/aggregator triage, inactive analogs, and genetic epistasis while treating colloidal aggregation, probe promiscuity, and degrader DC50/Dmax tag artifacts as first-class failure modes. |
| Chemical Engineer | process design / unit operations / separations & reaction engineering / HAZOP safety (API 520, IEC 61511) / Aspen flowsheeting | chemical-engineer/AGENTS.md |
Reasons from closing mass, energy, and momentum balances and competing equilibrium/kinetics/transport regimes through Aspen Plus/HYSYS flowsheeting, McCabe-Thiele and Damkohler-based sizing, pinch analysis, and HAZOP/LOPA with API 520/521 relief, while treating azeotrope-pinched columns, reactor runaway, recycle impurity accumulation, and pump cavitation (NPSHa<NPSHr) as first-class failure modes. |
| Chemical Oceanographer | seawater carbonate chemistry / nutrient & trace-metal biogeochemistry / isotope tracers / shipboard & autonomous sampling / GEOTRACES-GLODAP synthesis | chemical-oceanographer/AGENTS.md |
Reasons from seawater thermodynamics, carbonate-system coupling (DIC, TA, pH, pCO2), redox hierarchies, and tracer conservation on density surfaces through CO2SYS/seacarb with Dickson CRMs, Winkler oxygen, IRMS isotopes, GO-FLO clean trace-metal sampling, and GLODAP/SOCAT/GEOTRACES synthesis while treating organic alkalinity, headspace equilibration, pCO2-mooring biofouling, and trace-metal contamination as first-class failure modes. |
| Cheminformatician | computational / medicinal-chemistry informatics / (Q)SAR | cheminformatician/AGENTS.md |
Reasons from Standard InChI identity and RDKit sanitization through ChEMBL pChEMBL harmonization, Morgan/ECFP fingerprints, scaffold splits and applicability domains, while treating tautomer collapse, KNIME-vs-Python canonicalization drift, and random-split QSAR leakage as first-class failure modes. |
| Chromatin Biologist | wet-lab / chromatin biochemistry / epigenomics | chromatin-biologist/AGENTS.md |
Reasons from nucleosome arrays, histone PTM crosstalk, remodelers, and 3D genome organization; validates ChIP/CUT&Tag/ATAC with spike-ins and IgG controls while separating composition from mechanism. |
| Chronobiologist | wet-lab / computational / human circadian physiology | chronobiologist/AGENTS.md |
Reasons from TTFL molecular clocks, SCN–peripheral coupling, and zeitgeber entrainment (PRC); analyzes actigraphy, DLMO, and PER2::LUC with ClockLab/LumiCycle, MetaCycle/eJTK/LimoRhyde, and CircaDB/CGDB/ChronobioticsDB while separating masking from endogenous τ under constant routine/FD. |
| Civil Engineer | structural / geotechnical / water resources / LRFD design-review / codes (ASCE 7, ACI 318, AASHTO LRFD) | civil-engineer/AGENTS.md |
Reasons from load paths, factored load combinations, soil-structure interaction, and governing limit states through ASCE 7, ACI 318, AISC 360, and tools like SAP2000/ETABS, PLAXIS, and HEC-RAS while treating missing load paths, connection and foundation failures, differential settlement, and unvalidated FEA as first-class failure modes. |
| Climate Risk Analyst | financial / insurance / disclosure & portfolio climate risk | climate-risk-analyst/AGENTS.md |
Reasons from TCFD/IFRS S2 four-pillar disclosure, NGFS Phase V orderly/disorderly/hot-house scenarios, hazard–exposure–vulnerability and RMS/AIR/CLIMADA cat economics, transition carbon-price and stranded-asset pathways, and PCAF financed emissions while treating exposure geocoding quality, Kotz damage-function retraction, and scenario-not-forecast misuse as first-class failure modes. |
| Climate Scientist | computational / observational / paleoclimate physical climate science | climate-scientist/AGENTS.md |
Reasons from ERF/EEI energy-budget closure, AR6 forcing (WMGHG vs ERFaci), optimal fingerprinting and FAR event attribution, CMIP6/ScenarioMIP SSP workflows (ESGF, ESMValTool), and paleo proxy physics (PAGES2k, ice-core δD/CO₂, foraminifera Mg/Ca, coral Sr/Ca) while treating aerosol uncertainty, tree-ring divergence, CMIP tuning circularity, and TLS under-coverage as first-class failure modes. |
| Climatologist | computational / observational climatology & paleoclimate reconstruction | climatologist/AGENTS.md |
Characterizes climate via WMO CLINO baselines (1991–2020 vs 1961–1990), ETCCDI indices, and teleconnection modes; bridges ERA5 climatology to CMIP6/ScenarioMIP SSP deltas (xsdba/QDM), optimal-fingerprint attribution, AR6 ERF/ECS/TCR, and proxy reconstructions (CPS/EIV, PAGES2k, MXD divergence)—distinct from weather forecasting and generic physical-climate narration. |
| Clinical Data Manager | clinical / research | clinical-data-manager/AGENTS.md |
Reasons from ALCOA+ data integrity, traceability, and analysis-ready datasets through CDASH/SDTM/ADaM pipelines, edit-check specs, Pinnacle 21 validation, MedDRA/WHO Drug coding, and define.xml under 21 CFR Part 11, treating blinding breaches, SAE-safety reconciliation gaps, mid-study IG/dictionary version drift, and unspecified partial-date imputation as first-class failure modes. |
| Clinical Embryologist | clinical / research | clinical-embryologist/AGENTS.md |
Reasons from gamete and embryo biology, manufacturing-quality lab control, and prespecified cycle/oocyte/embryo denominators through Vienna consensus KPIs, Gardner/ASEBIR grading, time-lapse morphokinetics, WHO 6th-edition andrology, and vitrification SOPs while treating media-lot and incubator-gas drift, witness mix-ups, abnormal fertilization (1PN/3PN), and clinical case-mix confounding as first-class failure modes. |
| Clinical Epidemiologist | clinical / dry-computational (observational & evidence synthesis) | clinical-epidemiologist/AGENTS.md |
Clinical epidemiology expert for causal study design, observational bias control, GRADE/EBM synthesis, and principled reporting (CONSORT/STROBE/PRISMA). |
| Clinical Laboratory Scientist | clinical / core laboratory (chemistry, hematology, microbiology, blood bank, molecular) | clinical-laboratory-scientist/AGENTS.md |
Reasons from pre-analytical–analytical–post-analytical total testing process; EP15/EP09/EP28 validation, Westgard/Sigma IQC, HIL indices (C56), EP23/IQCP, critical-value read-back, type-and-screen/crossmatch, CLSI M100 direct AST, LC-MS/MS C62, and AUTO10 autoverification. |
| Clinical Microbiologist | clinical diagnostic microbiology / bacteriology service line | clinical-microbiologist/AGENTS.md |
Reasons from blood-culture volume and contamination criteria, staged Gram–ID–AST reporting, MALDI-TOF/VITEK/Phoenix and EUCAST RAST, CLSI M100 vs EUCAST breakpoint discipline, WHONET antibiograms, and NHSN MDRO alerts—treating contaminant vs pathogen and VME/ME as first-class failure modes. |
| Clinical Pharmacologist | clinical / translational pharmacometrics & regulatory PK/PD | clinical-pharmacologist/AGENTS.md |
Reasons from exposure–response, popPK (NONMEM), DDI (ICH M12), TDM/NTI windows, and renal/hepatic/allometric adjustment; aligns dose finding with ICH E4 and FDA clinical pharmacology labeling. |
| Clinical Trial Scientist | clinical operations / GCP trials | clinical-trial-scientist/AGENTS.md |
Reasons from protocol SAPs, ICH-GCP, randomization/blinding, and CDISC SDTM while treating protocol deviations and immortal time as first-class failure modes. |
| Coastal Engineer | field / computational / coastal structures & flood risk | coastal-engineer/AGENTS.md |
Reasons from joint-probability surge and waves through CEM/EurOtop runup-overtopping, Van der Meer/Rock Manual armor, CERC–Van Rijn sediment budgets, and CMS/XBeach/ADCIRC–SWAN model selection while treating toe scour, armor breakage, datum mismatch (BFE vs MHHW), and downdrift impacts as first-class failure modes. |
| Cognitive Neuroscientist | human experimental / fMRI–EEG–MEG / behavioral cognitive neuroscience | cognitive-neuroscientist/AGENTS.md |
Reasons from latent constructs through converging behavior, fMRI/M/EEG, TMS, and lesion evidence; designs factorial and dissociation contrasts, fMRIPrep/GLMsingle/MNE pipelines, MVPA/RSA, and COBIDAS reporting while treating pure insertion, reverse inference, motion confounds, and in-sample decoding as first-class failure modes. |
| Cognitive Scientist | behavioral experiments / computational modeling (DDM, ACT-R, Bayesian) / Marr levels / strong inference / preregistration | cognitive-scientist/AGENTS.md |
Reasons from Marr's levels of analysis, latent processes behind RT and accuracy, and strong inference through PsychoPy paradigms, signal-detection d-prime/criterion, sequential-sampling and ACT-R models, and crossed mixed-effects designs while treating speed-accuracy tradeoffs, criterion shifts, item confounds, and underpowered WEIRD samples as first-class failure modes. |
| Colloid Chemist | wet-lab / dispersion formulation / DLS-zeta-SAXS characterization / interfacial rheology / nano & emulsion stability (ISO DLS, REACH) | colloid-chemist/AGENTS.md |
Reasons from interfacial thermodynamics, DLVO and non-DLVO forces, zeta-potential, and rheology through orthogonal characterization (DLS, NTA, cryo-TEM, SAXS/SANS S(Q), pendant-drop tensiometry) and accelerated-aging stability tests while treating coalescence, Ostwald ripening, creaming, and flocculation crossing the isoelectric point as first-class failure modes. |
| Combinatorialist | theoretical / computational discrete mathematics | combinatorialist/AGENTS.md |
Reasons from labelled vs unlabelled enumeration, EGF/OGF and species, bijective and probabilistic proofs, Turán/Ramsey/extremal bounds, and BIBD/OA design parameters through SageMath/GAP/nauty, OEIS, House of Graphs, and Colbourn–Dinitz tables while treating isomorphism double-counting, parity barriers, and OEIS false matches as first-class failure modes. |
| Combustion Engineer | experimental / combustion & propulsion | combustion-engineer/AGENTS.md |
Reasons from stoichiometry, flame stability, emissions, and CFD-reacted flows while treating blow-off, flashback, and soot formation as first-class failure modes. |
| Communications Engineer | digital / wireless & wired PHY / link & system simulation | communications-engineer/AGENTS.md |
Reasons from Shannon capacity and matched-filter detection through OFDM/MIMO, 3GPP NR LDPC/polar (TS 38.212), TR 38.901 link budgets, Keysight 89600 VSA EVM, ns-3 SLS, and berconfint Monte Carlo while treating CFO/IQ/phase-noise coupling, pre- vs post-FEC BER, and AWGN-only optimism as first-class failure modes. |
| Community Ecologist | field / experimental / multivariate community assembly | community-ecologist/AGENTS.md |
Reasons from Vellend's four processes and Chesson stabilizing/equalizing coexistence through PERMANOVA/betadisper, betapart turnover–nestedness, Gotelli SIM9/C-score null models, and vegan/entropart/picante pipelines while treating compositional closure, dispersion heterogeneity, and pseudoreplicated quadrats as first-class failure modes. |
| Comparative Medicine Researcher | clinical / research | comparative-medicine-researcher/AGENTS.md |
Reasons from species biology, translational validity, and the 3Rs through model-validity frameworks, IACUC protocols, ARRIVE 2.0 reporting, and FELASA/AALAS health surveillance while treating substrain drift, subclinical colony infection (murine norovirus, pinworm, Mycoplasma), analgesia-pathway confounds, and unstated husbandry variables as first-class failure modes. |
| Comparative Physiologist | integrative / respirometry / field & lab comparative biology | comparative-physiologist/AGENTS.md |
Reason from the Krogh principle and oxygen cascade through intermittent-flow respirometry, SMR/BMR/MMR scope, Q10 and heterothermy, hemoglobin P50, allometry and PGLS, while treating chamber drift, activity artifacts, phylogenetic pseudoreplication, and SMR definition mismatch as first-class failure modes. |
| Composites Engineer | design / manufacturing / test / certification | composites-engineer/AGENTS.md |
Reasons from CLT/ABD laminate mechanics, Halpin–Tsai micromechanics, and CMH-17/NCAMP allowables through autoclave/OOA/RTM process control, ASTM D30 mechanical qualification, ultrasonic C-scan and CAI damage tolerance while treating fiber waviness, void content, under-cure, and quasi-isotropic strength traps as first-class failure modes. |
| Computational Chemist | computational / dry / quantum chemistry & molecular simulation | computational-chemist/AGENTS.md |
Reasons from Kohn–Sham DFT, def2/D4 functional selection, and conformer ensembles through VASP/Gaussian/ORCA, AMBER/GROMACS MD, CREST/CENSO sampling, ONIOM/QM/MM electrostatic embedding, GMTKN55 validation, and SCF convergence escalation while treating B3LYP/6-31G*, BSSE, link-atom artifacts, and force-field mismatch as first-class failure modes. |
| Computational Linguist | computational / corpus & annotation / parsing & semantics | computational-linguist/AGENTS.md |
Reasons from UD/PTB formalisms, validate.py/eval.py (LAS/MLAS/ELAS), and evalb .prm settings through Stanza/UDPipe pipelines, PropBank/FrameNet/AMR/UMR layers, IAA (κ, Krippendorff α), CONDA contamination checks, and ARR reproducibility while treating tokenizer mismatch, oracle inflation, train–test leakage, and guideline drift as first-class failure modes. |
| Computational Neuroscientist | computational / dry / modeling & neural data analysis | computational-neuroscientist/AGENTS.md |
Reasons from encoding/decoding, GLM/LNP spike-train likelihood, mean-field E-I balance, and neural manifolds through NEST/Brian/NEURON/BMTK, GPFA/LFADS, Brain-Score alignment, and trained-RNN reverse engineering while treating spike-sorting contamination, model non-identifiability, nested-CV leakage, and task-optimization≠mechanism as first-class failure modes. |
| Computational Physicist | computational / dry / HPC simulation | computational-physicist/AGENTS.md |
Reasons from governing equations, discretization, and HPC scaling through code/solution verification, DFT, MD, Monte Carlo, and FEM/FVM workflows (VASP, LAMMPS, COMSOL, OpenFOAM, QE). |
| Computational Scientist | computational / dry / simulation, UQ, and reproducible workflows | computational-scientist/AGENTS.md |
Reasons from Roache code/solution verification and ASME V&V 10/20/40 credibility through MMS/GCI, UQ ensembles, and Snakemake/Nextflow/CWL pipelines with conda-lock/Apptainer provenance while treating environment drift, workflow cache staleness, and validation-vs-calibration conflation as first-class failure modes. |
| Computational Social Scientist | digital-trace / network science / text-as-data / causal inference (DiD, IV, RDD) / field & survey experiments | computational-social-scientist/AGENTS.md |
Reasons from social mechanisms, measurement validity, and sampling frames through DAGs, fixed-effects and IV/DiD/RDD designs, ERGM/SAOM network models, and human-audited text classifiers while treating unobserved homophily, network interference and SUTVA violations, platform-driven selection, bot contamination, and digital-skew unrepresentativeness as first-class failure modes. |
| Computer Architecture Researcher | computational / simulation / architecture evaluation | computer-architecture-researcher/AGENTS.md |
Reasons from ISA semantics, AMAT/CPI, MESI coherence, and branch prediction through gem5/SPEC/MLPerf evaluation, Amdahl and roofline discipline, TPU/GPU dataflow accelerators, DVFS/EDP, and Spectre/Meltdown mitigation overhead at ISCA/MICRO/HPCA rigor. |
| Computer Graphics Researcher | computational / offline & real-time rendering / neural graphics | computer-graphics-researcher/AGENTS.md |
Reasons from the rendering equation and Monte Carlo MIS through Mitsuba/Embree/Blender, Vulkan/DXR real-time stacks, BRDF/BSDF validation, SIGGRAPH/EG reporting, NeRF/3DGS pitfalls, OCIO color pipelines, OIDN denoising bias, and mesh/UV artifact diagnosis while treating train–display gamma errors and unequal-spp comparisons as first-class failure modes. |
| Computer Hardware Engineer | RTL / microarchitecture / physical design / verification | computer-hardware-engineer/AGENTS.md |
Reasons from CPI/AMAT and MESI/MOESI coherence through SystemVerilog RTL, PrimeTime/Design Compiler/Innovus signoff, PCIe LTSSM/TLP, SVA formal, and clock-gating power while treating CDC metastability, false-path abuse, X-optimism, and coherency traffic as first-class failure modes. |
| Computer Scientist | theory + systems / algorithms & complexity / distributed data / formal methods (TLA+, Coq) / security (STRIDE, OWASP ASVS) | computer-scientist/AGENTS.md |
Reasons from computational models, abstraction contracts, invariants, and measurable complexity through CLRS-grade algorithm analysis, impossibility results (FLP, CAP, NP-hardness), property-based and chaos testing, and formal tools (TLA+, Coq, Z3) while treating partial failure, race conditions, label leakage, and abstraction leaks like GC pauses and clock skew as first-class failure modes. |
| Computer Security Researcher | dry-computational / vulnerability, protocol, and empirical security research | computer-security-researcher/AGENTS.md |
Reasons from explicit threat models and CIA/STRIDE through AFL++/libFuzzer triage, ASan/KASAN oracles, ProVerif/Tamarin proofs, CVE/CWE/CAPEC taxonomies, CyberGym dual-execution benchmarks, Menlo/CVD ethics, and USENIX open-science artifact norms. |
| Computer Vision Scientist | computational / detection, segmentation, pose & 3D vision | computer-vision-scientist/AGENTS.md |
Reasons from calibration, augmentations, and domain shift through COCO/LVIS/KITTI metrics (mAP, IoU, mask AP), convnets vs ViTs, OpenCV/PyTorch/MMDetection stacks, COLMAP/NeRF 3D, and CVPR/ICCV/ECCV eval discipline while treating label noise, train-test leakage, and resolution mismatch as first-class failure modes. |
| Condensed Matter Physicist | experimental / computational / quantum materials | condensed-matter-physicist/AGENTS.md |
Reasons from Bloch bands, quasiparticles, and symmetry through ARPES/STM/neutron/transport workflows, VASP/QE/Wannier90/DMFT, and Materials Project/ICSD/MPDS while treating matrix-element artifacts, Mott vs. DFT gaps, pseudogap vs. SC gap, and Planckian bad-metal transport as first-class failure modes. |
| Connectomics Scientist | computational / volume EM connectomics + collaborative proofreading | connectomics-scientist/AGENTS.md |
Reasons from vEM acquisition and petascale alignment through FFN/RoboEM segmentation, FlyWire/neuPrint/MICrONS/H01 graphs, and synapse-level QC while treating split/merge errors, alignment tears, false synapses, and release-version drift as first-class failure modes. |
| Conservation Biologist | field / genetics / planning / threat & recovery assessment | conservation-biologist/AGENTS.md |
Reasons from IUCN Red List A–E and Green Status recovery metrics, PVA/Ne, occupancy and distance sampling (unmarked, msocc, RMark), prioritizr/Marxan SCP, Conservation Evidence and ROSES synthesis, counterfactual impact evaluation, METT/SMART PAME, and eDNA false-positive models while treating pseudoreplication, GBIF effort bias, offset baselines, and Red List≠priority conflation as first-class failure modes. |
| Conservation Scientist | field monitoring / conservation genetics / systematic planning / impact evaluation / IUCN assessment (Red List, Green Status) | conservation-scientist/AGENTS.md |
Reasons from measurable biodiversity change, counterfactual impact, and effective population size through IUCN Red List/Green Status criteria, occupancy and PVA models (unmarked, Vortex), Marxan/prioritizr planning, and BACI/matching designs while treating detection heterogeneity, spatial pseudoreplication, REDD+ leakage, and Ne sample bias as first-class failure modes. |
| Construction Engineer | field + office / construction management, means & methods, QA/QC | construction-engineer/AGENTS.md |
Reasons from design intent versus means-and-methods through CPM/P6 and Last Planner scheduling, Revit/Navisworks BIM coordination, IBC Chapter 17 special inspections, ASTM C31/C39 cylinder acceptance, and ACI 318 low-break/core protocols while treating formwork collapse, honeycombing, tolerance stack-up, and schedule logic errors as first-class failure modes. |
| Control Systems Engineer | feedback design / state-space & robust control / digital implementation / industrial (PLC/DCS, IEC 61508/61511) | control-systems-engineer/AGENTS.md |
Reasons from plant dynamics, stability margins, and disturbance-rejection specs through Bode/Nyquist and Routh-Hurwitz analysis, LQR/H-infinity and pole placement, Kalman/EKF observers, RGA pairing, and HIL validation while treating integrator windup, actuator saturation and backlash limit cycles, sensor delay masking phase margin, and estimator divergence as first-class failure modes. |
| Corrosion Engineer | field / laboratory / asset integrity & oil & gas infrastructure | corrosion-engineer/AGENTS.md |
Reasons from electrochemical couples, Pourbaix/galvanic selection, and ISO 15156 sour-service limits through AMPP SP0169/SP0502 CP and ECDA, CO₂ models (NORSOK M-506, OLI), coupon/ER/LPR monitoring, and ASTM G5/G48/G61 qualification while treating IR-masked CIPS, salt-spray overclaim, MIC vs. biocide residual, and MR0175≠fit-for-service as first-class failure modes. |
| Cosmochemist | meteorite petrology / isotope geochemistry / presolar grains | cosmochemist/AGENTS.md |
Reasons from oxygen three-isotope taxonomy (Δ17O), chondrite–achondrite classification, and presolar grain NanoSIMS through Meteoritical Bulletin curation, Al–Mg and Pb–Pb isochrons, CRE vs formation-age separation, and clean-lab sample prep while treating terrestrial weathering, mount contamination, and breccia mixing as first-class failure modes. |
| Cosmologist | theoretical / observational / computational cosmology | cosmologist/AGENTS.md |
Reasons from Friedmann/ΛCDM, r_s and transfer functions, and multi-probe inference (Planck CMB, DESI BAO, lensing, Pantheon+ SNe) through CAMB/CLASS, Cobaya, and GetDist while treating photo-z–IA coupling, CMB foreground pipelines, H0/S8 tensions, and emulator extrapolation as first-class failure modes. |
| Critical Care Researcher | clinical / research | critical-care-researcher/AGENTS.md |
Reasons from acute physiology trajectories, modular organ dysfunction, and cluster-aware trial design through APACHE/SAPS/SOFA scoring, Berlin/Sepsis-3/KDIGO definitions, MIMIC-IV phenotyping, and target-trial emulation with clone-censor-weighting while treating immortal-time bias, cluster contamination, competing risks from early death, and sepsis-phenotype cohort inflation as first-class failure modes. |
| Crop Protection Scientist | field / regulatory / IPM & pesticide stewardship | crop-protection-scientist/AGENTS.md |
Reasons from IPM, EIL/ET, and FRAC/HRAC/IRAC MoA rotation through GEP/EPPO efficacy trials, CDMS label law, BBCH timing, DRT application, PPDB/fate modeling, and MRL/GAP alignment while treating resistance, drift, herbicide carryover, and abiotic mimicry as first-class failure modes. |
| Crop Scientist | field trials / agronomy / crop physiology / G×E×M / MET stability analysis | crop-scientist/AGENTS.md |
Reasons from genotype-by-environment-by-management interaction, yield-component partitioning, and phenology-gated critical periods through MET stability analysis (AMMI, Finlay-Wilkinson, GGE biplots), mixed models (ASReml-R, lme4), N-response curves (quadratic-plateau, MRTN), and crop models (APSIM, DSSAT) while treating pseudo-replicated subsamples, single-site yield champions, uncorrected harvest moisture, and weather-during-anthesis confounding as first-class failure modes. |
| Cryo-EM Structural Biologist | wet-lab / structural biology / single-particle cryo-EM | cryo-em-structural-biologist/AGENTS.md |
Reasons from vitrified specimens, CTF-modulated projections, particle heterogeneity, FSC validation, local resolution, preferred orientation, and map-model fit before making structural claims. |
| Cryptographer | theoretical / applied / implementation & standards cryptography | cryptographer/AGENTS.md |
Reasons from IND-CCA/EUF-CMA games and tight reductions through AES-GCM/RSA-OAEP/ECDSA, ML-KEM/ML-DSA (FIPS 203/204), ProVerif/Tamarin/EasyCrypt, dudect constant-time, CAVP/ACVP and FIPS 140-3 CMVP—not pure number theory or vuln fuzzing. |
| Cryptography Engineer | applied crypto / protocol design & review / key management (HSM/KMS) / standards (NIST, IETF, FIPS 140-3) / PQC migration | cryptography-engineer/AGENTS.md |
Reasons from explicit threat models, vetted primitives, key hierarchy, and constant-time secret handling through STRIDE threat modeling, standards (RFC 8446 TLS 1.3, FIPS 203/204, Ed25519), test vectors (Wycheproof, NIST CAVP), and protocol verifiers (Tamarin, ProVerif) while treating nonce reuse in AEAD, padding/Bleichenbacher oracles, timing side channels, and weak-RNG keys as first-class failure modes. |
| Crystal Growth Specialist | melt/solution/vapor growth / Cz-Bridgman-FZ-LEC-PVT / defect characterization / SEMI specs | crystal-growth-specialist/AGENTS.md |
Reasons from thermodynamic driving force, interface stability, constitutional supercooling, and dopant segregation (keff vs. k0, G/R) through Cz/Bridgman/FZ/LEC/PVT growth, CGSim and phase-field simulation, XRT topography, etch-pit counting, and FTIR/SIMS mapping while treating striations, inclusions, crucible-reaction contamination, and cool-down slip and cracking as first-class failure modes. |
| Crystallographer | crystal growth / X-ray & neutron diffraction / phasing & refinement / structure validation / deposition (PDB, CSD/CCDC) | crystallographer/AGENTS.md |
Reasons from reciprocal-space diffraction data, Bragg's law, and space-group symmetry through XDS/DIALS scaling, Phaser/SHELX phasing, Coot/Olex2 building, and MolProbity/checkCIF validation while treating merohedral twinning, wrong space groups, model-bias density unsupported by omit/polder maps, and R_free overfitting as first-class failure modes. |
| Cytogeneticist | clinical / research | cytogeneticist/AGENTS.md |
Reasons from chromosome architecture, copy-number state, banding resolution, and cell-line/clonal context through karyotype, FISH, chromosomal microarray, optical genome mapping, ISCN, and ACMG/ClinGen dosage standards while treating confined placental mosaicism, maternal cell contamination, pseudomosaicism, and culture/banding artifacts as first-class failure modes. |
| Dairy Scientist | clinical / research | dairy-scientist/AGENTS.md |
Reasons from the lactation curve, dry matter intake, and rumen health through NASEM Dairy 2021/CNCPS ration formulation, Penn State particle separation, DHIA records, and pen-level mixed models while treating subacute ruminal acidosis, milk fat depression, transition-cow hypocalcemia, and unadjusted DIM/parity confounding as first-class failure modes. |
| Data Engineer | computational / batch & streaming data platforms | data-engineer/AGENTS.md |
Reasons from idempotent ELT, medallion bronze/silver/gold, Kimball grain and SCD2, CDC/Debezium and watermark incremental loads, dbt/GX quality gates, Airflow/Dagster orchestration, Iceberg/Delta lakehouse MERGE, data contracts and freshness SLIs while treating silent join drops, duplicate amplification, schema drift, and green-DAG-wrong-numbers as first-class failure modes. |
| Data Scientist | computational / analytics, ML & experimentation | data-scientist/AGENTS.md |
Reasons from CRISP-DM business estimands, leakage-safe sklearn Pipelines and nested CV, SQL/warehouse semantic metrics, A/B power and SRM/AA guardrails, causal DAG covariate discipline, and Model Cards/Datasheets while treating train-test leakage, Simpson's paradox, peeking, and PSI>0.25 drift as first-class failure modes. |
| Database Systems Researcher | systems prototyping / storage engines & concurrency control / query optimization / workload benchmarking (TPC, YCSB, JOB) | database-systems-researcher/AGENTS.md |
Reasons from storage hierarchy, concurrency semantics, query-optimization theory, and declared workload models through TPC-C/H, YCSB, and JOB benchmarks, Jepsen/Elle correctness checkers, and perf/blktrace/fio profiling while treating cardinality-estimation plan regressions, tail-latency spikes under skew, unfair fsync-disabled speedups, and benchmark-trick wins as first-class failure modes. |
| Deep Learning Scientist | computational / architecture & large-scale training | deep-learning-scientist/AGENTS.md |
Reasons from CNN/Transformer inductive bias, Li et al. loss landscapes, grokking/mode connectivity, and Kaplan/Chinchilla scaling (~20 tokens/param); designs ResNet/ViT/DiT/MoE/FlashAttention stacks with FLOPs-matched ablations; trains AdamW+cosine/WSD via Megatron-FSDP/DeepSpeed; evaluates FID/MMLU-Pro/MMLU-CF with lm-eval decontamination and Pineau/NeurIPS reproducibility checklists. |
| Dentist-Scientist | clinical / research | dentist-scientist/AGENTS.md |
Reasons from oral biofilm-host ecology, tissue healing capacity, and patient-level clinical endpoints (DMFS, PD/CAL, implant survival) through PICO/PROSPERO protocols, CAMBRA and 2017 AAP/EFP staging, ISO 4049/14801 bench tests with thermocycling, and GRADE-rated reviews while treating in-vitro-to-chairside leaps, plaque-index surrogates without caries reduction, and examiner calibration drift as first-class failure modes. |
| Dermatologist | clinical / research | dermatologist/AGENTS.md |
Clinical-research dermatologist: layered skin anatomy, inflammatory dermatoses and trial endpoints, dermoscopy vs clinical ABCDE, biopsy/pathology, patch testing, telederm, AAD guidelines, and topical steroid potency. |
| Developmental Biologist | embryology / fate-mapping & lineage tracing / morphogenesis imaging / GRN dissection / perturbation (CRISPR, morpholino, Cre-lox) | developmental-biologist/AGENTS.md |
Reasons from stage, positional information, gene regulatory networks, and tissue mechanics through morphology-based staging (Carnegie/HH/Theiler/NF/hpf), French-flag morphogen logic, light-sheet 4D imaging, lineage tracing, and ARRIVE/MDAR/REMBI reporting while treating developmental delay, CRISPR F0 mosaicism, morpholino p53 toxicity, and conflated fate-versus-lineage claims as first-class failure modes. |
| Developmental Psychologist | longitudinal cohorts / age-normed psychometrics / ToM & EF paradigms / looking-time methods / IRB assent (45 CFR 46 subpart D) | developmental-psychologist/AGENTS.md |
Reasons from developmental trajectories, measurement invariance, and familial-environmental context through age-normed instruments (Bayley, WPPSI/WISC, CBCL, MacArthur-Bates CDI), false-belief and violation-of-expectation paradigms, and lme4/lavaan growth models while treating verbal-demand confounding of theory of mind, informative attrition, adult-normed task misapplication, and parent-versus-direct-assessment divergence as first-class failure modes. |
| Differential Geometer | theoretical / geometric analysis / gauge & index theory | differential-geometer/AGENTS.md |
Reasons from connections, curvature, and holonomy; fixes Lee vs Besse/MTW Riemann signs; uses SageManifolds/xAct/Cadabra, Chern–Weil and Atiyah–Singer index theory, and model-space checks (S^n, flat tori) while treating chart artifacts, torsion misuse, and CAS convention drift as first-class failure modes. |
| Digital Pathology Scientist | clinical / research | digital-pathology-scientist/AGENTS.md |
Reasons from whole-slide pixels, pathologist-ground-truth label levels, and stain/scanner batch effects through QuPath, CLAM/TIAToolbox MIL, Macenko/Vahadane normalization, and MI-CLAIM/TRIPOD+AI standards while treating patch-level leakage, scanner-ID shortcuts, attention-on-necrosis artifacts, and inter-pathologist-kappa ceilings as first-class failure modes. |
| Distributed Systems Researcher | protocol R&D / consensus & replication / consistency semantics / chaos & formal verification (TLA+, Jepsen) | distributed-systems-researcher/AGENTS.md |
Reasons from failure models, consistency contracts, and tail-latency-and-recovery performance through TLA+ model checking, Jepsen and Porcupine linearizability checking, and YCSB/DeathStarBench benchmarking with iptables and kill -9 fault injection, while treating unbounded leases and split-brain, clock skew under NTP, and GC-induced p99 spikes as first-class failure modes. |
| Dynamical Systems Theorist | analysis + numerics / bifurcation theory / normal forms / continuation (AUTO, MatCont) / chaos diagnostics | dynamical-systems-theorist/AGENTS.md |
Reasons from state spaces, invariant sets, bifurcations, and multiple time scales through normal-form classification, center-manifold reduction, Floquet/Poincaré maps, and continuation tools like AUTO, MatCont, and DynamicalSystems.jl while treating spurious chaos from finite-time Lyapunov bias, false limit cycles mistaken for tori, numerical blow-up versus true singularity, and Takens embedding artifacts as first-class failure modes. |
| Earthquake Engineer | structural / bridge seismic design, analysis & retrofit | earthquake-engineer/AGENTS.md |
Reasons from ASCE 7 DRS and SDC, capacity design (R, Cd, Ω₀), ELF/MRS/NRHA and ASCE 41 pushover; models in SAP2000/ETABS/OpenSees with PEER NGA-West2 motions; treats liquefaction, soft-story P-delta collapse, and record-scaling artifacts as first-class failure modes. |
| Ecologist | field / observational / community & spatial ecology | ecologist/AGENTS.md |
Reasons from Preston/Fisher SADs and Hutchinson fundamental vs realized niches; designs quadrat/transect and distance/occupancy surveys; filters GBIF issue flags and iNaturalist DQA; fits vegan/iNEXT/unmarked GLMMs with Moran's I and nlme/glmmTMB spatial correlation while treating pseudoreplication, effort bias, and citizen-science artifacts as first-class failure modes. |
| Economic Geologist | field / exploration / ore deposit modelling / geochemistry / resource estimation | economic-geologist/AGENTS.md |
Reasons from mineral systems and deposit-type models (porphyry, VMS, orogenic Au, SEDEX, IOCG) through regolith and lithogeochemistry, LA-ICP-MS sulfide fingerprinting, and geophysical vectors to JORC/CIM/NI 43-101 MRE domaining, variography, OK/MIK estimation, and classification while treating transported regolith, dispersion shadows, pXRF false highs, and Inferred-overclaim as first-class failure modes. |
| Ecosystem Ecologist | field / flux towers / biogeochemistry / process modeling | ecosystem-ecologist/AGENTS.md |
Reasons from NEE/NEP mass balance, ecological stoichiometry, and u*-filtered eddy covariance; processes with ONEFlux/REddyProc, NEON DP4.00200, and CENTURY/DayCent while treating gap-fill partitioning artifacts, chamber pressure pulses, harvest omission, and footprint shifts as first-class failure modes. |
| Ecotoxicologist | regulatory / laboratory & field ERA (aquatic–terrestrial) | ecotoxicologist/AGENTS.md |
Reasons from bioavailability (BLM/WHAM), OECD 201–222 tiered tests, and ECx/SSD HC5–PNEC derivation; compares PEC/PNEC under REACH/PPP frames while treating third-phase BCF artifacts, mixture CA departures, and mesocosm exposure mismatch as first-class failure modes. |
| Edge / Embedded AI Engineer | embedded firmware / on-device inference | edge-embedded-ai-engineer/AGENTS.md |
Reasons from tensor-arena budgets, full-int8 PTQ with representative calibration, and TFLM/CMSIS-NN or Vela/Ethos-U compile paths through ONNX Runtime QNN HTP and mobile delegates—treating train–serve preprocessing skew, float thresholds on quantized outputs, and NPU operator fallback as first-class failure modes. |
| Electric Machines Engineer | electromechanical design / motor drives | electric-machines-engineer/AGENTS.md |
Reasons from magnetic circuit design, dq-frame machine models, FEM flux paths, and drive efficiency maps while treating saturation, cogging, thermal derating, and inverter harmonics as first-class failure modes. |
| Electrical Engineer | circuits & boards / analog & power / SI & EMC / instrumentation / standards-based verification (IEC 62368, CISPR) | electrical-engineer/AGENTS.md |
Reasons from Kirchhoff's laws, Maxwell's quasi-static limit, energy conservation, and LTI superposition through SPICE loop-gain and corner analysis, Bode gain/phase-margin checks, impedance-controlled layout, and IEC 62368/CISPR compliance, while treating unmodeled PCB parasitics, ground-return loops, protection let-through energy versus semiconductor SOA, and probe-artifact confounders as first-class failure modes. |
| Electrochemist | wet-lab / electroanalytical / energy storage | electrochemist/AGENTS.md |
Reason from interfacial thermodynamics and transport: Nernst sets equilibrium, Butler–Volmer sets kinetics, Levich/Randles–Ševčík set mass transport, and EIS deconvolves electrode and battery interphases. |
| Electromagnetics Engineer | RF/microwave / full-wave simulation / VNA measurement / EMC-SAR | electromagnetics-engineer/AGENTS.md |
Reasons from Maxwell scaling and S-parameters through HFSS/CST/ADS workflows, SOLT/TRL calibration, mesh ΔS convergence, Smith-chart matching, anechoic OTA, and CISPR/FCC Part 15 / IEC-IEEE 62209-1528 SAR compliance while treating PML reflections, probe de-embedding, and chamber ripple as first-class failure modes. |
| Electronic Materials Engineer | thin-film / semiconductor materials / process-metrology | electronic-materials-engineer/AGENTS.md |
Reasons from band alignment, defect chemistry, and process–structure–property links; correlates Hall, C–V (Dit), XRD/RSM, SIMS, and ALD/MOCVD/sputtering recipes while treating dopant activation vs. chemical dose, high-κ trap charging, and reliability (NBTI/TDDB) as first-class failure modes. |
| Electronics Engineer | board/IC design / mixed-signal & precision analog / PCB DFM-DFT / manufacturing test & failure analysis | electronics-engineer/AGENTS.md |
Reasons from datasheet-corner device physics, signal-chain error budgets, and analog-digital return-path coupling through LTspice/IBIS-AMI simulation, ICT/boundary-scan coverage, golden-board signature comparison, and IPC/AEC-Q standards while treating ESD versus EOS overstress, MLCC DC-bias derating, reference and clock-jitter ENOB loss, and NFF field returns as first-class failure modes. |
| Electrophysiologist | patch clamp / extracellular LFP & MEA / ion-channel biophysics / rig artifact compensation | electrophysiologist/AGENTS.md |
Reasons from membrane voltage, conductance kinetics, series resistance, and filter settings through pClamp/Multiclamp acquisition, pharmacological channel isolation (TTX, NBQX/APV, picrotoxin), Hodgkin-Huxley/Markov gating fits, and NWB-standardized reporting while treating Rs drift, dialysis run-down, space clamp, and polysynaptic contamination as first-class failure modes. |
| Embedded Systems Engineer | bare-metal/RTOS firmware / board bring-up / JTAG-SWD debug / WCET & power budgeting / MISRA C & safety (ISO 26262, IEC 62304) | embedded-systems-engineer/AGENTS.md |
Expert profile for embedded systems engineer — see AGENTS.md for field-specific methods and failure modes. |
| Emergency Medicine Researcher | clinical / health services research | emergency-medicine-researcher/AGENTS.md |
ED trial design expert for pragmatic and cluster RCTs, time-zero and immortal-time bias in acute cohorts, NIHSS/SOFA/qSOFA and ESI/CTAS triage, NEDS/NHAMCS registries, and CONSORT/SPIRIT reporting with Hawthorne and selection-bias failure modes. |
| Endocrinologist | clinical / research | endocrinologist/AGENTS.md |
Start with the axis, not the number. Every hormone sits in a loop: hypothalamus → Keep the major axes distinct: HPA: CRH → ACTH → cortisol (and adrenal androgens). HPT: TRH → TSH → T4/T3; peripheral deiodinases and T3 receptor signaling. |
| Energy Storage / Battery Scientist | electrochemistry / cell build & testing / materials characterization / failure analysis / standards (IEC 62660, UN 38.3, USABC) | energy-storage-battery-scientist/AGENTS.md |
Reasons from interfacial thermodynamics, ion transport, SEI/CEI dynamics, and cell engineering constraints (N/P and E/S ratio, mass loading) through galvanostatic cycling, dQ/dV, GITT and EIS/DRT, operando XRD, and PyBaMM/Newman models, while treating Li plating, lithium-inventory loss, transition-metal crossover, and coin-cell artifacts as first-class failure modes. |
| Energy Systems Engineer | techno-economic / dispatch modeling / exergy & pinch / CHP & storage / M&V (IPMVP, ISO 50001) | energy-systems-engineer/AGENTS.md |
Reasons from exergy, load duration curves, capacity factor, and grid boundary constraints through pinch analysis, hourly dispatch models (PLEXOS, HOMER Pro, SAM, PVsyst), spark-spread CHP screening, and IPMVP M&V while treating nameplate-vs-utilization confusion, average-vs-marginal grid emissions, unrealistic arbitrage spreads, and demand-charge ratchet resets as first-class failure modes. |
| Entomologist | field / lab / systematics / applied IPM | entomologist/AGENTS.md |
Reasons from tagmata, Comstock-Needham venation, and tarsal formula through trap-guild sampling (Malaise, pitfall, pan, light), host–parasitoid ecology, ICZN vouchers and genitalia keys, BOLD/GBIF/COL/iNaturalist triage, IUCN invertebrate caveats, CITES/COSE permits, Taylor/GLMM on the correct EU, and EIL/ET with IRAC MoA rotation while treating teneral, dimorphic, and cryptic mis-IDs as first-class failure modes. |
| Environmental Chemist | field sampling / trace analysis (GC-MS, LC-MS/MS, ICP-MS) / fate & partitioning / remediation / regulatory (EPA SW-846, REACH) | environmental-chemist/AGENTS.md |
Reasons from thermodynamic partitioning (K_oc/K_ow, Henry's law), pathway-specific half-lives, and mass balance through GC-MS/LC-MS/MS/ICP-MS analysis, EPI Suite and fugacity fate models, and EPA SW-846 QA/QC while treating blank contamination, matrix suppression, censored sub-LOD data, and unscoped transformation products as first-class failure modes. |
| Environmental Engineer | treatment design / water-air-waste / remediation / compliance (NPDES, NAAQS, RCRA/CERCLA) | environmental-engineer/AGENTS.md |
Reasons from mass balances, reaction kinetics, source-pathway-receptor transport, and permit limits through BioWin/GPS-X, SWMM, AERMOD/CALPUFF, GAC/IX and activated-sludge design, and 40 CFR Part 136 QA/QC, while treating nitrifier washout, clarifier upset, PFAS breakthrough, and remediation rebound as first-class failure modes. |
| Environmental Health Scientist | population / field-lab-modeling / regulatory & EJ practice | environmental-health-scientist/AGENTS.md |
Reasons from source–pathway–receptor chains, classical vs Berkson exposure error, and tiered biomonitoring (NHANES/BEs); runs STROBE-grade epi, IRIS/OEHHA/ATSDR risk assessment, AERMOD/CALPUFF, EPHT/EJSCREEN, and HIA while treating surrogate misclassification, mobility bias, and detection≠harm as first-class failure modes. |
| Environmental Microbiologist | field sampling / amplicon + shotgun metagenomics / biogeochemistry coupling / microbial ecology stats | environmental-microbiologist/AGENTS.md |
Reasons from spatial patchiness, redox thermodynamic ceilings, and process-over-taxonomy guild function through DADA2/QIIME2 amplicons keyed to SILVA/GTDB/PR2/UNITE, metaSPAdes/MetaBAT2 MAGs vetted by CheckM/GUNC, and SIP/qSIP rate assays paired with IC/GC/ICP-MS chemistry, while treating extraction-batch effects, relic and extracellular DNA, primer-window bias, and core pseudoreplication as first-class failure modes. |
| Environmental Policy Analyst | regulatory / benefit-cost / NEPA-ESA / climate policy economics | environmental-policy-analyst/AGENTS.md |
Reasons from statutory authority, baseline definition, and monetization boundaries through NEPA/ESA compliance, Circular A-4 RIAs, EPA SC-GHG and benefit transfer, IAM/IPCC scenario use, and APA regulatory comment while treating discount-rate dominance, weak transfer extrapolation, IAM structural uncertainty, and baseline inflation as first-class failure modes. |
| Environmental Scientist | fate & transport / exposure-risk assessment / groundwater & remediation / environmental chemistry / regulatory (CERCLA, SW-846) | environmental-scientist/AGENTS.md |
Reasons from source-pathway-receptor linkages, multimedia partitioning, and dose-as-exposure through conceptual site models, fate models (MODFLOW/MT3DMS, AERMOD), SW-846 QA/QC chains, and ProUCL/Mann-Kendall statistics while treating censoring bias, conceptual-model error, well-construction artifacts, and seasonal confounding as first-class failure modes. |
| Enzymologist | wet-lab / steady-state & transient kinetics / inhibition mechanism / biocatalysis engineering / reporting (STRENDA, EnzymeML) | enzymologist/AGENTS.md |
Reasons from catalytic mechanism, kcat/Km, elementary rate constants, and active-site [E]t through Michaelis-Menten and global fitting in KinTek Explorer, stopped-flow/quench-flow, SPR/BLI/ITC, and STRENDA/EnzymeML reporting while treating substrate inhibition, morpheein equilibria, coupled-assay artifacts, and colloidal-aggregator inhibitor hits as first-class failure modes. |
| Epidemiologist | clinical / research | epidemiologist/AGENTS.md |
Reasons from person-time, transmission dynamics, and population case definitions through epidemic curves, DAGs, renewal and SEIR models (EpiEstim, deSolve), SaTScan clustering, and STROBE/ORION/GRADE standards while treating confounding, collider stratification from test-positive conditioning, reporting-delay and testing-intensity artifacts, and superspreading overdispersion as first-class failure modes. |
| Epigeneticist | epigenomic assays / ChIP-CUT&RUN-ATAC / bisulfite methylation (EWAS) / 3D genome (Hi-C) / epigenome editing (dCas9) | epigeneticist/AGENTS.md |
Reasons from chromatin state, DNA methylation, histone marks, accessibility, and 3D genome topology through ChIP/CUT&RUN, ATAC-seq, WGBS/EM-seq, Hi-C, and dCas9-DNMT3A/KRAB perturbation while treating cell-composition shifts, batch confounding, antibody nonspecificity, Tn5 bias, and incomplete bisulfite conversion as first-class failure modes. |
| Ethologist | field / lab / comparative observational ethology | ethologist/AGENTS.md |
Reasons from Tinbergen's four questions and versioned species vs experimental ethograms; scores with BORIS (Cohen's κ per behavior), Altmann focal/scan budgets, and ARRIVE 2.0/study-plan lab reporting while treating observer expectation, field–lab arena mismatch, habituation, and pseudoreplication as first-class failure modes. |
| Evolutionary Biologist | computational / field / experimental evolution | evolutionary-biologist/AGENTS.md |
Reasons from coalescent demography, MSC gene-tree discordance, and selection–drift nulls; runs IQ-TREE/BEAST/ASTRAL/ANGSD workflows while treating LBA, rogue taxa, batch effects, and uncorrected genome scans as first-class failure modes. |
| Exercise Physiologist | human performance laboratory / clinical CPET / applied sport science | exercise-physiologist/AGENTS.md |
Reason from the Fick principle and verified gas exchange: separate VO2max, VT1/RCP, MLSS, and lactate kinetics before metabolic carts, biopsy, MRS, or periodization prescriptions. |
| Exoplanet Scientist | detection / RV & transits / atmospheric retrieval / occurrence demographics | exoplanet-scientist/AGENTS.md |
Reasons from Keplerian motion, transit and RV geometry, and degenerate retrieval spaces through TLS/BLS searches, centroid and odd-even vetting, RadVel and GP activity models, and petitRADTRANS retrievals while treating eclipsing-binary blends, stellar-rotation-mimicking RV signals, and look-elsewhere completeness cliffs as first-class failure modes. |
| Experimental Physicist | laboratory / apparatus / precision measurement | experimental-physicist/AGENTS.md |
Reasons from GUM error budgets, traceable calibration chains, and multiplied signal-chain transfer functions — separating Type A and Type B uncertainty, null runs, and ELN-linked reproducibility before precision or discovery claims. |
| Extremophile Biologist | wet-lab / field sampling / high-pressure and anaerobic cultivation / metagenomics / astrobiology analogs | extremophile-biologist/AGENTS.md |
Reason from physicochemical limits—T, pH, salinity, pressure, and redox—as filters on membrane chemistry, osmoadaptation, chaperones, and cultivation fidelity before astrobiology or extremozyme claims. |
| Fermentation Scientist | wet-lab / SmF & SSF R&D / starter cultures / kinetic & metabolic modeling | fermentation-scientist/AGENTS.md |
Reasons from Monod–Luedeking–Piret kinetics, overflow μcrit, OTR/RQ/RAMOS analytics, DoE media optimization, and 13C-MFA/COBRApy flux bounds while treating stuck-ferment ethanol×T synergy, SSF heat/moisture gradients, and OD-as-biomass red herrings as first-class failure modes. |
| Finite Element Analyst | computational / simulation / verification & validation | finite-element-analyst/AGENTS.md |
Reasons from discretization error, element technology, and constraint physics; runs mesh convergence and Richardson studies, Nastran/Abaqus/ANSYS workflows, RBE2/RBE3 and contact discipline, and ASME V&V 10 verification-before-validation reporting on governing QoIs. |
| Fire Protection Engineer | design / engineering / performance-based fire modeling | fire-protection-engineer/AGENTS.md |
Reasons from NFPA 13 Hazen-Williams hydraulics (K-factor, remote area, hose stream) and NFPA 101 egress (occupant load, travel distance, capacity factors) through NFPA 92 smoke containment/management, ASET/RSET PBD, and FDS/CFAST/CONTAM/PyroSim modeling while treating breached compartmentation, C-factor/fitting errors, and supply-curve shortfall as first-class failure modes. |
| Fisheries Scientist | stock assessment / population dynamics / harvest control rules / MSE / reference points (F_MSY, B_lim) | fisheries-scientist/AGENTS.md |
Reasons from recruitment, growth, and natural and fishing mortality through state-space assessment models (SS3, SAM, JABBA), CPUE/GLM standardization, and reference points like F_MSY and B_lim under ICES and Magnuson-Stevens frameworks, while treating hyperstability, retrospective bias (Mohn's rho), unaccounted discard mortality, and misspecified M or selectivity as first-class failure modes. |
| Flavor & Fragrance Chemist | aroma chemistry / GC-MS-O analysis / sensory evaluation / formulation / regulatory (IFRA, FEMA GRAS) | flavor-fragrance-chemist/AGENTS.md |
Reasons from odor activity values, threshold perception, matrix release, and degradation kinetics through GC-MS with retention indices, GC-O/AEDA, chiral GC authentication, ISO 8586 trained sensory panels, and IFRA/FEMA regulatory limits while treating aldehyde oxidation, citral cyclization, top-note fade, and allergen exceedance as first-class failure modes. |
| Fluid Dynamicist | computational CFD / theoretical scaling / experimental validation | fluid-dynamicist/AGENTS.md |
Reasons from Navier–Stokes and dimensionless scaling through RANS/LES/DNS selection, mesh/y+ strategy, OpenFOAM/Fluent workflows, and MMS + ASME V&V 20 / PIV validation. |
| Fluid Mechanics Engineer | plant hydraulics / piping & pump systems / CFD verification | fluid-mechanics-engineer/AGENTS.md |
Reasons from Navier–Stokes reductions through Darcy–Weisbach/Crane TP-410 pipe networks, pump system curves, NPSH/affinity laws, HI turbomachinery selection, and ASME V&V 20 CFD validation when simulation supports design. |
| Food Chemist | analytical / regulatory food chemistry | food-chemist/AGENTS.md |
Reasons from food matrix effects, aw and lipid oxidation, AOAC-validated HPLC/GC-MS/LC-MS/MS, FoodData Central/FNDDS, and trained sensory panels while treating matrix suppression, accelerated-shelf-life misuse, and untrained-taster data as first-class failure modes. |
| Food Engineer | process engineering / thermal & nonthermal processing / HACCP validation / pilot-to-plant scale-up | food-engineer/AGENTS.md |
Reasons from water activity, thermal microbiology, transport-coupled reaction, and rheology through heat-penetration studies, F0/D/z lethality integration, HACCP with prerequisite programs, and CFR Title 21 LACF/acidified-food rules while treating cold-point under-processing, aw and pH drift, post-process contamination, and unvalidated scale-up as first-class failure modes. |
| Food Microbiologist | QC lab / food safety / spoilage ecology / HACCP / method validation (ISO 16140, BAM) | food-microbiologist/AGENTS.md |
Reasons from food as a hurdle-governed matrix of water activity, pH, and redox through BAM/ISO reference methods, c/n/m/M sampling plans, PMA-v-qPCR, and ComBase kinetics while treating VBNC and injured cells, post-process contamination, matrix inhibition, and unconfirmed PCR hits as first-class failure modes. |
| Food Scientist | product development / process engineering / sensory / food-safety systems | food-scientist/AGENTS.md |
Reasons from a_w and GAB isotherms, Maillard/acrylamide kinetics, HLB emulsions, TPA/rheology, ISO sensory methods, and HACCP/FSMA preventive controls while treating aw–moisture conflation, HLB-only emulsion fixes, and Arrhenius misuse as first-class failure modes. |
| Forensic Chemist | accredited crime lab / seized-drug & trace analysis / GC-MS & LC-MS/MS / courtroom reporting (SWGDRUG, ISO/IEC 17025, Daubert/Frye) | forensic-chemist/AGENTS.md |
Reasons from chain of custody, validated methods, measurement uncertainty, and class-versus-individual characteristics through GC-MS, LC-MS/MS, FTIR, and SWGDRUG-aligned identification under ISO/IEC 17025, while treating carryover contamination, secondary transfer, isomer co-elution, and upgrading equivocal results into source attribution as first-class failure modes. |
| Forestry Scientist | field / inventory / silviculture / remote sensing / forest carbon | forestry-scientist/AGENTS.md |
Reasons from silvicultural systems, site index, DGH and DBH increment, and FIA cruise design through FVS/ORGANON calibration, LiDAR area-based inventory with support matching, and IPCC carbon pools while treating site-index misassignment, plot edge effects, and change-of-spatial-support bias as first-class failure modes. |
| Formal Methods Researcher | theoretical / verification / interactive proof & model checking | formal-methods-researcher/AGENTS.md |
Reasons from operational semantics and temporal logics through SPIN/TLA+/PRISM, Coq/Lean/Isabelle, Z3/CVC5, refinement and separation logic, vacuity and false-positive diagnosis, and Dafny/F* versus property-based testing boundaries. |
| Foundation Engineer | geotechnical design / deep & shallow foundations / soil-structure interaction / LRFD (AASHTO, Eurocode 7) / site investigation | foundation-engineer/AGENTS.md |
Reasons from effective stress, ULS versus SLS limit states, and construction-altered soil behavior through CPT/SPT logging, triaxial and oedometer testing, LRFD φ-factor checks, and LPILE/PLAXIS analysis while treating liquefaction-driven lateral spread, negative skin friction downdrag, differential settlement, and scour as first-class failure modes. |
| FPGA Engineer | RTL design / timing closure / CDC / SoC integration / lab bring-up (Vivado, Quartus) | fpga-engineer/AGENTS.md |
Reasons from metastability budgets, setup/hold margins, and tool-reported WNS/TNS through Vivado/Quartus timing and CDC reports, XDC/SDC constraints, Spyglass/Verilator lint, and ILA/IBERT lab bring-up while treating unsafe clock-domain crossings, reset domain crossings, sim-versus-silicon X mismatches, and unconstrained timing paths as first-class failure modes. |
| Functional Genomics Scientist | pooled screens / CRISPR-RNAi-ORF / MPRA / Perturb-seq / dependency analysis / hit validation | functional-genomics-scientist/AGENTS.md |
Reasons from perturbation as causal probe, genotype-to-phenotype linkage, library representation, and effect-size-plus-FDR statistics through MAGeCK/BAGEL/CERES-Chronos, CRISPRcleanR, CRISPResso2, MPRAnalyze, and Perturb-seq pipelines while treating MOI/bottleneck artifacts, copy-number and p53/DSB toxicity, RNAi seed effects, and guide-assignment or gating errors as first-class failure modes. |
| Fusion Scientist | experimental plasma physics / integrated modeling / fusion systems | fusion-scientist/AGENTS.md |
Reasons from Lawson triple product and Q through tokamak/stellarator confinement (H-mode, ELMs, RMP), NBI/ICRH/ECRH heating, EFIT/TRANSP/SOLPS-ITER workflows, ITER/JET/DIII-D/W7-X benchmarks, PMI (W/Be PFCs), and tritium breeding blankets. |
| Galactic Astronomer | Galactic archaeology / survey astrometry / stellar populations / chemodynamics / orbit modeling | galactic-astronomer/AGENTS.md |
Reasons from distance ladders, dust extinction, and survey selection functions through Gaia DR3 cross-matches, isochrone and Bayesian SFH fitting (PARSEC/MIST, Starfish), and orbit integration in named potentials (McMillan17, MWPotential2015) via galpy, Agama, and Gala, while treating parallax-S/N and RUWE failures, unresolved binaries and fiber collisions, dust-or-crowding overdensities, and spiral-arm-mimicking-streams as first-class failure modes. |
| Gene Therapy Scientist | clinical / research | gene-therapy-scientist/AGENTS.md |
Reasons from vector biology, biodistribution, linked potency, and integration risk through ddPCR titer, empty/full analytics, ISA and off-target NGS (GUIDE-seq, CIRCLE-seq), and ICH S12 nonclinical design while treating pre-existing capsid neutralizing antibodies, RCV/RCA/RCR positivity, gonadal vector genome, and oligoclonal VCN expansion as first-class failure modes. |
| Genetic Counselor | clinical / research | genetic-counselor/AGENTS.md |
Reasons from probabilistic penetrance, Bayesian pretest probability, and patient autonomy through three-generation pedigrees, ACMG/AMP variant criteria, ClinVar/ClinGen/gnomAD, NCCN and CPIC guidelines, and cascade-testing protocols while treating VUS over-upgraded to pathogenic, screening-versus-diagnostic confusion (NIPT vs amnio/CVS), and unaddressed psychosocial and GINA discrimination risk as first-class failure modes. |
| Geneticist | variant interpretation / GWAS-linkage / pedigree & crosses / population genetics (ACMG/AMP, ClinGen) | geneticist/AGENTS.md |
Reasons from particulate inheritance, segregation, recombination, allele frequency, and genotype-phenotype evidence through ACMG/AMP-ClinGen classification, gnomAD/ClinVar/OMIM, HPO phenotyping, and PLINK/GATK/VEP QC while treating sample swaps, cryptic relatedness, population stratification, LD tagging, phenocopies, winner's curse, and build/transcript mismatch as first-class failure modes. |
| Genome Engineering (CRISPR) Scientist | wet-lab / therapeutic / cell-line engineering | genome-engineering-crispr-scientist/AGENTS.md |
Reasons from NHEJ/HDR/MMEJ competition and editor modality choice through CRISPick/CRISPResso2 guide design, LOCK/lssDNA and RNP HDR, base and prime editing (PE4/PE5, epegRNA), CAST-Seq/UDiTaS on-target SV assessment, clonal genotyping, and FDA/IBC-bound off-target and genome-integrity analytics. |
| Genomicist | clinical / research | genomicist/AGENTS.md |
Reasons from reference-relative coordinates, haplotypes, variant classes, and sequencing-as-measurement through GATK/DeepVariant, VEP/ClinVar/gnomAD, GIAB/hap.py benchmarking, and ACMG/AMP-ClinGen frameworks while treating build mismatches, paralog/pseudogene and GC dropout artifacts, contamination and index hopping, batch effects, and annotation drift as first-class failure modes. |
| Geobiologist | biosignature assessment / isotope geochemistry / microbe-mineral petrography / deep-biosphere -omics / astrobiology | geobiologist/AGENTS.md |
Reasons from metabolism, redox geochemistry, microbe-mineral interactions, and diagenetic filters through stromatolite microfabric petrography, CSIA and clumped-isotopologue analysis, nanoSIMS-FISH mapping, and NASA's Ladder of Life Detection while treating Fischer-Tropsch-type synthesis, serpentinization, Rayleigh distillation, drilling-fluid contamination, and epigenetic overprint as first-class failure modes. |
| Geochemist | lab / field sampling / isotope & aqueous geochemistry / thermodynamic modeling | geochemist/AGENTS.md |
Reasons from Gibbs equilibria, mass and isotope balance, and fluid–rock interaction through stable (δ) and radiogenic (ε, isochron) systems, ICP-MS/LA-ICP-MS/TIMS/MC-ICP-MS/IRMS, PHREEQC/Perple_X phase modeling, and EarthChem/GeoReM workflows while treating alteration, matrix effects, Pb loss, mixing arrays, and Fretwell’s Law violations as first-class failure modes. |
| Geodesist | space geodesy / reference-frame realization (ITRF) / GNSS-InSAR-SLR-VLBI-DORIS / crustal deformation / gravity-field modeling | geodesist/AGENTS.md |
Reasons from coordinates as four-dimensional objects with epoch, velocity, and frame realization (ITRS vs. ITRF2020, WGS84) through GAMIT/GLOBK and Bernese PPP-AR, SBAS/PS-InSAR with GACOS atmospheric correction, IERS Conventions, and 14-parameter Helmert transforms while treating ITRF-realization switches, undocumented APC/ATX mismatches, monument motion, and unscreened seasonal loading as first-class failure modes. |
| Geodynamics & Tectonics Scientist | geodesy (GPS/InSAR) / earthquake hazard (PSHA) / geodynamic modeling / paleoseismology / tsunami | geodynamics-tectonics-scientist/AGENTS.md |
Reasons from plate kinematics, lithospheric rheology, and interseismic-versus-coseismic strain partitioning through GAMIT/GLOBK and MintPy geodesy, Okada/viscoelastic slip inversion, OxCal paleoseismic chronologies, ASPECT mantle modeling, and OpenQuake/USGS NSHM hazard while treating InSAR atmospheric delay, monument instability, unmodeled postseismic afterslip, and incompatible-timescale rate stacking as first-class failure modes. |
| Geographic Information Scientist (GIS) | geospatial data engineering / CRS & topology / spatial statistics & geostatistics / network & hydrologic analysis / web GIS (OGC, STAC) | geographic-information-scientist-gis/AGENTS.md |
Reasons from location, topology, scale, and positional uncertainty through PostGIS/GDAL pipelines, explicit EPSG/datum choices, kriging with cross-validated variograms, and ISO 19115/FGDC metadata while treating MAUP and ecological fallacy, Web Mercator area statistics, floating-point slivers and broken topology, and spatial-autocorrelation-inflated significance as first-class failure modes. |
| Geological Oceanographer | seafloor mapping / sedimentology / marine geophysics / coring & seismic / geohazards | geological-oceanographer/AGENTS.md |
Reasons from sediment transport mechanics, stratigraphic context, and accommodation through multibeam (EM122/EM712) and sub-bottom/seismic imaging, gravity and piston cores with XRF/X-ray CT, CTD tow-yo ORP/Mn/CH4 plume surveys, and Bouma/Lowe facies analysis, while treating bathymetry-mimicking multipath artifacts, bioturbation homogenizing event beds, glacial isostasy mistaken for eustasy, and single-core turbidite extrapolation as first-class failure modes. |
| Geologist | field / mapping / stratigraphy / petrography / structural geology | geologist/AGENTS.md |
Reasons from Steno's principles and Walther's Law through Brunton strike/dip, measured sections, hand-lens rock ID (QAPF/Folk/Dunham), thin-section petrography (PPL/XPL, Michel-Lévy, point counting), FGDC/GeMS geologic maps, NGMDB/Geolex/Macrostrat, and stereonet structural analysis while treating weathering, float, and map-as-hypothesis as first-class failure modes. |
| Geomagnetist | observatory / satellite / paleomag & rock magnetic lab | geomagnetist/AGENTS.md |
Reasons from spherical-harmonic main-field theory and remanence physics through IGRF-14/WMM2025 vs CHAOS-8 SV, INTERMAGNET baseline adoption (IBFV2.00), Swarm quiet-time modeling, stepwise AF/thermal demagnetization with PCA/Fisher, GEOMAGIA50/MagIC archaeomagnetic SVCs, and GFZ Kp/ap indices while treating geomagnetic jerks, IGRF epoch mismatch, VRM/CRM overprints, and Day-diagram mixed-carrier traps as first-class failure modes. |
| Geomorphologist | field mapping / DEM geomorphometry / cosmogenic dating / landscape evolution modeling | geomorphologist/AGENTS.md |
Reasons from coupled form, process, and time and from rates, thresholds, and lag times through field mapping, lidar/SfM DEM morphometry (chi profiles, Ksn in LSDTopoTools/Landlab), cosmogenic nuclide dating (CRONUS-Earth, OSL, U-Th), and landscape-evolution models, while treating equifinality, inheritance, DEM artifacts, and steady-state assumed over transient response as first-class failure modes. |
| Geophysicist | field acquisition / processing / inversion / interpretation | geophysicist/AGENTS.md |
Reasons from wavelength and skin-depth limits through earthquake catalogs (USGS ComCat, ObsPy/FDSN), Bouguer/IGRF gravity-magnetics, MT distortion and dimensionality, and SEG-Y reflection processing (NMO, migration) while treating statics, galvanic distortion, velocity ambiguity, and header mis-mapping as first-class failure modes. |
| Geotechnical Engineer | design / field investigation / construction engineering | geotechnical-engineer/AGENTS.md |
Reasons from effective stress and LRFD/EC7 limit states through GDR/GBR/FDR deliverables, shallow and deep foundations (GEC 6/10/12), excavation support (DeepEX, LPILE), ground improvement, ASCE 7 liquefaction, observational-method triggers, and FHWA pile acceptance while treating DSC claims, setup vs. blow count, and GBR-vs-design conflation as first-class failure modes. |
| Geotechnical Scientist | field / lab / computational geotechnics | geotechnical-scientist/AGENTS.md |
Reasons from Terzaghi effective stress, Mohr–Coulomb/CSSM, and consolidation/seepage through SPT/CPTU (Robertson SBT), triaxial/oedometer (ASTM D-series), Boulanger–Idriss liquefaction, Hoek–Brown/GSI rock mass, EC7 characteristic values, and PLAXIS/Slide2/RS2/GeoStudio workflows while treating sample disturbance, N-value correction chains, spatial variability, and LEM-vs-FEM mismatch as first-class failure modes. |
| Gerontologist | clinical / research | gerontologist/AGENTS.md |
Reasons from senescence hallmarks, frailty, multi-morbidity, and life-course exposures through validated instruments (Fried phenotype, Rockwood CFS, SPPB/gait speed), epigenetic clocks (Horvath, PhenoAge, GrimAge), competing-risk survival (Fine-Gray), and NIA cohorts (HRS, NHATS, ITP) while treating survivor bias, differential attrition, healthy-volunteer bias, and frail-subset toxicity as first-class failure modes. |
| Glaciologist | field / remote sensing / ice-core paleoclimate / ice-sheet modeling | glaciologist/AGENTS.md |
Reasons from mass-budget closure (SMB, dynamic discharge, calving), Glen flow law, and subglacial effective pressure through WGMS/GlaMBIE stake networks, ICESat-2/CryoSat altimetry with firn and radar-penetration corrections, ITS_LIVE velocities, ApRES basal melt, RES/MCoRDS bed picks, RGI/BedMachine inventories, OGGM mountain-glacier projections, and PISM/ISSM ISMIP6/7 protocols while treating firn-compaction aliasing, DEM penetration bias, GRACE leakage/GIA, and tidal InSAR artifacts as first-class failure modes. |
| Global Health Researcher | field / health systems / implementation & mixed-methods research | global-health-researcher/AGENTS.md |
Reasons from burden, equity, and health-system building blocks through DHS/MICS/DHIS2/GBD triangulation, cluster and stepped-wedge designs, RE-AIM/CFIR implementation science, and CIOMS-fair partnership while treating survey weights, HMIS completeness, and GBD smoothing as first-class failure modes. |
| Glycobiologist | wet-lab / structural glycobiology / glycomics & glycoproteomics | glycobiologist/AGENTS.md |
Reasons from N-/O-glycan biosynthesis, O-GlcNAc cycling (OGT/OGA), LC-MS glycomics, exoglycosidase sequencing, and lectin microarrays; uses GlyTouCan/SNFG/MIRAGE, pGlyco/GlycoWorkbench, and treats PNGase F limits, isomer collapse, and ER-stress high-mannose as first-class failure modes. |
| Gravitational Physicist | GW data analysis / matched-filter search & PE / numerical relativity / GR tests (LVK, GWOSC) | gravitational-physicist/AGENTS.md |
Reasons from calibrated strain, colored non-stationary noise PSDs, matched-filter SNR, and Bayesian posteriors through PyCBC/GstLAL/cWB searches, Bilby/LALInference PE with NRSur/SEOBNR/IMRPhenom waveforms, and FAR/p_astro significance while treating glitch contamination, waveform-approximant mismatch, mass-spin and distance-inclination degeneracies, and unmodeled selection effects as first-class failure modes. |
| Gravitational-Wave Astronomer | observational / multi-messenger | gravitational-wave-astronomer/AGENTS.md |
Reasons like a senior GW astronomer across LIGO–Virgo–KAGRA matched-filter CBC searches, calibration-aware PE, GraceDB/GWTC alert–catalog discipline, BAYESTAR/Bilby skymaps, and EM follow-up campaigns. |
| Green Chemist | process R&D / pharmaceutical & fine-chemical manufacturing / sustainable design | green-chemist/AGENTS.md |
Reasons from Anastas–Warner 12 principles, Trost atom economy, and PMI/MMI/E-factor mass metrics; selects solvents via CHEM21/GSK/ACS GCIPR guides, integrates catalysis and LCA (ISO 14040), and aligns REACH/CSS with ACS GC&E benchmarking. |
| Health Economist | computational / HEOR / health technology assessment | health-economist/AGENTS.md |
Reasons from QALY/ICER and NMB opportunity-cost framing, NICE reference case and WTP bands, cohort Markov/PSM models with PSA (CEAC/CEAF), ISPOR transferability and DCE conjoint checklists, CHEERS 2022 and trial-based RCT-CEA reporting. |
| Health Informatician | clinical / research | health-informatician/AGENTS.md |
Reasons from semantic interoperability, provenance, and patient safety through FHIR/US Core, SNOMED-LOINC-RxNorm terminology mapping, OMOP/OHDSI ETL with DQD/Achilles, and chart-review PPV validation while treating immortal-time and confounding-by-indication bias, patient-matching/MPI failures, billing-code phenotypes, and vocabulary version drift as first-class failure modes. |
| Heat Transfer Engineer | thermal analysis / conjugate CFD-FEA / heat exchanger design / electronics cooling / standards (ASME, TEMA, JEDEC JESD51) | heat-transfer-engineer/AGENTS.md |
Reasons from conduction, convection, radiation, and coupled fluid-solid physics through thermal resistance networks, Biot/NTU/film-temperature scaling, LMTD and epsilon-NTU exchanger methods, fin efficiency, and conjugate-heat-transfer CFD while treating contact resistance and TIM pump-out, fouling, boiling CHF, non-condensables, and non-conservative interface flux mapping as first-class failure modes. |
| Heliophysicist | remote sensing + in situ / MHD-plasma / space-weather forecasting / magnetosphere coupling | heliophysicist/AGENTS.md |
Reasons from MHD, magnetic topology, reconnection, and IMF Bz coupling through SDO/HMI magnetograms, DEM and NLFFF analysis, coronagraph GCS fitting, and WSA-ENLIL/EUHFORIA ensembles while treating LOS foreshortening, AIA stray light, force-free NLFFF breakdown, and Dst/SYM-H saturation as first-class failure modes. |
| Hematologist | clinical / research | hematologist/AGENTS.md |
Reasons from hematopoietic hierarchy, clonal evolution, and hemostatic balance through peripheral smear review, reticulocyte production index, flow cytometry, mixing studies, and WHO/ICC-anchored NGS and cytogenetics, while treating pseudothrombocytopenia, preanalytic line-draw and EDTA artifacts, and missed consumptive emergencies like TTP and DIC as first-class failure modes. |
| Hepatologist | clinical / research | hepatologist/AGENTS.md |
Reasons from hepatic injury pattern (R-value), synthetic function, and portal hypertension through Child-Pugh/MELD 3.0, FIB-4 and elastography, LI-RADS/BCLC staging, SAAG paracentesis, and Baveno VII criteria while treating DILI misattribution, elastography false positives in cholestasis, hypersplenic thrombocytopenia, and missed acute-on-chronic decompensation as first-class failure modes. |
| Herpetologist | field / observational / lab / conservation herpetology | herpetologist/AGENTS.md |
Reasons from detectability-limited sampling and ectotherm phenology through VES, pitfall/drift-fence and cover-board arrays, NAAMP call surveys, Program MARK CJS, unmarked/occuTTD occupancy, and Bd/Bsal MW113 qPCR biosecurity; uses AmphibiaWeb, Reptile Database, SSAR 9th ed./CNAH names, Amphibian Disease Portal, GBIF/CoordinateCleaner, and ARRIVE 2.0 while treating weather bias, pitfall selectivity, and pathogen cross-contamination as first-class failure modes. |
| High-Energy Astrophysicist | observational / computational X-ray & gamma-ray | high-energy-astrophysicist/AGENTS.md |
Reasons from Compton/synchrotron radiative processes and compact-object energetics through HEASARC/Fermi/Swift/XMM/Chandra/NuSTAR/XRISM pipelines, XSPEC/Sherpa spectral fitting, pile-up and background systematics, blazar/GRB/TDE campaigns, and GCN multi-messenger coordination while treating RMF versioning, soft-proton flares, and look-elsewhere significance as first-class failure modes. |
| High-Performance Computing Specialist | computational / cluster & supercomputing | high-performance-computing-specialist/AGENTS.md |
Reasons from NUMA topology and hybrid MPI+OpenMP+CUDA decomposition through Slurm fairshare/backfill job design, strong/weak scaling (Amdahl/Gustafson), Darshan/mpiP/Nsight profiling, and parallel HDF5/MPI-IO on Lustre while treating I/O storms, collectives bottlenecks, and rank-binding mistakes as first-class failure modes. |
| Histologist | wet-lab / clinical & research histology | histologist/AGENTS.md |
Reasons from fixation-through-stain pre-analytical chain (NBF, grossing, processing, embedding orientation, microtomy); validates H&E pH/QC, CAP IHC (90% concordance, predictive scoring systems), RNAscope controls, WSI (60-case validation), and treats floaters, autolysis, crush, ice-crystal, and decalcification artifacts as first-class failure modes. |
| Horticulturist | orchard/CEA trials / postharvest physiology / rootstock-scion & crop load / IPM (degree-day, MRL/PHI) | horticulturist/AGENTS.md |
Reasons from plant-environment-cultural coupling, source-sink carbon partitioning, and chilling/photoperiod thresholds through rootstock-scion matching, DLI/VPD and substrate EC/pH targets, Dynamic/Utah chill models, and CA/MA postharvest setpoints while treating blossom-end rot, bitter pit, tipburn, storage scald, and MRL/PHI breaches as first-class failure modes. |
| Human–Computer Interaction Researcher | empirical / design / field & lab HCI research | human-computer-interaction-researcher/AGENTS.md |
Reasons from situated context, Fitts/GOMS/KLM, and CHI contribution types; runs contextual inquiry through LMM/CLMM analysis with SUS/NASA-TLX triangulation; uses Prolific/OSF and treats demand characteristics, novelty effects, ordinal misuse, and WEIRD samples as first-class failure modes. |
| HVAC Engineer | load calc / psychrometrics / system selection / refrigeration / TAB & commissioning (ASHRAE 62.1, 90.1, Guideline 36) | hvac-engineer/AGENTS.md |
Reasons from psychrometric state, parallel heating and cooling load paths, and vapor-compression thermodynamics through TRACE/HAP and EnergyPlus load models, ASHRAE 62.1/55/90.1 and Guideline 36 sequences, and TAB/commissioning per ASHRAE 15/34, while treating low ΔT syndrome, simultaneous reheat fight, coil-leaving condensation, and A2L refrigerant safety as first-class failure modes. |
| Hydraulic Engineer | open-channel / pipe flow / water systems | hydraulic-engineer/AGENTS.md |
Reasons from Bernoulli–Darcy–Weisbach, Moody diagrams, HEC-RAS/EPANET modeling, and pump/system curves while treating transient water hammer, air entrainment, and roughness aging as first-class failure modes. |
| Hydrogeologist | field hydraulics / aquifer testing / contaminant transport / MODFLOW modeling / remediation | hydrogeologist/AGENTS.md |
Reasons from Darcy's law, mass conservation, aquifer heterogeneity, and coupled biogeochemical transport through Theis and Cooper-Jacob aquifer-test analysis, MODFLOW/MT3DMS modeling with PEST uncertainty, and low-flow geochemical sampling while treating wellbore-storage and skin artifacts, equivalent-porous-medium failure in fractured/karst flow, and non-unique K-S calibration as first-class failure modes. |
| Hydrologist | rainfall-runoff modeling / flood forecasting / watershed hydrology / cold-regions & ecohydrology / uncertainty quantification | hydrologist/AGENTS.md |
Reasons from hydrologic-cycle closure (P = ET + Q + ΔS + I), runoff-generation mechanisms, and channel routing through HEC-HMS, HEC-RAS, the National Water Model, and split-sample KGE/NSE/PBIAS calibration, while treating post-flood rating-curve shifts, radar QPE bias, snow/rain misclassification, and non-stationarity in extremes as first-class failure modes. |
| Ichthyologist | field / museum / fisheries science / ichthyoplankton / eDNA | ichthyologist/AGENTS.md |
Reasons from meristic fin formulae, sagittal otolith annuli/daily increments, larval flexion staging, and ICZN type discipline through Eschmeyer's Catalog, FishBase/WoRMS, MiFish/12S eDNA with blank controls, FSA/TropFishR/SS3 stock assessment, and Darwin Core museum metadata while treating CPUE catchability, unvalidated otolith ages, larval pigmentation loss, and eDNA false positives as first-class failure modes. |
| Immunogeneticist | clinical laboratory / transplant histocompatibility / MHC population genetics | immunogeneticist/AGENTS.md |
Reasons from HLA/KIR/FcγR diversity, haplotype LD, and epitope immunogenicity; adjudicates NGS typing, imputation fine-mapping, eplet/TCE matching, and DSA/crossmatch artifacts. |
| Immunologist | wet-lab / translational immunology | immunologist/AGENTS.md |
Reasons from innate/adaptive immunity and MHC presentation; designs flow cytometry (FMO, gating, exhaustion panels), ICS, ELISpot (DFR), tetramer, and multiplex cytokine assays; validates epitopes via IEDB/NetMHCpan; reports per MIATA and MIFlowCyt. |
| Immunotherapy Scientist | translational / cellular & checkpoint immunotherapy | immunotherapy-scientist/AGENTS.md |
Reasons from antigen recognition and checkpoint circuits through CAR-T/bispecific design, ASTCT CRS/ICANS grading, flow cytometry release CQAs, iRECIST response assessment, COMPASS/TIDE biomarker modeling, and JACIE/FACT IEC accreditation while treating antigen escape, pseudoprogression, tonic signaling, and step-up CRS as first-class failure modes. |
| Industrial Ecologist | MFA/SFA accounting / dynamic stock modeling / industrial symbiosis (EIP) / EEIO-LCA linkage / circular economy metrics | industrial-ecologist/AGENTS.md |
Reasons from mass balance closure, in-use stocks, and system boundaries through STAN (ÖNorm S 2096), dynamic MFA with Weibull lifetime distributions, EEIO tables (EXIOBASE, USEEIO) and pedigree-scored Monte Carlo while treating non-closing residuals, re-export trade hubs, downcounted informal-sector leakage, and Kalundborg-copied symbiosis without quality-spec match as first-class failure modes. |
| Industrial Engineer | manufacturing / logistics / service operations / ergonomics & simulation | industrial-engineer/AGENTS.md |
Reasons from takt, Little's Law, and ρ-stable queueing (M/M/c, Erlang C) through DMAIC/DMADV, VSM, line balancing, SLP/ALDEP/CRAFT layout, MTM/MOST, work sampling, RNLE/RULA/REBA, ISO 22400 OEE, and Arena/AnyLogic DES V&V; treats simulation warm-up/replication gaps, CRAFT non-contiguity, and OEE-without-takt red herrings as first-class failure modes. |
| Industrial Microbiologist | wet-lab / bulk & GMP-adjacent fermentation, environmental & mining biotech, biocontrol | industrial-microbiologist/AGENTS.md |
Reasons from SmF/SSF physiology, fed-batch μ/OTR–OUR/RQ, DoE media optimization, PAT (Raman soft sensors), ICH Q8/Q7 characterization, bioleaching, SVI/F/M filament ID, and phage (10⁴–10⁶ PFU/mL) plant hygiene; treats antifoam kLa penalty, F₀ CIP/SIP cold spots, DSP mass balance, and golden-batch vs biofilm red herrings as first-class failure modes. |
| Infectious Disease Specialist | clinical / research | infectious-disease-specialist/AGENTS.md |
Reasons from the host-pathogen-antimicrobial triangle, source control, and local resistance through IDSA/CLSI M100 breakpoints, PK/PD targets (vancomycin AUC24 400-600, beta-lactam time-above-MIC), and diagnostics like MALDI-TOF, BioFire panels, and galactomannan while treating colonization-versus-infection, blood-culture contaminants, and noninfectious fever mimics (drug fever, IRIS) as first-class failure modes. |
| Information Retrieval Scientist | ranking / evaluation (TREC, trec_eval) / BM25 + neural retrieval / search-log privacy | information-retrieval-scientist/AGENTS.md |
Reasons from the Probability Ranking Principle, ranked-list utility, and candidate-generation-versus-re-ranking separation through BM25 baselines, dense and cross-encoder retrieval, and TREC-style qrels evaluated with trec_eval and nDCG, while treating position-biased clicks, unjudged-as-nonrelevant pools, analyzer mismatches, and AOL-style search-log re-identification as first-class failure modes. |
| Inorganic Chemist | wet-lab / coordination & organometallic synthesis / solid-state & catalysis | inorganic-chemist/AGENTS.md |
Reasons from electron counting, ligand field theory, and HSAB matching through Schlenk/glovebox air-sensitive synthesis, SCXRD/checkCIF validation, Evans/EPR/XANES oxidation-state assignment, and hot-filtration leaching tests while treating paramagnetic NMR overinterpretation, mystery-oil misidentification, and DFT-without-multiplicity claims as first-class failure modes. |
| Instrumentation Engineer | I&C loops / 4-20 mA & HART / calibration & metrology / safety systems (ISA-84/IEC 61511) | instrumentation-engineer/AGENTS.md |
Reasons from the process variable, its transduction chain, 4-20 mA loop integrity, and traceable calibration through ISA-5.1 P&IDs, NAMUR NE43 fault bands, ISO 5167 orifice sizing, and GUM uncertainty budgets while treating plugged impulse lines, double-applied square-root, ground-loop noise, and unrevalidated SIS bypasses as first-class failure modes. |
| Integrated Circuit Designer | custom analog/RF / mixed-signal / DRC-LVS-PEX signoff / corner & Monte Carlo / tapeout & silicon debug | integrated-circuit-designer/AGENTS.md |
Reasons from spec through Virtuoso schematic/layout, Calibre DRC/LVS/RCX, and foundry PDK corners across analog, mixed-signal, RF, and structured digital blocks; treats TT-only signoff, LVS-without-PEX, and common-centroid violations as first-class tapeout failure modes. |
| Isotope Geochemist | mass spectrometry (TIMS/MC-ICP-MS/IRMS/SIMS) / radiogenic geochronology / stable-isotope tracers / clean-lab separation chemistry | isotope-geochemist/AGENTS.md |
Reasons from fractionation theory, decay schemes, reservoir mixing, and closure assumptions through standard-sample bracketing, double-spike deconvolution, isochron/Tera-Wasserburg fitting with MSWD, and ISO Guide uncertainty propagation while treating Pb-blank and lab-air contamination, mass bias, Pb loss and inheritance, and open-system resetting as first-class failure modes. |
| Knowledge Representation Researcher | ontology engineering / description logics / semantic web (OWL 2, SPARQL, SHACL) / OBDA / neuro-symbolic integration | knowledge-representation-researcher/AGENTS.md |
Reasons from model-theoretic semantics, the expressivity-vs-decidability-vs-scalability tradeoff, and competency questions through OWL 2 profiles, reasoners (HermiT, Pellet, ELK), ROBOT/Protégé pipelines, and SHACL validation while treating unsatisfiable classes, silent OWA-vs-CWA semantic mixing, hallucinated LLM-suggested axioms, and IRI-reuse on bad merges as first-class failure modes. |
| Landscape Ecologist | spatial pattern analysis / connectivity modeling / landscape genetics / remote sensing / disturbance ecology | landscape-ecologist/AGENTS.md |
Reasons from scale-explicit pattern-process feedbacks, configuration over composition, and functional rather than graphical connectivity through FRAGSTATS, landscapemetrics, Circuitscape resistance surfaces, NLMR neutral models, and block cross-validation, while treating MAUP grain artifacts, classification error propagation, isolation-by-distance confounding isolation-by-resistance, and resistance surfaces unvalidated by movement as first-class failure modes. |
| Laser Physicist | laser source R&D / ultrafast & CPA / nonlinear frequency conversion / beam metrology / laser safety (ISO 11146, IEC 60825) | laser-physicist/AGENTS.md |
Expert profile for laser physicist — see AGENTS.md for field-specific methods and failure modes. |
| Life-Cycle Assessment Analyst | attributional/consequential LCA / inventory & impact assessment / allocation & uncertainty / EPD critical review (ISO 14040/14044, EN 15804) | life-cycle-assessment-analyst/AGENTS.md |
Reasons from functional unit, attributional-versus-consequential framing, and ISO 14044 allocation hierarchy through openLCA, SimaPro, Brightway2, ecoinvent, and LCIA methods like TRACI and EF 3.0 while treating allocation-driven ranking flips, biogenic-versus-fossil carbon mistagging, cut-off-masked hotspots, and PCR mismatch as first-class failure modes. |
| Limnologist | field / observational / physical limnology / lake ecology / paleolimnology | limnologist/AGENTS.md |
Reasons from stratification, Schmidt stability, and nutrient–light coupling; profiles with CTD/EXO and Carlson TSI components; models with rLakeAnalyzer and GLM while treating internal P loading, sensor fouling, and spatial pseudoreplication as first-class failure modes. |
| Logician | proof theory / model theory / computability / set theory / formal verification (Lean, Coq, Z3) | logician/AGENTS.md |
Expert profile for logician — see AGENTS.md for field-specific methods and failure modes. |
| Low-Temperature Physicist | experimental / cryogenic / condensed-matter & quantum transport | low-temperature-physicist/AGENTS.md |
Reasons from kT budgets, He-3/He-4 dilution refrigeration, and BCS/GL superconductivity; measures Tc, QHE, and Landauer conductance with lock-in/SQUID workflows while treating wiring heat loads, Kapitza resistance, flux trapping, TLS dielectric loss, and sample-vs-MXC thermometer mismatch as first-class failure modes. |
| Machine Learning Engineer | production ML / MLOps / feature stores & serving | machine-learning-engineer/AGENTS.md |
Reasons from feature-store point-in-time joins (Feast/Tecton), Airflow/Kubeflow training pipelines, MLflow registry, Triton/TorchServe/BentoML serving, Evidently/WhyLabs drift and PSI, shadow/canary/A/B rollouts, inference SLAs, and reproducible training hashes while treating train–serve skew, label leakage, and peeking A/B as first-class failure modes. |
| Machine Learning Researcher | computational / empirical & theoretical machine learning research | machine-learning-researcher/AGENTS.md |
Reasons from population risk, double descent, and inductive bias; enforces sacred test sets, hierarchical ablations, nested CV, and HELM/Dynabench-aware benchmarking; reports with NeurIPS and Pineau reproducibility checklists while treating leakage, meta-overfitting, benchmark contamination, Goodhart gaming, and seed variance as first-class failure modes. |
| Mammalogist | field / observational / museum systematics / telemetry | mammalogist/AGENTS.md |
Reasons from mammalian life history and detectability-limited sampling through ASM MDD taxonomy, Sherman/camera-trap/SCR survey design, occupancy and SECR models, bat acoustic validation, and museum voucher discipline while treating trap heterogeneity, camera autocorrelation, closure violation, and WNS decontamination gaps as first-class failure modes. |
| Manufacturing Engineer | process planning / CNC-CAM / GD&T / quality launch (APQP/PPAP, MSA/SPC) / multi-process (machining, welding, casting) | manufacturing-engineer/AGENTS.md |
Reasons from process physics, capability, and cost through Shercliff-Lovatt process selection, ASME Y14.5 GD&T, CAM simulation, and AIAG APQP/PPAP with MSA-gated SPC capability, treating high %GRR masquerading as variation, false Cpk on unstable or short runs, datum-scheme mismatch, and uncontrolled ECN tweaks as first-class failure modes. |
| Marine Biologist | field / shipboard / biological oceanography / eDNA & observing systems | marine-biologist/AGENTS.md |
Reasons from water-mass stratification, CTD–Niskin and CalCOFI-style net tows, BRUV, and MiFish/COI eDNA through OBIS/WoRMS/GBIF and ARGO/BGC-Argo; treats mesopelagic DVM, hypoxia/Ω_aragonite constraints, fluorometer quenching, BRUV MaxN bias, and transect pseudoreplication as first-class failure modes. |
| Marine Engineer | shipboard / design / machinery systems / class compliance | marine-engineer/AGENTS.md |
Reasons from propulsion thermodynamics, shaft BPF/torsional barred speeds, central LT/HT cooling, class machinery surveys, and ISO 15016:2025 sea trials while treating cat fines liner wear, scavenge fire, purifier mis-set, blackout PMS logic, and tropical SW fouling as first-class failure modes. |
| Marine Geologist | ship/AUV survey / seismic + multibeam / IODP coring + stratigraphy / marine geohazards + seafloor resources | marine-geologist/AGENTS.md |
Reasons from stratigraphy, sedimentary processes, geophysical facies, and age control through multibeam bathymetry, 2D/3D seismic, piston/IODP cores tied via synthetic seismograms, and CSF-A age models while treating bad-SVP false scarps, BSRs mimicking free gas, gas-charged push-down faking structural offset, and reworked-carbon radiocarbon dates as first-class failure modes. |
| Mass Spectrometrist | clinical / research | mass-spectrometrist/AGENTS.md |
Reasons from ion formation, m/z resolution and mass accuracy, fragmentation, and calibrated ion statistics through ESI/APCI/MALDI tuning, CID/HCD/ETD MS/MS, isotope-pattern formula assignment, and spectral libraries (NIST, mzCloud, GNPS) under FDA/ICH M10/MSI tiers, while treating matrix suppression, PEG/siloxane/keratin contamination, decoy-driven FDR inflation, and unassigned adducts as first-class failure modes. |
| Materials Chemist | wet-lab / solid-state & solution synthesis / diffraction & spectroscopy | materials-chemist/AGENTS.md |
Reasons from Kröger–Vink defect equilibria, soft-chemistry routes (sol-gel, hydrothermal, ALD), and structure–property links; validates with GSAS-II/TOPAS Rietveld QPA, GIPAW ssNMR, ICSD/COD/Materials Project, and XPS/BET protocols while treating preferred orientation, AdC mis-referencing, degas artifacts, and metastable phase traps as first-class failure modes. |
| Materials Physicist | experimental / thin-film & bulk / spectroscopy–transport | materials-physicist/AGENTS.md |
Reasons from band structure, defects, strain, and Landau order parameters; integrates HRXRD/RSM, ARPES, TEM/4D-STEM, van der Pauw transport, and SQUID/MOKE with Materials Project/VASP while treating matrix-element ARPES artifacts, substrate-dominated GIXRD, contact-resistance Hall errors, and DFT gap overclaim as first-class failure modes. |
| Materials Scientist | laboratory / computational / processing–structure–property | materials-scientist/AGENTS.md |
Reasons from CALPHAD phase diagrams, Scheil solidification, and Hall–Petch microstructure–property links; validates with XRD Rietveld QPA, EBSD, TEM/STEM, and ASTM mechanical testing while treating preferred orientation, FIB Ga artifacts, EBSD overlap, and Rietveld overfitting as first-class failure modes. |
| Mathematical Analyst | proof-theoretic / PDE & functional analysis / harmonic analysis / operator spectral theory / symbolic-numerical (SymPy, FEniCS, Lean) | mathematical-analyst/AGENTS.md |
Reasons from function-space topology, convergence modes, and constant-dependent inequalities (Hölder, Sobolev, Gronwall) through compactness theorems (Rellich-Kondrachov, Banach-Alaoglu), Calderon-Zygmund and Schauder estimates, and Lax-Milgram while treating limit-integral swaps without dominated convergence, boundary-degenerating constants, weak-versus-classical regularity gaps, and concentration-compactness loss as first-class failure modes. |
| Mathematical Modeler | mechanistic modeling / ODE-PDE & agent-based / identifiability & UQ / calibration & inverse problems | mathematical-modeler/AGENTS.md |
Reasons from nondimensionalization, conservation/positivity laws, and minimal-viable model structure through mechanistic ODE/PDE, stochastic, and agent-based formulations, profile-likelihood and Fisher-information identifiability, and Sobol/Morris sensitivity analysis, while treating sloppy unidentifiable parameters, structural model uncertainty, and out-of-regime extrapolation as first-class failure modes. |
| Mathematical Physicist | theoretical / axiomatic & constructive mathematical physics | mathematical-physicist/AGENTS.md |
Reasons from Hilbert-space domains, Wightman/OS and Haag–Kastler axioms, constructive QFT, Gibbs measures, and spectral/scattering theory; uses Reed–Simon, Glimm–Jaffe, MathSciNet/math-ph, while treating wrong self-adjoint extensions, invalid Wick rotation, limit-order swaps, and lattice-as-continuum claims as first-class failure modes. |
| Mathematical Statistician | theoretical / computational | mathematical-statistician/AGENTS.md |
Reasons from LAN, empirical processes, and influence functions; proves M/Z-estimator limits, minimax rates (Fano/Le Cam/Assouad), and semiparametric efficiency while validating with ADEMP simulations and treating naive bootstrap, non-Donsker classes, and debiasing sparsity violations as first-class failure modes. |
| Mechanical Design Engineer | CAD / GD&T / tolerance / DFM | mechanical-design-engineer/AGENTS.md |
Reasons from function, datum reference frames, and tolerance budgets; releases inspectable drawings and MBD through ASME Y14.5 GD&T, WC/RSS/Monte Carlo stack-ups, SAE J1739 DFMEA (Action Priority), and Boothroyd–Dewhurst DFM/DFA—not stress plots alone. |
| Mechanical Engineer | design / simulation / prototyping | mechanical-engineer/AGENTS.md |
Reasons from equilibrium, failure physics, and code-backed allowables; designs through requirements, GD&T, DFMEA, and hand/FEA/test validation with explicit governing failure modes. |
| Mechatronics Engineer | electromechanical co-design / motion control / FOC drives / fieldbus (EtherCAT, CiA 402) / drive safety (IEC 61800-5-2, ISO 13849) | mechatronics-engineer/AGENTS.md |
Reasons from reflected inertia, control bandwidth, sensor physics, and thermal duty cycle through Bode loop-shaping with phase/gain margins, FOC current-velocity-position loops, plant identification, HIL, and IEC 61800-5-2 STO architecture while treating backlash and structural-mode resonance, transport-delay phase loss, encoder aliasing, and EMC ground loops as first-class failure modes. |
| Medical Geneticist | clinical / laboratory genetics / genetic counseling | medical-geneticist/AGENTS.md |
Reasons from pedigree priors, HPO phenotype match, and ACMG/ClinGen variant classification; integrates exome/genome, CMA, RNA splicing, NBS ACT pathways, Tier 3 carrier screening, SF v3.3, and CPIC pharmacogenomics while treating VUS overcall, CPM/NIPT discordance, mtDNA heteroplasmy sampling, and SpliceAI-only splicing claims as first-class failure modes. |
| Medical Mycologist | clinical / laboratory medical mycology | medical-mycologist/AGENTS.md |
Reasons from EUCAST/CLSI antifungal susceptibility, culture and MALDI-TOF ID, galactomannan/β-D-glucan assays, and CLSI breakpoints while treating contamination, cryptic species mis-ID, and azole MIC trailing as first-class failure modes. |
| Medical Parasitologist | clinical / research | medical-parasitologist/AGENTS.md |
Reasons from specimen-stage fit, exposure-based pretest probability, and antigen-versus-antibody kinetics through thick/thin Giemsa films, formalin-ethyl-acetate concentration with trichrome, multiplex PCR, and EITB serology against CDC DPDx and WHO algorithms, while treating pfhrp2/3-deleted RDT false-negatives, single-O&P misses of Strongyloides, and colonization-mistaken-for-infection as first-class failure modes. |
| Medical Physicist | clinical / diagnostic & nuclear imaging / health physics | medical-physicist/AGENTS.md |
Reasons from CTDIvol/SSDE, HU accuracy, ACR/MQSA QA, TG-126 PET/CT, TG-18/TG-270 displays, and NCRP 147 shielding across CT, MRI, mammography, NM/PET, and therapy QA while treating phantom-mismatch dose claims, SUV normalization drift, display washout, and post-upgrade MEE gaps as first-class failure modes. |
| Medicinal Chemist | lead optimization / SAR / DMPK & ADME / structure-based design / multiparameter (LLE, Fsp3, TPP) | medicinal-chemist/AGENTS.md |
Reasons from structure-activity relationships, lipophilicity and unbound-fraction physicochemistry, synthetic accessibility, and target-product-profile multiparameter optimization through LLE/Fsp3/QED scoring, FEP+/Glide docking validated against co-crystal and SPR data, ELN-tracked LC-MS/NMR synthesis, and DMPK panels (microsomal CL, Caco-2 efflux, hERG, CYP) while treating PAINS and aggregation assay artifacts, biochemical-versus-cellular potency gaps, reactive-metabolite soft spots, and freedom-to-operate cliffs as first-class failure modes. |
| Membrane Biophysicist | wet-lab / computational membrane biophysics | membrane-biophysicist/AGENTS.md |
Reasons from Helfrich elasticity, Lo/Ld phase behavior, and intrinsic curvature; builds GUVs, SLBs, nanodiscs, and BLMs; reads Laurdan GP, FRAP/FCS, aspiration, and electrophysiology while treating multilamellarity, detergent carryover, and probe misinterpretation as first-class failure modes. |
| MEMS Engineer | silicon micromachining / transducer design / simulation & WLT | mems-engineer/AGENTS.md |
Reasons from scale-dependent mechanics, squeeze-film damping, and electrostatic pull-in through DRIE Bosch/surface micromachining, CoventorMP/COMSOL, foundry PDKs, LDV/WLI metrology, and AEC-Q103 qual while treating release stiction, DRIE scallop bias, package-stress offset drift, and functional-WLT-vs-reliability gaps as first-class failure modes. |
| Metabolomics Scientist | wet-lab / LC-MS & GC-MS / computational metabolomics | metabolomics-scientist/AGENTS.md |
Reasons from MSI annotation levels, pooled-QC RSD and D-ratio gates, MZmine/MS-DIAL/XCMS pipelines, HMDB/GNPS identification, and MetaboAnalyst batch correction (ComBat, QC-RLSC); treats injection-order drift, ComBat over-correction, and Level-5 pathway stories as first-class failure modes. |
| Metallurgist | physical / extractive / process metallurgy | metallurgist/AGENTS.md |
Reasons from phase diagrams, TTT/CCT paths, and Scheil solidification through Jominy hardenability (ASTM A255), ASM heat-treat cycles, metallography (ASTM E3/E112/E407), and staged failure analysis while treating decarburization, quench cracking, HAZ liquation, hot tearing, and microsegregation as first-class failure modes. |
| Meteorologist | operational / research atmospheric forecasting | meteorologist/AGENTS.md |
Reasons from hydrostatic and geostrophic balance, scale-dependent dynamics, and the obs-to-NWP pipeline; works the Snellman funnel, matches HRRR/GFS/ECMWF to scale, and treats spin-up, convective scheme bias, radar AP, and PoP misinterpretation as first-class failure modes. |
| Metrology Scientist | calibration laboratory / NMI / measurement assurance | metrology-scientist/AGENTS.md |
Reason from SI traceability, GUM uncertainty budgets, and VIM distinctions between calibration and verification; propagates Type A/B components, CIPM MRA equivalence, and ILAC decision rules before any pass/fail claim. |
| Microbial Ecologist | field / mesocosm / amplicon & metagenomic community ecology | microbial-ecologist/AGENTS.md |
Reasons from Vellend assembly (selection, dispersal, drift, diversification), compositional stats (ANCOM-BC2, MaAsLin2, Aitchison), and SILVA/GTDB/EMP workflows; treats kitome contamination, GCN bias, pseudoreplication, SparCC-as-interaction, and PICRUSt2-as-measured-function as first-class failure modes. |
| Microbial Physiologist | wet-lab / chemostat & metabolic-flux physiology | microbial-physiologist/AGENTS.md |
Reasons from Monod/chemostat (μ = D), YX/S and Pirt maintenance, Crabtree/overflow, 13C-MFA and FBA, and BMSAB taxonomy; treats OD-as-biomass yield error, FBA-as-measured-flux, washout misread, and portable ms across media as first-class failure modes. |
| Microbiologist | wet-lab / culture, amplicon & shotgun microbiomics | microbiologist/AGENTS.md |
Reasons from culturability limits, CFU/MPN enumeration, selective media, DADA2/QIIME2 16S ASVs (SILVA/GTDB), and shotgun metagenomics (Kraken2, MetaPhlAn, HUMAnN); treats plate-count anomaly, compositional stats pitfalls, kit contamination, and index hopping as first-class failure modes. |
| Microbiome Scientist | cohort / intervention / multi-omics host–microbiome | microbiome-scientist/AGENTS.md |
Reasons from compositional and longitudinal stats (MaAsLin2, ANCOM-BC2), STORMS pre-analytics, FMT/LBP and diet trials, and multi-omics integration; treats PPI/antibiotic confounders, kitome contamination, host-DNA swamping, and HMA causality overclaim as first-class failure modes. |
| Microelectronics Engineer | packaging / assembly / thermal & reliability | microelectronics-engineer/AGENTS.md |
Reasons from CTE mismatch, θja networks (JESD51), and package RLC through wire bond (Au–Al IMC, loop height), flip-chip (UBM, underfill, HIP/NWO), J-STD-020 MSL, and JESD22 TCT/uHAST; treats datasheet θja without board definition, wire sweep, die-attach voids, and soak-mode mismatch as first-class failure modes. |
| Mineralogist | laboratory / field mineral identification / crystallography / economic mineralogy | mineralogist/AGENTS.md |
Reasons from crystal chemistry, Pauling coordination, and converging optics–XRD/Raman–EPMA evidence; uses RRUFF/Mindat/AMCSD and CNMNC Checklist 2025 while treating preferred orientation, clay EG/heat triads, metamict amorphization, and QEMSCAN library bias as first-class failure modes. |
| Mining Geologist | field / exploration drilling / ore deposit modelling / geostatistics / resource estimation | mining-geologist/AGENTS.md |
Reasons from deposit-type models (porphyry, VMS, SEDEX, orogenic Au, IOCG, skarn) through oriented core logging, domaining, variography, OK/MIK/LUC estimation, and Chain-of-Mining reconciliation to JORC Table 1, NI 43-101 Item 14, and CIM MRMR reporting; uses Leapfrog, GIM Suite/MX Deposit, and Parker F-series factors while treating support/compositing errors, batch QA/QC failures, OK smoothing bias, and Inferred-overclaim as first-class failure modes. |
| MLOps Engineer | ML lifecycle ops / feature stores & serving / drift monitoring / CI-CD-CT / registry promotion | mlops-engineer/AGENTS.md |
Reasons from data contracts, feature parity, evaluation gates, and rollback-readiness through MLflow/W&B registries, Feast feature stores, KServe/Triton serving, Great Expectations/TFDV validation, and Evidently PSI/KS drift monitors while treating train-serve skew, data leakage, silent degradation, and schema/concept drift as first-class failure modes. |
| Molecular Biologist | wet-lab / molecular genetics / functional genomics / assay validation (MIQE, ARRIVE 2.0) | molecular-biologist/AGENTS.md |
Reasons from central-dogma sequence flow, binding affinity (Kd/Km/kcat), gene regulation, and biological-versus-technical replicate structure through MIQE-compliant RT-qPCR, ddPCR, Western/flow/microscopy, CRISPR editing with rescue, and IWGAV antibody validation while treating off-target reagent effects, batch effects, mycoplasma and cell-line misidentification, and toxicity-driven artifacts as first-class failure modes. |
| Molecular Ecologist | field / lab / computational population & environmental genetics | molecular-ecologist/AGENTS.md |
Reasons from population genetics, eDNA/metabarcoding, and marker choice (microsatellites, SNPs, mtDNA); analyzes with STRUCTURE/ADMIXTURE, hierfstat FST, DADA2 pipelines, and ddPCR; treats null alleles, Wahlund effect, batch effects, and eDNA allelic dropout as first-class failure modes. |
| Molecular Geneticist | clinical / research | molecular-geneticist/AGENTS.md |
Reasons from sequence-as-hypothesis, reference context (genome build, MANE/RefSeq transcript, HGVS), and allele-level molecular consequence through ACMG/AMP-ClinGen criteria, IGV/VEP/SpliceAI/gnomAD/ClinVar review, MIQE-compliant qPCR/ddPCR, and Sanger/NGS validation while treating allele dropout, pseudogene/paralog misalignment, FFPE deamination, contamination and barcode bleed, and transcript/build mismatch as first-class failure modes. |
| Molecular Neuroscientist | wet-lab / synaptic biochemistry + optogenetics + viral tracing + region RNA-seq | molecular-neuroscientist/AGENTS.md |
Reasons from NPQ transmission, AMPAR/NMDAR trafficking, monoamine receptor/transporter systems, optogenetics (ChR2/Chrimson/ACR) with retinal-artifact controls, AAV/rabies circuit tracing, and region RNA-seq with DESeq2/SynGO—integrating synaptic biochemistry, perturbation, and omics while treating mini-detection bias, TVA leak, and batch/composition confounds as first-class failure modes. |
| Molecular Pathologist | clinical / anatomic & molecular diagnostic pathology | molecular-pathologist/AGENTS.md |
Reasons from tumor cellularity, assay-specific LOD, and AMP/ASCO/CAP Tier I–IV classification; validates IHC (CAP ≥90% concordance), FISH (HER2/ALK break-apart), and NGS oncology panels under CAP/CLIA MM09 while treating FFPE deamination, HER2-low/ultralow scoring, PD-L1 TPS vs CPS, and ctDNA CHIP as first-class failure modes. |
| Molecular Virologist | wet-lab / reverse genetics & virus–host molecular mechanism | molecular-virologist/AGENTS.md |
Reasons from Baltimore mRNA pathways, RNP/polymerase biochemistry, cap-snatching and expression strategy, CPER/BAC/trVLP rescue, protease cis/trans mapping, viral-factory LLPS, and CRISPR host-factor screens (Brunello/MAGeCK/replicon/TRPPC) with iCLIP/ChIP-seq—while treating CPER PCR errors, DIP packaging competition, minigenome structural-protein signal, and uninfected CRISPR dropout as first-class failure modes. |
| Mycobacteriologist | BSL-3 clinical microbiology / TB-NTM culture & molecular DST / WGS resistance genotyping / public-health reporting | mycobacteriologist/AGENTS.md |
Reasons from slow-growing acid-fast bacilli, knife-edge NALC-NaOH decontamination, and BSL-3 aerosol risk through MGIT culture, Xpert MTB/RIF and line-probe assays, MALDI-TOF and WGS resistance calls against the WHO mutation catalog while treating over-decontamination false negatives, laboratory cross-contamination pseudo-outbreaks, and NTM colonizer-versus-disease misclassification as first-class failure modes. |
| Mycologist | field / herbarium / culture & molecular systematics | mycologist/AGENTS.md |
Reasons from fungal life cycles, voucher-first taxonomy, and integrated sporocarp–culture–ITS/multilocus workflows; uses MycoBank/UNITE/MaarjAM, FUSARIUM-ID, EPPO Q-bank, and MycoCosm while treating rich-media non-sporulation, ITS saturation in Fusarium/Penicillium, AMF SSU vs ITS misuse, environmental-DNA-only names, and BSL-3 dimorphic mould handling as first-class failure modes. |
| Nanomaterials Scientist | colloidal synthesis / multi-modal characterization / nanoscale metrology / EHS-regulatory (ISO/TR 13014, OECD) | nanomaterials-scientist/AGENTS.md |
Reasons from size-dependent thermodynamics, surface-to-volume ratio, and DLVO colloidal stability through TEM/STEM statistics, DLS/NTA, XRD Scherrer, XPS, ICP-MS, and PL quantum-yield methods while treating aggregation, beam damage, intensity-weighted DLS sizing bias, and Ostwald ripening as first-class failure modes. |
| Nanophysicist | experimental / low-T transport / SPM / electron spectroscopy | nanophysicist/AGENTS.md |
Reasons from quantum confinement dimensionality, Coulomb diamonds and SET conditions, Kondo vs Luttinger-liquid power laws, and lock-in cryostat transport through STM/STS, AFM/KPFM, and STEM/EELS while treating charging artifacts, tip convolution, contact resistance, and beam-damage plasmon shifts as first-class failure modes. |
| Nanotechnologist | fabrication / integration / nanoscale devices & scale-up | nanotechnologist/AGENTS.md |
Reasons from length-scale manufacturing limits, EUV/NIL/EBL patterning, DSA defectivity, and interface-controlled integration through CD-SEM/AFM/TEM metrology, SEMI E10 yield discipline, and ISO 80004/FDA nanomaterial reporting while treating SEM shrinkage, NIL residual-layer non-uniformity, overlay error, and cherry-picked die yield as first-class failure modes. |
| Natural Language Processing Scientist | computational / language modeling, evaluation & alignment | natural-language-processing-scientist/AGENTS.md |
Reasons from tokenization, data curation (datatrove/NeMo), and evaluation protocols (SacreBLEU/COMET, IFEval, HELM); enforces contamination audits (ConTAM, perplexity separation), paired bootstrap significance, SFT→DPO/RLHF with alignment-tax checks, and ARR/Dodge reproducibility while treating exposure bias, benchmark leakage, prompt-template confounds, and metric gaming as first-class failure modes. |
| Natural Products Chemist | wet-lab / isolation & structure elucidation / metabolomics-guided discovery | natural-products-chemist/AGENTS.md |
Reasons from dereplication (GNPS FBMN, NPAtlas, SNAP-MS, COCONUT), bioassay-guided and MS-triggered isolation, NMR/HRMS structure tiers (DP4+/DU8+), antiSMASH/MIBiG BGC linkage, and PAINS/IMP assay interference while treating HMBC ambiguity, stereochemical misassignment, and aggregator false positives as first-class failure modes. |
| Naval Architect | ship & offshore design / hydrostatics / hydrodynamics / class compliance | naval-architect/AGENTS.md |
Reasons from displacement, Bonjean/KN–GZ stability, ITTC-78 resistance extrapolation, Wageningen B-series propulsion, WAMIT/NEMOH seakeeping, and IACS CSR scantlings while treating Froude/Re scale mismatch, free-surface GM error, Holtrop range violations, and trial CA bias as first-class failure modes. |
| Network Engineer | operations / design — campus, WAN, datacenter fabric | network-engineer/AGENTS.md |
Reasons from OSI layering, control vs. data plane, and path symmetry through BGP policy (TCP/179, communities, RR), OSPF areas/LSA adjacency, 802.1Q VLAN/trunk design, spine-leaf Clos/VXLAN-EVPN fabrics, and L1→L7 troubleshooting while treating asymmetric routing, MTU black holes, native-VLAN mismatch, and BGP OutQ/hold-time flaps as first-class failure modes. |
| Network Scientist | graph theory / community detection / generative models (SBM, ERGM) / network dynamics / null-model inference | network-scientist/AGENTS.md |
Reasons from adjacency structure, generative models, and null hypotheses through configuration-model and SBM/ERGM nulls, CSN power-law fitting with log-normal Vuong tests, and multi-algorithm community detection (Louvain, Leiden, Infomap, graph-tool) while treating artifactual scale-free tails from correlation thresholding, modularity's resolution bias, force-directed hairball over-interpretation, and test-edge leakage in link prediction as first-class failure modes. |
| Neuroanatomist | wet-lab histology / tract tracing + computational atlas registration | neuroanatomist/AGENTS.md |
Stereotaxic targeting and skull leveling, Paxinos/Allen atlases, anterograde/retrograde tracing, Nissl vs IHC, BrainGlobe/QuickNII registration, and injection-spread or fibers-of-passage artifacts. |
| Neuroendocrinologist | wet-lab / in vivo physiology + translational neuroendocrine | neuroendocrinologist/AGENTS.md |
Reasons from hypothalamic–pituitary portal axes (HPA, HPG, HPT), KNDy/GnRH pulsatility, SCN circadian gating, and SON/PVN neuropeptide release; uses HypoMap/HYPOMAP, stereotaxics with opto/chemogenetics, validated ELISA/RIA/FCM and LC-MS/MS, CoAL/CAR reporting, while treating bleed-stress corticosterone, pulse undersampling, assay-kit bias, and species translation as first-class failure modes. |
| Neuroengineer | wet-lab / neural interfaces / chronic electrophysiology / translational regulatory | neuroengineer/AGENTS.md |
Reasons from electrode–electrolyte charge-density limits and foreign-body gliosis through Utah/Neuropixels chronic recording, EIS impedance spectroscopy, Kilosort3/MountainSort validation, FDA IDE pathways, and explant histology (GFAP/Iba1) while treating impedance drift, unvalidated auto-sort inflation, and acute-to-chronic yield collapse as first-class failure modes. |
| Neuroimaging Scientist | clinical / research | neuroimaging-scientist/AGENTS.md |
Reasons from k-space acquisition physics, BOLD hemodynamics, and per-voxel statistical models through fMRIPrep/QSIPrep BIDS pipelines, FSL/SPM/nilearn analysis, neuroCombat harmonization, and TFCE/permutation inference while treating head motion, partial-volume and reference-region errors in PET, global-signal regression artifacts, and site over-correction as first-class failure modes. |
| Neuroinformatician | data standards / BIDS-NWB / reproducible pipelines / archive federation (DANDI, OpenNeuro) / atlas registration | neuroinformatician/AGENTS.md |
Reasons from FAIR schema, provenance, and pinned software environments through BIDS, NWB, ontologies, versioned Snakemake/Nextflow pipelines, and bids-validator/nwbinspector checks while treating silent metadata failures like wrong NWB units, colliding multi-site subject IDs, unsynced event onsets, and atlas-version mismatch as first-class failure modes. |
| Neurologist | clinical / research | neurologist/AGENTS.md |
Reasons from anatomic localization, time course, and phenomenology through NIHSS/ASPECTS stroke triage, ILAE 2025 seizure classification, McDonald 2017 and AQP4/MOG cell-based assays, EEG and EMG/NCS, and SNOOP4 red flags, while treating CT-negative early ischemia, ~50%-sensitive routine EEG, MS-versus-NMOSD/MOGAD misdiagnosis, and missed myasthenic-crisis respiratory decline as first-class failure modes. |
| Neuropharmacologist | wet-lab / in vitro pharmacology + in vivo behavioral PK/PD + translational imaging | neuropharmacologist/AGENTS.md |
Reasons from Kp,uu,brain and receptor occupancy, radioligand binding with depletion-aware Ki, biased GPCR/allosteric signaling, PDSP/GtoPdb panels, microdialysis and PET RO, and operant self-administration while treating Cheng-Prusoff error, P-gp efflux, FST validity limits, and patch-clamp Rs artifacts as first-class failure modes. |
| Neurophysiologist | wet-lab / intracellular & extracellular electrophysiology + spike sorting | neurophysiologist/AGENTS.md |
Reasons from membrane biophysics, patch clamp Rs/seal quality, Neuropixels AP/LF streams, LFP referencing and spike contamination, Kilosort4/Phy curation, and stimulation-artifact suppression. |
| Neuroscientist | integrative / multiscale circuits / in vivo electrophysiology + optogenetics / translational (ARRIVE, BIDS/NWB) | neuroscientist/AGENTS.md |
Expert profile for neuroscientist — see AGENTS.md for field-specific methods and failure modes. |
| Nonlinear Dynamics & Chaos Scientist | theoretical / computational / experimental dynamical systems | nonlinear-dynamics-chaos-scientist/AGENTS.md |
Reasons from flows, maps, bifurcations, and invariant sets; continues with MatCont/AUTO/COCO, validates chaos with IAAFT surrogates and embedding convergence, and treats spurious Lyapunov exponents, stiff integrator artifacts, and colored-noise confounds as first-class failure modes. |
| Nuclear Chemist | clinical / research | nuclear-chemist/AGENTS.md |
Reasons from decay-corrected activity ledgers, decay modes and cross sections, and ALARA dose control through Bateman/ORIGEN modeling, extraction-chromatography separations (TRU/Sr/TEVA resins), and HPGe/alpha/LSC spectroscopy while treating daughter ingrowth, generator breakthrough, spectral pile-up and sum peaks, and swipe-test cross-contamination as first-class failure modes. |
| Nuclear Engineer | reactor physics / thermal hydraulics / safety & licensing | nuclear-engineer/AGENTS.md |
Reasons from k_eff, DNBR/CHF margins, xenon transients, and defense-in-depth; couples SCALE/MCNP, PARCS, TRACE/RELAP, and MELCOR to 10 CFR and PRA; treats nodalization, nuclear-data, and CHF-correlation uncertainties as first-class failure modes. |
| Nuclear Medicine Scientist | clinical / research | nuclear-medicine-scientist/AGENTS.md |
Reasons from radioactive decay, biodistribution kinetics, and detector physics through HPLC/TLC radiochemical-purity QC, dose-calibrator cross-calibration, OSEM/PSF reconstruction, and MIRD/OLINDA dosimetry while treating partial-volume effects, attenuation mismatch, 68Ge breakthrough and other radionuclidic impurity, and unharmonized cross-center SUV as first-class failure modes. |
| Nuclear Physicist | experimental / theoretical / nuclear data & applications | nuclear-physicist/AGENTS.md |
Reasons from shell and collective structure, reaction mechanisms, and ENDF/EXFOR data; matches FRIB–CEBAF–RHIC science to R-matrix, Hauser-Feshbach, chiral ab initio, and GEANT4 tools; treats dead time, normalization, and evaluation covariances as first-class failure modes. |
| Number Theorist | theoretical / computational pure and arithmetic number theory | number-theorist/AGENTS.md |
Reasons from primes, congruences, L-functions, and the Langlands web; chooses algebraic, analytic, and sieve methods; validates with SageMath/PARI/LMFDB while treating PARI stack overflows, conditional-proof leaks, and CRT moduli errors as first-class failure modes. |
| Numerical Analyst | theoretical / computational scientific computing | numerical-analyst/AGENTS.md |
Reasons from well-posedness, discretization, conditioning, and stability; verifies codes with MMS and convergence studies; treats cancellation, stiffness, and solver tolerance floors as first-class failure modes. |
| Nutrition Scientist | nutritional epidemiology / controlled feeding trials / dietary assessment & biomarker validation / survey analysis (NHANES, DLW) | nutrition-scientist/AGENTS.md |
Reasons from intake measurement error, energy balance, and causal triangulation through doubly-labeled-water validation, NCI usual-intake models, DRI (EAR/RDA/UL) frameworks, crossover feeding trials, and Mendelian randomization while treating dietary underreporting, reverse causation (sick-quitter), unadjusted total-energy confounding, and weight-loss-versus-macronutrient attribution as first-class failure modes. |
| Observational Astronomer | multi-wavelength observational / calibration & photometry / time-domain & transients / Bayesian inference / multi-messenger | observational-astronomer/AGENTS.md |
Reasons from radiative transfer, the distance ladder, and statistical-versus-systematic error budgets through HST/JWST/ALMA pipelines, Gaia DR3 astrometry, archives (SIMBAD, MAST, HEASARC), and emcee/dynesty inference while treating the look-elsewhere effect, PSF and flat-field artifacts, photo-z catastrophic outliers, and Malmquist/Eddington selection bias as first-class failure modes. |
| Occupational Health Scientist | industrial hygiene / exposure assessment / occupational epidemiology / sampling and OELs (PEL, TLV, REL) / hierarchy of controls | occupational-health-scientist/AGENTS.md |
Reasons from exposure route and receptor, dose-response, and the hierarchy of controls through SEG-based personal sampling, NIOSH/OSHA analytical methods, AIHA Bayesian exceedance statistics, and SMR cohort analysis, while treating healthy worker effect, below-LOD censoring, fraction-size and OEL mismatch, and JEM misclassification as first-class failure modes. |
| Oceanographer | seagoing / interdisciplinary / water-mass & tracer analysis / air-sea flux & biogeochemistry / TEOS-10 | oceanographer/AGENTS.md |
Reasons from basin-scale budgets, three-dimensional circulation, and forcing-transport-transformation coupling through θ–S and OMP water-mass analysis, transient-tracer ventilation ages (CFC/SF₆/¹⁴C), GO-SHIP/Argo/SOCAT networks, and TEOS-10 thermodynamics while treating mesoscale aliasing of single sections, mixed real-time and delayed-mode QC, and freshwater-driven salinity confounds as first-class failure modes. |
| Oncologist | clinical / multidisciplinary oncology | oncologist/AGENTS.md |
Stages with AJCC TNM and molecular prognostic groups, selects biomarker-matched therapy from NCCN guidelines, assesses response with RECIST 1.1/iRECIST, and interprets trial endpoints with calibrated clinical judgment. |
| Operations Researcher | optimization modeling / stochastic & robust programming / discrete-event simulation / VRP & scheduling / production solve ops (ERP/WMS/TMS) | operations-researcher/AGENTS.md |
Reasons from decision structure, integrality and convexity, and explicit uncertainty through LP/MIP solvers (Gurobi, CPLEX, OR-Tools CP-SAT), stochastic and Wasserstein-distributionally-robust formulations, and DES (SimPy, AnyLogic) benchmarked on Solomon/MIPLIB instances, while treating unit inconsistencies, optimality-gap-versus-stale-data trade-offs, infeasibility (IIS) from forgotten labor and fairness constraints, and day-to-day solution oscillation as first-class failure modes. |
| Ophthalmologist | clinical / retina, glaucoma & vision trials | ophthalmologist/AGENTS.md |
Reasons from structure–function pairing (OCT RNFL/CST, HVF MD/VFI, ETDRS BCVA); manages glaucoma IOP targets and anti-VEGF treat-and-extend while treating field learning effect, OCT floor effect, and 15-letter regulatory margins as first-class failure modes. |
| Optical Physicist | ultracold AMO / laser cooling & trapping / optical lattices & tweezers / precision clocks / quantum simulation | optical-physicist/AGENTS.md |
Reasons from quantized atom-field coupling, recoil and trap energy scales (Γ, E_rec, U/J, κ), and coupled instability-versus-systematic budgets through optical Bloch equations, in-situ lattice-depth and Rabi calibration, QuTiP and ARC modeling, and Allan-deviation and clock systematic tables, while treating uncalibrated lattice depth, intensity-noise heating, double-occupancy mimicking unity filling, and missing BBR or AC-Stark shifts as first-class failure modes. |
| Optimization Scientist | computational / mathematical optimization | optimization-scientist/AGENTS.md |
Reasons from convexity class, KKT/complementarity, and LP/MIP relaxation gaps through interior-point and branch-and-cut (Gurobi, CPLEX, MOSEK, Ipopt) while treating loose big-M, IntegralityTol cheaters, IIS-hidden infeasibility, nonconvex KKT-as-global, and MIPGap-at-TimeLimit-as-optimal as first-class failure modes. |
| Optoelectronics Engineer | device R&D / characterization / PIC & semiconductor photonics | optoelectronics-engineer/AGENTS.md |
Reasons from photon–electron conversion, ABC recombination, and IQE/EQE/WPE budgets; runs LIV/pulsed laser, EMVA 1288, and responsivity metrology; designs with Lumerical/Sentaurus/COMSOL TCAD and foundry PDKs while treating efficiency droop, thermal rollover, LIV kinks, and calibration geometry as first-class failure modes. |
| Oral Biologist | clinical / research | oral-biologist/AGENTS.md |
Reasons from biofilm dysbiosis, demineralization-remineralization balance, and host-mineral-microbe partitioning through pH-cycling and ligature models, 16S/shotgun metagenomics (DADA2/QIIME2, HOMD), micro-CT, and ICDAS/AAP-EFP staging, while treating saliva-ignored caries models, low-biomass contamination, probe-force inconsistency, and unconfounded oral-systemic claims as first-class failure modes. |
| Organic Chemist | wet-lab / synthetic and methods organic chemistry | organic-chemist/AGENTS.md |
Reasons from retrosynthesis, protecting-group strategy, and stereoelectronics; executes air-sensitive chemistry, flash/LC-MS purification, and NMR/IR/MS proof; mines SciFinder/Reaxys and reports ACS-grade experimentals with E-factor/PMI and pyrophoric safety discipline. |
| Organoid Biologist | wet-lab / stem-cell and 3D epithelial culture | organoid-biologist/AGENTS.md |
Reasons from niche signaling, Matrigel scaffolds, and culture geometry; engineers Wnt/R-spondin expansion, ALI differentiation, and PDO biobanks while treating matrix lot effects and donor-level pseudoreplication as first-class failure modes. |
| Organometallic Chemist | air-sensitive synthesis / homogeneous catalysis / multinuclear NMR & SCXRD / mechanistic kinetics | organometallic-chemist/AGENTS.md |
Reasons from electron counting, oxidation states, and elementary catalytic steps through Schlenk/glovebox technique, multinuclear NMR and νCO IR, SCXRD with checkCIF, and TON/TOF kinetics while treating air oxidation to oxo/hydroxo species, paramagnetic line-broadening, and trace or colloidal-metal leaching as first-class failure modes. |
| Ornithologist | field / observational / banding / bioacoustics / population monitoring | ornithologist/AGENTS.md |
Reasons from detectability-limited surveys through BBS/MAPS protocols, distance sampling and unmarked occupancy, eBird/auk hygiene, BirdNET–Raven validation, BBL permitting, Pyle molt scoring, MOTUS/FlightR connectivity, and AviList/Clements taxonomy while treating roadside bias, space-for-time pseudo-replicates, and AI false positives as first-class failure modes. |
| Orthopedic Biomechanist | clinical / research | orthopedic-biomechanist/AGENTS.md |
Reasons from joint kinematics, forces, moments, and tissue stress through optical motion capture with force plates, inverse dynamics with de Leva segment parameters, OpenSim/AnyBody and FEBio/Abaqus models, and ISO 14243 wear testing while treating skin motion artifact, cardan gimbal lock, unnormalized moments, and over-read FEA stress hotspots as first-class failure modes. |
| Paleobotanist | field / laboratory paleobotany & palynology | paleobotanist/AGENTS.md |
Reasons from phytotaphonomy and preservation mode (compression, permineralization, palynomorphs); prepares coal-ball peels and cuticle/maceral workflows; applies LMA/CLAMP/DiLP and stomatal/Franks CO₂ proxies; uses PBDB, Neotoma, IFPNI/PFNR, and ICN fossil-taxon nomenclature while treating transport bias, organographic filters, and laboratory acid loss as first-class failure modes. |
| Paleoceanographer | field / observational marine paleoceanography | paleoceanographer/AGENTS.md |
Reasons from foraminiferal proxy system science (G. ruber, Cibicidoides, species/size fraction), Barker Mg/Ca cleaning and Anand/Gray calibrations, paired planktic δ¹⁸O–Mg/Ca and LR04 benthic stacks, IODP depth scales and splice ties, and AMOC fingerprints (benthic δ¹³C gradients, εNd, ²³¹Pa/²³⁰Th, sortable silt) while treating clay contamination, orbital-tuning circularity, Pa/Th scavenging, and bioturbation mixing as first-class failure modes. |
| Paleoclimatologist | proxy reconstruction / chronology & age modeling / spectral & cyclostratigraphy / model-data comparison (PMIP, DeepMIP) | paleoclimatologist/AGENTS.md |
Reasons from proxy transfer functions, archive integration time, and orbital forcing through Bayesian age-depth modeling (Bacon, OxCal), IntCal20 radiocarbon calibration, PAGES2k compositing, and proxy-equivalent PMIP/DeepMIP comparison while treating age-model uncertainty, non-stationary calibration (CO2 fertilization, divergence), diagenesis, and single-site-as-global-anomaly claims as first-class failure modes. |
| Paleontologist | field / museum / computational | paleontologist/AGENTS.md |
Reason from taphonomic filters first: biostratinomy, diagenesis, time-averaging, and Signor–Lipps before biostratigraphic correlation, morphometrics, or phylogenetic claims. |
| Palliative Care Researcher | clinical trials / symptom science / patient-reported outcomes / health services / reporting (CONSORT-PRO, SPIRIT, PCORI) | palliative-care-researcher/AGENTS.md |
Reasons from serious-illness trajectories, multidimensional symptom burden, goals-of-care concordance, and caregiver dyad outcomes through validated PROMs (ESAS-r, IPOS, FACIT-Pal), prespecified MCID responder analysis, mixed-effects and joint survival-QoL models, and CONSORT-PRO/SPIRIT/PCORI reporting while treating death-related attrition, unjustified proxy substitution, inconsistent palliative-care exposure definitions, and hospice-versus-consult conflation as first-class failure modes. |
| Parasitologist | field / laboratory parasitology + public-health surveillance | parasitologist/AGENTS.md |
Reasons from parasite life cycles, WHO NTD program logic, and diagnostic performance (Kato-Katz, qPCR/MIQE, RDTs); troubleshoots microscopy artifacts, MDA surveillance, and anthelmintic resistance. |
| Particle Physicist | experimental / phenomenological high-energy physics | particle-physicist/AGENTS.md |
Reasons from SM gauge structure, parton PDFs, and detector response through ATLAS/CMS/LHCb/Belle II/DUNE workflows, Geant4+Pythia/MG5 simulation, HistFactory/Combine/pyhf likelihoods, and HEPData/Rivet preservation while treating LEE/global significance, JES/pile-up, fake leptons, and flux×cross-section systematics as first-class failure modes. |
| Pathologist | clinical / research | pathologist/AGENTS.md |
Reasons from H&E morphology, pretest-probability differentials, and pre-analytic integrity through CAP synoptic protocols, staged IHC and FISH panels, WHO/AJCC grading and staging, and Bethesda/Paris/Milan cytology systems while treating crush artifact, fixation/decalcification failure, single-frozen-section overcall, and IHC-without-morphology as first-class failure modes. |
| Pavement Engineer | mechanistic-empirical design / flexible & rigid pavements / NDE & forensics / asset management (MEPDG, FWD) | pavement-engineer/AGENTS.md |
Reasons from layered-elastic stress/strain, traffic spectra, climate, and material temperature-dependence through AASHTOWare Pavement ME (MEPDG) hierarchical inputs, FWD deflection-basin backcalculation with GPR/core thickness, binder PG selection, and LTPP-calibrated transfer functions, while treating mis-specified traffic, seasonal moisture-weakened subgrade, reflective cracking, and construction segregation as first-class failure modes. |
| Pedologist | soil survey / pedon morphology / classification (USDA Taxonomy, WRB) / micromorphology / digital soil mapping | pedologist/AGENTS.md |
Reasons from CLORPT factors, genetic horizons, and catenary position through the USDA Field Book, Soil Taxonomy and WRB 2022 keys, XRD clay mineralogy, micromorphology, and NASIS/SSURGO correlation while treating colluvial-versus-illuvial Bt confusion, lithologic discontinuities, surface-color-alone drainage calls, and digital-map covariate leakage as first-class failure modes. |
| Petrochemist | refinery process chemistry / crude assay / fuels & lubricants spec testing / catalyst performance / standards (ASTM D02, EN 228/590) | petrochemist/AGENTS.md |
Reasons from boiling range, hydrocarbon class, sulfur/nitrogen speciation, and octane/cetane drivers through SimDist and PIONA/SARA group-type analysis, CFR-engine RON/MON and cetane testing, refinery LP models, and ASTM/EN spec methods, while treating light-ends loss, assay mismatch versus plant yields, catalyst end-of-run deactivation, and asphaltene instability as first-class failure modes. |
| Petroleum / Reservoir Engineer | field development / dynamic subsurface (MBE, PTA, simulation, reserves) | petroleum-reservoir-engineer/AGENTS.md |
Reasons from Darcy flow, Havlena–Odeh MBE, Fetkovich/VEH aquifers, Horner/derivative PTA, Buckley–Leverett/Welge floods, Eclipse/CMG/tNavigator history match, PRMS/SEC reserves (P90/P50/P10), and SPE11 CO₂ benchmarks; treats transient Arps b>1, negative-skin grid artifacts, and microseismic≠SRV as first-class failure modes. |
| Petroleum Geologist | exploration / appraisal / development geoscience | petroleum-geologist/AGENTS.md |
Reasons from petroleum-system elements (kerogen I–IV, kitchens, critical moment), trap/spill-point and SGR fault seal, AVO/DHI and inversion QC, Archie/Simandoux/NMR petrophysics with Monte Carlo STOIIP, and PetroMod 1D–3D charge migration; treats tuning flat spots, post-trap charge, and uncorrected Archie Sw as first-class failure modes. |
| Petrologist | igneous/metamorphic petrology / petrography / EPMA-LA-ICP-MS microanalysis / thermodynamic modeling (Perple_X, THERMOCALC, MELTS) / thermobarometry | petrologist/AGENTS.md |
Reasons from Gibbs free energy minimization, the phase rule, and protolith-specific facies assemblages through petrography, EPMA/LA-ICP-MS microanalysis, pseudosections (Perple_X, THERMOCALC, MELTS), and classical thermobarometry while treating retrograde overprinting, serpentinization, propylitic alteration mimicking grade, and EPMA analytical scatter mistaken for P-T trends as first-class failure modes. |
| Phage Biologist | wet-lab / phage isolation, genomics, and phage-therapy R&D | phage-biologist/AGENTS.md |
Reasons from lytic vs lysogenic cycles, PFU/MOI/Poisson kinetics, one-step growth and EOP host-range matrices, PhagesDB/Phamerator/Pharokka genomics, and CRISPR/restriction escape—treating prophage immunity, defective particles, and therapy integrase scans as first-class failure modes. |
| Pharmaceutical Formulation Scientist | formulation development / QbD-CMC / solid-state & dissolution / regulatory (ICH Q8, USP, Module 3.2.P) | pharmaceutical-formulation-scientist/AGENTS.md |
Anchor every decision in the QTPP and critical quality attributes (CQAs): assay, Classify the API before choosing a technology path. Use BCS (solubility vs. |
| Pharmacokineticist | clinical / research | pharmacokineticist/AGENTS.md |
Reasons from mass balance, exposure-response, and separation of structural from statistical models through NCA in Phoenix WinNonlin, mixed-effects popPK in NONMEM, PBPK in Simcyp/GastroPlus, and VPC diagnostics while treating BLQ mishandling, ETA shrinkage, over-parameterization for small n, and unit/analyte/matrix errors as first-class failure modes. |
| Pharmacologist | wet-lab / in vitro pharmacology / drug discovery | pharmacologist/AGENTS.md |
Reasons from receptor occupancy, Black–Leff τ, EC50/IC50/Kd/Ki distinctions, Schild/Cheng–Prusoff antagonism, allosteric PAM/NAM cooperativity, GPCR bias, and PK/PD linkage; interprets binding/functional/HTS via GtoPdb/ChEMBL while treating spare receptors, radioligand depletion, and assay autofluorescence as first-class failure modes. |
| Pharmacovigilance Scientist | regulatory / drug safety surveillance (clinical & post-marketing) | pharmacovigilance-scientist/AGENTS.md |
Reasons from ICSR validity, MedDRA/SMQ coding, seriousness/expectedness/listedness, WHO-UMC causality, and PRR/ROR/IC/EBGM signal workflows through E2B(R3), EudraVigilance/FAERS/VigiBase, GVP Modules VI–IX, and PSUR/PBRER/RMP while treating duplicates, MLM scope, innocent-bystander confounding, and Weber/stimulated reporting as first-class failure modes. |
| Photochemist | photophysics / excited-state spectroscopy / actinometry / time-resolved (TCSPC, flash photolysis) / photoredox & solar chemistry | photochemist/AGENTS.md |
Reasons from Jablonski diagrams, quantum yields, and excited-state potential energy surfaces through ferrioxalate actinometry, TCSPC and transient-absorption flash photolysis, Stern–Volmer quenching, and TDDFT/CASPT2 calculations while treating inner-filter distortion, oxygen-sensitive triplet pathways, photodegradation mistaken for reaction, and emission from impurities as first-class failure modes. |
| Photonics Engineer | design / simulation / characterization / optical systems & PIC | photonics-engineer/AGENTS.md |
Reasons from Maxwell modes, FSR–Q–coupling trade-offs, and optical power/loss budgets; designs PICs and free-space systems with FDTD/INTERCONNECT/Zemax/GDSFactory and certifies links with OLTS/OTDR/M² while treating mesh dispersion errors, TE/TM birefringence, APC/PC connector mismatch, OTDR ghost/gainer events, and Fabry–Pérot convolution artifacts as first-class failure modes. |
| Photonics Scientist | research / integrated photonics / nonlinear optics | photonics-scientist/AGENTS.md |
Reasons from guided-wave dispersion, ring FSR–Q–coupling, and FWM phase matching; designs waveguides, lasers, and modulators with Lumerical MODE/FDTD/CHARGE/INTERCONNECT while treating dispersive FSR mismatch, TPA/FCA/XPM detuning, mesh dispersion, etalon ripples, and thermal bistability as first-class failure modes. |
| Photovoltaics / Solar Cell Scientist | device characterization / loss-budget analysis / c-Si & perovskite tandem / module reliability (IEC 61215/61730) | photovoltaics-solar-cell-scientist/AGENTS.md |
Reasons from the Shockley-Queisser detailed-balance limit and the diode coupling of Voc, Jsc, FF, and Rs/Rsh through light I-V, Suns-Voc implied Voc, EQE integration, lifetime mapping (QSSPC, μ-PCD, DLTS), and IEC 60904/61215 qualification while treating spectral mismatch, surface-recombination and shunt losses, perovskite hysteresis and ion migration, and PID/LID-LeTID degradation as first-class failure modes. |
| Phylogeneticist | computational / molecular & morphological systematics | phylogeneticist/AGENTS.md |
Reasons from Hennigian homology and MSC/coalescent-aware species trees through MAFFT/trimAl alignment, IQ-TREE 3 ModelFinder and gCF/sCF/gDF discordance, ASTRAL/ASTRAL-Pro 2/BEAST2 FBD dating, bPP/BFD* delimitation, and MIAPA/TreeBASE provenance while treating LBA, mis-rooting, compositional heterogeneity, gene flow, rogue taxa, and bootstrap-vs-posterior conflation as first-class failure modes. |
| Physical Chemist | wet-lab / calorimetry (DSC, ITC) / spectroscopy (FTIR, Raman, UV-vis) / kinetics / statistical thermodynamics | physical-chemist/AGENTS.md |
Reasons from state functions, partition functions, rate laws, and selection rules through Eyring and van't Hoff fits, DSC/ITC calorimetry, and stopped-flow spectroscopy anchored to NIST thermochemical data, while treating inner-filter and aggregation artifacts, curved Arrhenius plots from mechanism change, and concentration-for-activity substitution as first-class failure modes. |
| Physical Oceanographer | observational / field / computational ocean physics | physical-oceanographer/AGENTS.md |
Reasons from geostrophy, thermal wind, PV, and Ekman/Sverdrup balances; integrates GO-SHIP/CCHDO sections, Argo DMQC, DUACS/CMEMS altimetry, and ROMS/MITgcm/NEMO validation while treating reference-level transport ambiguity, Argo conductivity drift, and MDT/alias artifacts as first-class failure modes. |
| Physician-Scientist | clinical / translational / basic and patient-oriented research | physician-scientist/AGENTS.md |
Reasons across the bedside–bench cycle and T0–T4 spectrum; navigates PSTP/ABIM pathways, K08/K23/R01 funding, IRB/IND/IDE sponsor-investigator duties, and CONSORT/SPIRIT reporting while treating protected-time loss and preclinical irreproducibility as first-class failure modes. |
| Planetary Geologist | remote sensing / GIS / planetary surfaces (Mars, Moon) | planetary-geologist/AGENTS.md |
Reasons from stratigraphy and landform genesis through ISIS/GDAL/JMARS/ArcGIS, CraterTools/CSFD Tools/CraterStats2 chronology, CRISM/M3/THEMIS spectroscopy with SPLib/RELAB, and PDS archives while treating secondaries, projection/datums, and production-function choice as first-class failure modes. |
| Planetary Scientist | solar-system / remote-sensing & in situ / exoplanet detection-characterization / mission archives (PDS, SPICE) | planetary-scientist/AGENTS.md |
Expert profile for planetary scientist — see AGENTS.md for field-specific methods and failure modes. |
| Plant Breeder | field breeding / quantitative & molecular genetics / genomic selection / METs / cultivar release (DUS, UPOV/OECD) | plant-breeder/AGENTS.md |
Reasons from genetic variance, selection response (R = h²S), and breeding values through BLUP/GBLUP mixed models, multi-environment alpha-lattice trials with check cultivars, genomic selection validated within relatedness, and DUS/seed-certification standards, while treating linkage drag, G×E and G×management rank inversions, unvalidated GWAS hits, and seed mix-ups or off-type contamination as first-class failure modes. |
| Plant Pathologist | diagnostic clinic / field epidemiology / wet-lab & molecular phytopathology | plant-pathologist/AGENTS.md |
Reasons from the disease triangle, sign vs. symptom, and trophic strategy (biotroph/necrotroph/hemibiotroph); runs clinic-to-Koch workflows (TWA isolation, Phytophthora pear baiting, Baermann nematodes, EPPO PM7/qPCR with matrix-specific Ct cutoffs) and epidemic analysis (AUDPC/AUDPS, Vanderplank parameters, GLMMs) while treating abiotic mimicry, saprophyte overgrowth, and late-cycle PCR artifacts as first-class failure modes. |
| Plant Physiologist | wet-lab / greenhouse / field plant physiology | plant-physiologist/AGENTS.md |
Reasons from source–sink carbon–water balance, FvCB A–Ci and Ball–Berry gs models, LI-COR/PAM gas exchange, Scholander Ψ, drought–salt–heat signaling, and MIAPPE/Phytozome workflows while treating chamber leakage, pot-bound roots, and Fv/Fm–yield conflation as first-class failure modes. |
| Plasma Physicist | fusion + space plasma / MHD & gyrokinetic / PIC simulation / tokamak-stellarator diagnostics / reconnection | plasma-physicist/AGENTS.md |
Reasons from collective scales (Debye length, plasma frequency), dimensionless regime parameters (beta, collisionality, Lundquist number), and instability drive-versus-dissipation through Grad-Shafranov equilibria (EFIT, VMEC), gyrokinetic and MHD codes (GENE, NIMROD, XGC), PIC simulation (VPIC, OSIRIS), and confinement scalings (IPB98, Greenwald, Troyon) while treating probe sheath distortion, equilibrium-reconstruction error, resolution-limited reconnection rates, and unmatched wall conditioning as first-class failure modes. |
| Pollution Control Engineer | design / engineering / regulatory compliance | pollution-control-engineer/AGENTS.md |
Reasons from PTE, Title V Part 70, and NPDES limits through scrubber/baghouse/ESP/RTO selection, CEMS and stack-test demonstration, and parametric O&M (ΔP, pH, L/G) while treating synthetic-minor strategy, sulfite-blinded FGD, bag leaks, and WET/TIE toxicity as first-class failure modes. |
| Polymer Chemist | wet-lab / synthetic polymer chemistry | polymer-chemist/AGENTS.md |
Designs and interprets polymer synthesis, characterization, and structure–property relationships from mechanism (chain-growth, step-growth, RDRP, ROMP) through absolute MW verification to application-relevant thermal and rheological data. |
| Polymer Scientist | synthesis / characterization / rheology-morphology / polymer processing / failure analysis | polymer-scientist/AGENTS.md |
Reasons from molecular weight distribution, Tg/Tm and crystallinity, viscoelasticity, and phase behavior through GPC/SEC, DSC heat-cool-heat, capillary and oscillatory rheology, WAXD/SAXS, and DMA while treating thermal-history erasure, moisture hydrolysis, incomplete cure, and wrong-grade-lot artifacts as first-class failure modes. |
| Population Geneticist | dry-lab / computational population genomics | population-geneticist/AGENTS.md |
Reasons from Wright–Fisher/coalescent demography, Weir–Cockerham FST, EIGENSOFT PCA, ADMIXTURE ancestry, ADMIXTOOLS f-statistics, and selscan XP-EHH/iHS/PBS selection scans while treating batch confounding, LD pruning choices, cryptic relatedness, and admixture-LD artifacts as first-class failure modes. |
| Poultry Scientist | pen/house trials / nutrition & feed formulation / gut health & coccidiosis / hatchery & incubation / processing yield / poultry welfare | poultry-scientist/AGENTS.md |
Reasons from flock-level feed-to-gain conversion, digestible amino acid balance, and thermal/respiratory/pathogen load through FCR/EPEF and HDEP/HOF metrics, pen-or-house mixed models, coccidiosis lesion scoring, hatchery break-out, and strain management guides while treating subclinical coccidiosis and necrotic enteritis, wet-litter footpad dermatitis, pseudoreplicated subsampling, and woody-breast myopathy as first-class failure modes. |
| Power Electronics Engineer | converter design / magnetics / WBG semiconductors / loop-gain control / EMI-EMC / regulatory (CISPR, IEC 61000-3-2, IEEE 1547.1) | power-electronics-engineer/AGENTS.md |
Reasons from volt-second and charge balance, switched-mode energy transfer, and small-signal loop gain through PLECS/LTspice/SIMPLIS simulation, Steinmetz and Dowell magnetics loss accounting, Bode injection on hardware, and LISN-based EMI scans while treating shoot-through, RHP-zero subharmonic oscillation, Qrr and ZVS-window loss, and CM-choke saturation as first-class failure modes. |
| Power Grid Engineer | transmission / protection / planning / NERC compliance | power-grid-engineer/AGENTS.md |
Reasons from AC power flow, N-1 contingency, and relay coordination through PSS/E studies, distance/differential protection, IBR/IEEE 2800 models, COMTRADE event analysis, and NERC TPL/PRC standards while treating EMS topology drift, voltage collapse, and ATC vs nameplate as first-class failure modes. |
| Power Systems Engineer | power flow / protection coordination / DER hosting / stability & EMT / standards (NERC TPL, IEEE 1547, IEC 60909) | power-systems-engineer/AGENTS.md |
Reasons from per-unit impedances, symmetrical components, swing equations, and relay reach through PSS/E, OpenDSS, Aspen OneLiner, PSCAD, and NERC TPL/IEEE 1547/IEC 60909 criteria while treating loss of protection selectivity, DER-driven reverse power flow and voltage rise, CT saturation, and voltage collapse as first-class failure modes. |
| Precision Agriculture Specialist | site-specific crop management / VRT prescriptions / remote & proximal sensing / RTK-GNSS & ISOBUS / yield-map QA | precision-agriculture-specialist/AGENTS.md |
Reasons from management-zone heterogeneity, the spatial 4R (right input, rate, place, time), and per-zone margin maps through SSURGO/ECa zone delineation, NDVI/NDRE indices, RTK-GNSS georeferencing, and ISOBUS Task Controller as-applied logs while treating planned-versus-applied divergence, NDVI saturation, miscalibrated yield-monitor mass-flow and lag, and RTK float passes as first-class failure modes. |
| Precision Engineering Specialist | GD&T / CMM metrology / ultra-precision manufacturing | precision-engineering-specialist/AGENTS.md |
Reasons from ASME Y14.5 GD&T, GUM uncertainty, and micrometer error budgets through CMM programming (ISO 10360), volumetric compensation, UPDT/STS diamond turning, and ISO 14253 decision rules while treating datum mis-simulation, MMC bonus omission, and CMM program drift as first-class failure modes. |
| Precision Medicine Scientist | clinical / research | precision-medicine-scientist/AGENTS.md |
Reasons from molecular profiles, tiered actionability, tumor purity, and clonal architecture through OncoKB and AMP/ASCO/CAP tiers, Mutect2/STAR-Fusion calling, IGV review, and CPIC pharmacogenomic guidelines while treating FFPE C-to-T deamination, CHIP mimicking somatic drivers, immortal-time bias in real-world data, and ancestry-skewed polygenic scores as first-class failure modes. |
| Primatologist | field / observational ethology / conservation / comparative & captive research | primatologist/AGENTS.md |
Reasons from Tinbergen questions, habituation trade-offs, and phylogenetic comparative trees (TimeTree, Craig 2024) through focal/scan ethograms (BORIS, κ), Raven/Praat vocal repertoires, IUCN SSC great-ape surveys (A.P.E.S.), and CITES/IACUC/IPS health protocols while treating pseudoreplication, anthroponotic disease, nest-decay bias, and phylogenetic non-independence as first-class failure modes. |
| Probabilist | theoretical / computational probability | probabilist/AGENTS.md |
Reasons from Kolmogorov measure spaces through LLN/CLT, martingales, coupling, concentration/LDP, and Lévy/Feller/Itô calculus; uses Durrett/Kallenberg canon, Sage/NumPy/PyMC simulation, and R̂/ESS/IS diagnostics while treating a.s. vs sure, Borel conditioning, OST misuse, and importance-weight explosion as first-class failure modes. |
| Process Chemist | API/route development / scale-up & reaction engineering / crystallization & PAT / regulatory (ICH Q8-Q11, M7, QbD) | process-chemist/AGENTS.md |
Reasons from mass and energy balances, impurity fate maps, and supersaturation trajectories through RC1 calorimetry, DoE in JMP/MODDE, FBRM/XRPD crystallization tracking, and ICH Q8/Q9/Q11 control strategy while treating exotherm runaway at plant jacket capacity, ICH M7 genotoxic carry-over, polymorph shifts on scale, and unvalidated PAT release as first-class failure modes. |
| Process Engineer | process design / simulation / commissioning & plant troubleshooting | process-engineer/AGENTS.md |
Reasons from conservation laws, CSTR/PFR selectivity and RTD/Da scale-up through BFD→PFD→P&ID/HAZOP/LOPA/SIL, Aspen Plus/HYSYS HMB, API 520/521 relief and LMTD/F_t exchanger sizing, and lab→pilot→plant commissioning while treating frozen-design violations, simulation-without-data, and BPCS/IPL conflation as first-class failure modes. |
| Programming Languages Researcher | formal semantics / type systems / mechanized metatheory (Coq/Ott) / verification / POPL-PLDI | programming-languages-researcher/AGENTS.md |
Reasons from operational semantics, type-theoretic invariants, and soundness as preservation-plus-progress through Ott/LN-defined calculi, Coq/Isabelle/Agda mechanization, Hindley-Milner inference, and abstract-interpretation Galois connections while treating stuck terms, blame escaping onto well-typed pure terms, broken substitution and canonical-forms lemmas, and unsound widening as first-class failure modes. |
| Propulsion Engineer | engine design / hot-fire test / combustion stability / rockets-airbreathing-EP / cycle analysis | propulsion-engineer/AGENTS.md |
Reasons from thrust, specific impulse, characteristic velocity c*, thrust coefficient Cf, and NPSH through NASA CEA, RPA and NPSS cycle models, hot-fire thrust stands, and ROCCID/bomb-test stability screening while treating nozzle separation, inducer cavitation, chugging/screech combustion instability, and scramjet unstart as first-class failure modes. |
| Protein Engineer | directed evolution / display selection / biophysical characterization / ML-guided design / developability | protein-engineer/AGENTS.md |
Reasons from sequence-structure-function relationships, evolutionary constraint, and multiparameter developability through display selection, ProteinMPNN/RFdiffusion and AlphaFold modeling, SPR/BLI kinetics, and SEC/DSF/CE-SDS characterization while treating aggregation, Tm loss, proteolysis, glycoform mismatch, and immunogenic neo-epitopes as first-class failure modes. |
| Proteomics Scientist | bottom-up LC-MS/MS / DDA-DIA-TMT-SILAC / differential abundance / FDR & batch control | proteomics-scientist/AGENTS.md |
Reasons from peptide-to-protein inference, acquisition mode, quantification modality, and missing-value mechanism through MaxQuant, FragPipe/MSFragger, DIA-NN/Spectronaut, Skyline, and MSstats/proDA while treating MNAR missingness, batch confounding, TMT co-isolation ratio compression, and keratin/contaminant signal as first-class failure modes. |
| Protistologist | microscopy / 18S metabarcoding (PR2/SILVA) / culture & barcoding / HAB monitoring / paleoecology | protistologist/AGENTS.md |
Reasons from eukaryotic microbial diversity, trophic mode, and morphology-molecule integration through Utermöhl counts, SEM, 18S/V4 metabarcoding with PR2/SILVA, and IQ-TREE/MAFFT phylogenies while treating chimeric ASVs, kleptoplastic mixotroph misclassification, dinoflagellate multi-copy rRNA inflation, and reads-as-cell-counts conflation as first-class failure modes. |
| Psycholinguist | experimental / neurolinguistic / computational psycholinguistics | psycholinguist/AGENTS.md |
Reasons from incremental parsing, lexical access, and prediction; designs SPR, eyetracking, VWP, and ERP studies with SUBTLEX/CELEX/MRC norms, maximal LMEMs, and OSF preregistration while treating list effects, SAT, spillover, and N400/P600 over-interpretation as first-class failure modes. |
| Psychophysicist | laboratory / psychophysics & perception | psychophysicist/AGENTS.md |
Reasons from psychometric functions, staircase/MLE threshold procedures, signal-detection theory, and calibrated display/audio transducers while treating timing jitter, adaptation, and criterion/sensitivity conflation as first-class failure modes. |
| Public Health Scientist | population health / surveillance / program evaluation / policy | public-health-scientist/AGENTS.md |
Reasons from the 10 Essential Public Health Services, epidemiologic triad, and SDOH; runs outbreak field investigations, NSSP syndromic and NNDSS surveillance, BRFSS/WONDER complex-survey analysis, CDC Framework and RE-AIM program evaluation, PAF/PIF policy quantification, and Kass ethics review. |
| Pure Mathematician | proof-theoretic / theorem-proof / formal verification (Lean 4/mathlib, Coq, Isabelle) / MSC-classified | pure-mathematician/AGENTS.md |
Reasons from definitions, axioms, and proved theorems through lemma-ladder proof strategies, computer algebra (SageMath, GAP, Magma) and proof assistants (Lean 4/mathlib, Coq, Isabelle/HOL) checked against MathSciNet/zbMATH and OEIS, while treating hidden hypotheses, circular reasoning, unjustified w.l.o.g. steps, and ZFC-independence as first-class failure modes. |
| Quality / Six Sigma Engineer | DMAIC/DMADV / SPC & capability / measurement systems analysis / APQP-PPAP automotive / ISO 9001 auditing | quality-six-sigma-engineer/AGENTS.md |
Reasons from process variation, defect operational definitions, and customer-critical characteristics through Shewhart control charts, Gage R&R (%GRR, ndc), Cp/Cpk and Pp/Ppk capability, DMAIC tollgates, and AIAG PPAP/PFMEA in Minitab or JMP while treating Cpk on unstable processes, attribute data forced as normal, gauge spread consuming tolerance, and unverified projected savings as first-class failure modes. |
| Quantitative Biologist | computational / live-imaging / dynamical systems biology | quantitative-biologist/AGENTS.md |
Reasons from SBML/PEtab ODE models, structural and profile-likelihood identifiability, Bayesian inference (Stan/PyMC/AMICI), and live-cell pipelines (Cellpose/TrackMate/PhotoFiTT, REMBI); treats sloppiness, phototoxicity, and segmentation-tracking artifacts as first-class failure modes. |
| Quantum Chemist | computational / ab initio electronic structure theory | quantum-chemist/AGENTS.md |
Reasons from the Schrödinger equation through HF, MP2/CCSD(T)/CBS, and multireference (CASSCF/CASPT2); uses ORCA/Psi4/Gaussian with GMTKN55/WTMAD-4 validation, T1/D1 diagnostics, Helgaker CBS extrapolation, and BSSE/spin-contamination checks while treating SCF near-degeneracy, intruder states, and global-vs-local multireference masking as first-class failure modes. |
| Quantum Computing Scientist | experimental / computational / NISQ hardware & fault tolerance | quantum-computing-scientist/AGENTS.md |
Reasons from qubits as noisy open systems through T1/T2, gate fidelity, RB/GST/XEB, and quantum volume to surface-code QEC; compiles with Qiskit/Cirq, applies ZNE/PEC/readout mitigation, and treats crosstalk, transpilation depth, and calibration drift as first-class failure modes. |
| Quantum Information Scientist | theoretical / experimental QIS | quantum-information-scientist/AGENTS.md |
Reasons from qubits as open systems, gate fidelities, and error correction while treating crosstalk and calibration drift as first-class failure modes. |
| Quantum Optics Scientist | optical bench / single-photon & squeezed-light / cavity QED / correlation & homodyne metrology | quantum-optics-scientist/AGENTS.md |
Reasons from field quadratures, atom-photon coupling (g, κ, γ), and heralding efficiency budgets through g⁽²⁾ Hanbury Brown-Twiss measurement, balanced homodyne tomography, HOM interference, and SNSPD/APD detector calibration while treating afterpulsing-faked antibunching, LO phase drift erasing squeezing, accidentals and dark counts, and unaddressed Bell-test loopholes as first-class failure modes. |
| Quantum Physicist | theory / quantum information / open-system dynamics / device benchmarking / multi-platform hardware (superconducting, trapped-ion, photonic, neutral-atom) | quantum-physicist/AGENTS.md |
Reasons from Hilbert-space density operators, commutation relations, and Lindblad open-system dynamics through randomized benchmarking, gate-set and process tomography, Bell-CHSH tests, and Stim/PyMatching surface-code decoding while treating crosstalk, leakage, calibration drift, and measurement backaction as first-class failure modes. |
| Quaternary Scientist | field geochronology / glacial geomorphology / multi-proxy paleoclimate / ice-core & tephra correlation | quaternary-scientist/AGENTS.md |
Reasons from dated landform-sediment-proxy associations, multi-method chronology, and ice-age cyclicity (MIS, orbital forcing) through radiocarbon/OSL/cosmogenic dating, Bayesian age models (OxCal, Bacon, IntCal20), tephrochronology, and GIA models while treating uncalibrated 14C years, incomplete OSL bleaching, cosmogenic inheritance, and no-analog pollen assemblages as first-class failure modes. |
| Radiation Oncology Physicist | clinical / research | radiation-oncology-physicist/AGENTS.md |
Reasons from absorbed dose, fluence, beam geometry, and constraint-driven plan quality through TG-51/TRS-398 reference dosimetry, TPS engines (AAA, Acuros XB, Monte Carlo), DVH metrics, and gamma-based patient-specific QA while treating stale CT-to-density tables, couch-shift sign errors, MLC leaf-bank swaps, and small-field output mishandling as first-class failure modes. |
| Radio Astronomer | interferometry / uv-plane imaging / spectral-line & polarization / time-domain (pulsars, FRBs) | radio-astronomer/AGENTS.md |
Expert profile for radio astronomer — see AGENTS.md for field-specific methods and failure modes. |
| Radiochemist | tracer synthesis / radiopharmaceutical QC / cyclotron-generator production / dosimetry / GMP release (USP <823>, FDA 21 CFR 212) | radiochemist/AGENTS.md |
Reasons from radionuclide half-life, specific activity, radiochemical purity, and dosimetry through analytical/prep HPLC with radiodetector, iTLC, HPGe γ-spectroscopy, OLINDA/MIRD, and USP <823>/EANM release specs while treating defluorination, transchelation of ⁶⁸Ga/⁸⁹Zr, ⁹⁹ᵐTc colloid and ⁶⁸Ge breakthrough as first-class failure modes. |
| Radiologist | clinical / diagnostic imaging interpretation | radiologist/AGENTS.md |
Reasons from modality–question fit, contrast kinetics, and ACR Appropriateness Criteria (1–9); applies BI-RADS, LI-RADS, PI-RADS, and Lung-RADS with Fleischner/incidental-findings algorithms; integrates PACS/RIS/DICOM/IHE workflows, CTDIvol/DLP/DIR dose stewardship, and critical-results communication while treating perceptual misses, satisfaction of search, and CT/MRI/PET artifacts as first-class failure modes. |
| Reaction Engineering Specialist | kinetics / reactor design / catalysis / RTD & calorimetry / thermal-hazard & scale-up | reaction-engineering-specialist/AGENTS.md |
Reasons from rate laws, stoichiometry, residence-time distributions, and coupled heat-rate balances through LHHW and Michaelis-Menten kinetics, Thiele/effectiveness and Weisz-Prater diffusion criteria, tracer RTD models, and RC1/ARC calorimetry while treating thermal runaway, hot spots, catalyst deactivation, channeling, and k_L-a mass-transfer masking as first-class failure modes. |
| Regenerative Medicine Scientist | wet-lab / translational CGT, tissue engineering & ATMP CMC | regenerative-medicine-scientist/AGENTS.md |
Reasons from potency assurance, 361 vs 351/ATMP pathways, USP <1043> ancillary tiers, G-Rex/closed CAR-T manufacture, MSC matrix potency, and ISO 10993/dECM scaffolds while treating comparability-without-bioassay and CFU-F-as-potency as first-class failure modes. |
| Regulatory Affairs Scientist | regulatory / drug & biologic development (IND–MAA) | regulatory-affairs-scientist/AGENTS.md |
Reasons from CTD/eCTD Modules 1–5 traceability, FDA Type B/EOP and EMA PRIME/scientific-advice strategy, ICH Q8–Q12 lifecycle CMC, and expedited pathways (BTD/RMAT/accelerated approval); treats RTF, clinical-hold CMC gaps, ignored meeting minutes, and eCTD validation failures as first-class failure modes. |
| Rehabilitation Scientist | clinical / biomechanics lab / implementation-science rehabilitation research | rehabilitation-scientist/AGENTS.md |
Reasons from ICF/disablement models, COSMIN MCID/MDC triangulation, TIDieR-Rehab/CONSORT 2025 trial design, gait lab and PROMIS outcomes, motor-learning mechanisms, and RE-AIM implementation science; treats natural recovery, therapist allegiance, and lab-vs-function confounds as first-class failure modes. |
| Reinforcement Learning Researcher | computational / deep RL & sim-to-real | reinforcement-learning-researcher/AGENTS.md |
Reasons from MDP/POMDP and Bellman operators through DQN/PPO/SAC/TD3, MuJoCo/Atari/Procgen/Brax benchmarks, offline RL (CQL/IQL), reward-hacking diagnostics, Gymnasium/CleanRL/SB3 stacks, and NeurIPS/ICML/CoRL seed-stratified evaluation with bootstrap CIs. |
| Reliability Engineer | physics-of-failure / accelerated life testing (HALT/HASS/ALT) / Weibull & censored field analytics / RCM-FMECA / functional safety (ISO 26262, IEC 61508) | reliability-engineer/AGENTS.md |
Reasons from failure mechanisms, time-to-failure distributions, censored field data, and stress-strength interference through FMECA, physics-of-failure models (Coffin-Manson, Arrhenius, Peck), Weibull and Crow-AMSAA growth analysis, and demonstration tests while treating mixture populations, wrong acceleration models, common-cause failures, and lab-pass-equals-field-proof as first-class failure modes. |
| Remote Sensing Scientist | Earth observation / optical-SAR-LiDAR / atmospheric & geometric correction / change detection / Olofsson validation | remote-sensing-scientist/AGENTS.md |
Reasons from sensor physics, atmospheric state, surface BRDF, and sampling geometry through Sen2Cor/LaSRC/6S atmospheric correction, sub-pixel coregistration, SAR radiometric terrain correction, and Olofsson area-adjusted accuracy while treating misregistration, NDVI saturation, BRDF anisotropy, mixed pixels, and spatial label leakage as first-class failure modes. |
| Renewable Energy Scientist | field measurement / techno-economic modeling / grid-integrated renewables | renewable-energy-scientist/AGENTS.md |
Reasons from resource-to-energy conversion, P50/P90 yield risk, LCOE/LCA boundaries, IEC monitoring, and grid constraints while troubleshooting PV soiling/PID/clipping, wind wakes/icing/yaw, hydro drought, geothermal scaling, and biomass feedstock variability. |
| Reproductive Biologist | clinical / research | reproductive-biologist/AGENTS.md |
Reasons from the HPG axis, gametogenesis, embryo development, and endometrial receptivity through WHO 6th semen analysis, LC-MS/MS hormone assays, EmbryoScope morphokinetics, PGT-A, and ASRM/ESHRE guidelines while treating mis-timed cycle-day sampling, incubator CO2/pH drift, sperm DNA fragmentation, and embryo mosaicism as first-class failure modes. |
| Research Software Engineer | computational / research software engineering / HPC | research-software-engineer/AGENTS.md |
Reasons from Software Carpentry and FAIR4RS through SemVer releases, CITATION.cff/SPDX metadata, pytest/Hypothesis CI gates, Docker/Apptainer on Slurm, and maintainability discipline for citable, reproducible research code. |
| Restoration Ecologist | field / reference-ecosystem planning / native planting & monitoring | restoration-ecologist/AGENTS.md |
Reasons from SER International Standards (reference models, six ecosystem attributes, five-star recovery, restorative continuum), BACI/BARI monitoring, INSR seed provenance and provisional seed zones, FQA/cover-weighted metrics, and passive–active–assisted recovery while treating revegetation-as-restoration, chronosequence pseudoreplication, and year-3 cover photos as first-class failure modes. |
| RF / Microwave Engineer | RF/microwave circuit design / S-parameter & EM simulation / VNA bench validation / regulatory masks (FCC, ETSI, 3GPP) | rf-microwave-engineer/AGENTS.md |
Reasons from power-wave S-parameters, Friis noise-figure cascades, and Rollett/mu stability through ADS/AWR harmonic balance, HFSS/Sonnet EM, Smith-chart matching, and TRL/SOLT-calibrated VNA/spectrum bench work while treating reference-plane errors, LO leakage and IF feedthrough, conditional instability, and uncorrelated sim-versus-measured gain as first-class failure modes. |
| RNA Biologist | mixed molecular RNA biology (wet-lab assay design) and computational transcriptomics | rna-biologist/AGENTS.md |
Reasons like a senior RNA biologist across transcription and nascent assays, splicing, m6A, CLIP/eCLIP, RNA-seq, ribosome profiling, and GENCODE/MANE annotation—with rigor, troubleshooting, and reporting norms. |
| Robotics Engineer | hardware-software integration / manipulation, navigation & perception | robotics-engineer/AGENTS.md |
Reasons from DH/PoE kinematics, Jacobian singularities, and computed-torque/impedance control through ROS 2, MoveIt/OMPL, Nav2/SLAM/AMCL, hand-eye AX=XB, Isaac/Gazebo sim-to-real, and ISO 10218/ISO TS 15066 safety while treating tf/frame errors, encoder drift, backlash, and reality-gap overclaim as first-class failure modes. |
| Robotics Scientist | hardware validation / kinematics & dynamics / planning & control (MPC, WBC) / SLAM & perception / sim-to-real / safety (ISO 10218, ISO/TS 15066) | robotics-scientist/AGENTS.md |
Reasons from the closed sensor-to-actuator loop, kinematic reachability, and dynamic feasibility (friction cones, actuator saturation) through DH/PoE kinematics, RRT*/CHOMP planning, MPC and whole-body control, SLAM, and ROS 2 rosbag logging while treating TF-frame and timestamp mismatches, the sim-to-real gap, grasp slip, and ISO 10218/15066 force-limit violations as first-class failure modes. |
| Sedimentologist | field logging / facies analysis / granulometry & petrography / core-log-seismic integration / reservoir quality | sedimentologist/AGENTS.md |
Reasons from grain-scale hydraulics, facies associations, and base-level accommodation through measured sections, Folk & Ward granulometry, Bouma divisions, ichnofacies, and core-log-seismic ties while treating diagenetic overprint, bioturbation-destroyed laminae, fining-upward and shale-equals-deep-water defaults, and single-outcrop overextrapolation as first-class failure modes. |
| Seismologist | observational / computational / operational seismology | seismologist/AGENTS.md |
Reasons from elastic wave theory and Earth models through detection, HypoDD/iLoc location, moment tensors, ambient-noise and receiver-function imaging, PSHA/OpenQuake hazard, and NEIC-style operational products (ShakeMap, PAGER, EEW) with explicit artifact and magnitude-type discipline. |
| Semiconductor Device Engineer | device characterization / TCAD-to-silicon calibration / compact modeling (BSIM-CMG) / wafer-level reliability (NBTI/HCI/TDDB) / FinFET-GAA | semiconductor-device-engineer/AGENTS.md |
Reasons from electrostatics, capacitance-current MOSFET physics, interface-trap behavior, and self-heating through I-V/C-V extraction ladders, Sentaurus TCAD calibrated to silicon splits, BSIM-CMG compact modeling, and JEDEC reliability stress while treating uncalibrated TCAD, unstated constant-current Vt references, ignored BTI partial recovery, and self-heating-distorted DC Ron as first-class failure modes. |
| Semiconductor Materials Scientist | bulk & epitaxial growth / defect & transport characterization | semiconductor-materials-scientist/AGENTS.md |
Reasons from band structure, defect energetics, and process–structure–property links; grows and characterizes bulk and epitaxial semiconductors (Si, III–V, SiC, GaN, 2D) via MOCVD/MBE/HVPE, Hall/DLTS/XRD/RSM/ECCI/TEM/SIMS, and DFT defect levels while treating compensation, Fermi-level pinning, threading dislocations, and polytype mixing as first-class failure modes. |
| Semiconductor Physicist | theory / transport & defect spectroscopy / heterostructures | semiconductor-physicist/AGENTS.md |
Reasons from ε_n(k), effective-mass tensor, and 2D subband DOS through Hall/multiband fits, mobility scattering analysis, Lang DLTS (E_T, σ, N_T), and quantum-well intersubband spectroscopy while treating compensation, rate-window artifacts, and DFT gap error as first-class failure modes. |
| Sensor Engineer | MEMS / optical / instrumentation design and characterization | sensor-engineer/AGENTS.md |
Reasons from transduction physics and error budgets through MEMS IMU Allan variance (ARW, bias instability, rate random walk), six-position and temperature calibration, piezoresistive/capacitive pressure validation, and photodiode–TIA NEP/SNR while treating vibration rectification, mag distortion, and aliased decimation as first-class failure modes. |
| Separation Processes Engineer | process simulation / pilot plant / plant troubleshooting | separation-processes-engineer/AGENTS.md |
Reasons from VLE/LLE thermodynamics, FUG shortcuts, and NRTL/PR property packages through Aspen RadFrac, CGCC/pinch integration, membrane Robeson bounds, chromatography van Deemter scale-up, and MSZW crystallization while treating wrong BIPs, jet flood/entrainment, concentration polarization, and lab-to-plant MSZW as first-class failure modes. |
| Signal Processing Engineer | DSP algorithm design / detection & estimation / spectral analysis / multirate & adaptive filtering / fixed-point bit-true sign-off | signal-processing-engineer/AGENTS.md |
Reasons from the sampling theorem, LTI system functions H(z), and sufficient statistics for detection through Parks-McClellan filter design, Welch and multitaper spectral estimation, matched filters and CFAR detection, and bit-true fixed-point verification while treating aliasing, leakage and scalloping, IIR limit cycles, and detector leakage as first-class failure modes. |
| Single-Cell Biologist | wet-lab / computational single-cell genomics | single-cell-biologist/AGENTS.md |
Reasons from assay chemistry, sample-level replication, cell-state manifolds, and metadata provenance; treats ambient RNA, doublets, dissociation stress, batch, and pseudoreplication as core failure modes. |
| Sleep Scientist | clinical / polysomnography / circadian & sleep physiology research | sleep-scientist/AGENTS.md |
Reasons from Borbély Process S/C homeostatic–circadian integration, AASM v3 PSG scoring (1A/1B hypopnea rules), DLMO/forced desynchrony phase assays, MSLT/ICSD-3 hypersomnolence criteria, Cole-Kripke/Sadeh actigraphy, NSRR/SHHS cohorts, and CBT-I/CPAP trial design while treating first-night effect, actigraphy wake misclassification, 3% vs 4% AHI shifts, and consumer wearable stage overclaim as first-class failure modes. |
| Soft Matter Physicist | experimental / computational / condensed matter | soft-matter-physicist/AGENTS.md |
Reason from kT and mesoscale structure; couple rheology (TA Instruments, Anton Paar), scattering (SANS/SAXS/DLS/XPCS), and PIV to Flory-Huggins, de Gennes scaling, jamming, and active-matter hydrodynamics. |
| Soil Ecologist | field / lab biogeochemistry / molecular soil ecology | soil-ecologist/AGENTS.md |
Reasons from soil food webs (nematode EI/SI/CI), PLFA phenotypes, amoA/nirK/nifH qPCR, and 16S/ITS/metagenomics through gross 15N pool dilution and C/N priming while treating tillage, compaction, and fire recovery, compositional bias, and DNA-activity gaps as first-class failure modes. |
| Soil Fertility Scientist | soil testing / nutrient management / 4R stewardship / liming & pH / precision-ag VRT | soil-fertility-scientist/AGENTS.md |
Reasons from plant-available nutrient supply, pH-governed availability, and CEC/base saturation through Mehlich-3 extraction, buffer-pH lime calculations with ECCE/ENM, 4R stewardship, and regional extension calibration while treating uncalibrated cross-extractant comparison, no-till stratification, environmental P/nitrate loss, and N mineralization-immobilization leakage as first-class failure modes. |
| Soil Scientist | pedology / soil physics & chemistry / classification (USDA Taxonomy, WRB) / land evaluation | soil-scientist/AGENTS.md |
Reasons from CLORPT genetic horizonation, matric-potential water flow, and colloid exchange chemistry through Munsell pedon description, USDA Soil Taxonomy and WRB keys, buffer-pH lime calculation, and HYDRUS/RUSLE2/PHREEQC modeling while treating wrong-extractant nutrient values (Mehlich-3 vs Olsen), map-unit-as-pedon substitution, and PTF-output-as-measured-K_sat as first-class failure modes. |
| Solar Physicist | heliophysics / MHD / multi-wavelength remote sensing / space weather (SDO, PSP) | solar-physicist/AGENTS.md |
Reasons from magnetic field topology, plasma beta, reconnection, and radiative transfer through DEM inversion, NLFFF/PFSS extrapolation, coronal seismology, and WSA-ENLIL forecasting while treating single-channel AIA temperature claims, HMI disambiguation ambiguity at the PIL, limb projection artifacts, and Parker-spiral connectivity uncertainty as first-class failure modes. |
| Space Weather Scientist | observational / computational / operational heliophysics | space-weather-scientist/AGENTS.md |
Reasons from Dungey coupling and prolonged southward Bz through ICME vs. CIR/SIR drivers; uses OMNI/CDAWeb, L1 RTSW, WSA-Enlil, CCMC/CAMEL validation, SuperMAG SYM-H, GloTEC/IRI, and NOAA G/S/R scales while treating sheath-vs-cloud Bz, catalog false alarms, and Dst timing artifacts as first-class failure modes. |
| Spectroscopist | wet-lab / optical & magnetic spectroscopy (UV-Vis/fluorescence/IR-Raman/NMR/EPR/XAS) / peak assignment & quantitation / instrument QC & calibration | spectroscopist/AGENTS.md |
Reasons from selection rules, line shapes as convolutions of intrinsic and instrument broadening, and Beer-Lambert linearity through UV-Vis, fluorescence, IR/Raman, NMR, CD, EPR, and XAS/XPS with calibration standards (polystyrene 1601 cm⁻¹, TMS/DSS, C 1s 284.8 eV) while treating inner filter effects, baseline artifacts inventing peaks, Fermi resonances, and X-ray beam damage as first-class failure modes. |
| Spintronics Physicist | thin-film fab / magneto-transport / spin dynamics (ST-FMR, MTJ/SOT) / micromagnetics | spintronics-physicist/AGENTS.md |
Reasons from spin-orbit coupling, spin diffusion length, exchange and DMI, and spin-dependent transport through MTJ/TMR characterization, ST-FMR and harmonic-Hall torque measurement, nonlocal spin valves, and Valet-Fert and MuMax3/OOMMF modeling, while treating barrier pinholes and shunt paths, ordinary-versus-anomalous Hall and ISHE confusion, Oersted-field and Joule-heating artifacts, and incomplete magnetization switching as first-class failure modes. |
| Sports Scientist | applied / field & lab / team & individual performance monitoring | sports-scientist/AGENTS.md |
Reasons from periodization and session-RPE/ACWR/GPS load monitoring, VALD force-plate readiness, SWC/TE decision bands, and IOC/STROBE-SIIS/CERT/CONSORT reporting while treating pseudoreplication, Hawthorne reactivity, and single-metric injury claims as first-class failure modes. |
| Statistical Physicist | theoretical / computational / equilibrium and non-equilibrium statistical mechanics | statistical-physicist/AGENTS.md |
Reasons from ensembles and partition functions through finite-size scaling (Binder cumulant, data collapse), Wolff/cluster MC, and RG/MCRG to Jarzynski–Crooks fluctuation theorems; uses ALPS, NetKet, WHAM, and ED/DMRG while treating critical slowing down, subleading FSS humps, and poor work-histogram overlap as first-class failure modes. |
| Statistician | applied inference / experimental design / Bayesian-frequentist / causal & survey methods / SAP-driven consulting | statistician/AGENTS.md |
Reasons from estimands, generative-model assumptions, and a budgeted Type I/II error tradeoff through analysis plans (SAP, ICH E9(R1) estimands), mixed models, multiple imputation under MCAR/MAR/MNAR, and Benjamini-Hochberg FDR while treating naive post-selection SEs, unadjusted multiplicity, ignored clustering in survey PSUs, and sequential peeking as first-class failure modes. |
| Stellar Astrophysicist | stellar evolution modeling / spectroscopy + photometry / asteroseismology / multi-messenger observation / MESA simulation | stellar-astrophysicist/AGENTS.md |
Reasons from stellar structure, nucleosynthesis, radiative transfer, and the distance ladder through MESA evolution models, spectroscopic and asteroseismic fitting, Gaia astrometry, and MCMC/nested-sampling inference while treating PSF and flat-field artifacts, telluric contamination, Malmquist and Eddington selection bias, and look-elsewhere global significance as first-class failure modes. |
| Stem Cell Biologist | wet-lab / hPSC culture and directed differentiation | stem-cell-biologist/AGENTS.md |
Human pluripotent stem cell maintenance, ISSCR-aligned QC (pluripotency markers, tri-lineage differentiation, genomic drift, mycoplasma), and directed differentiation troubleshooting. |
| Stratigrapher | outcrop + subsurface / sequence stratigraphy / well & seismic correlation / biostratigraphy / basin analysis (ICS, NACS) | stratigrapher/AGENTS.md |
Reasons from the material-strata-versus-conceptual-time distinction, accommodation-and-supply systems tracts, and confidence-tiered correlation through ICS/NACS codes, sequence surfaces (SB, MFS, TS), wireline and seismic well ties, and biostratigraphic FAD/LAD plus U-Pb and chemostratigraphic tie points, while treating diachronous facies contacts, seismic tuning artifacts, and reworked or caved fossils as first-class failure modes. |
| String Theorist | formal hep-th / compactification & moduli stabilization / AdS-CFT holography / swampland & string phenomenology | string-theorist/AGENTS.md |
Reasons from worldsheet CFT anomaly cancellation, moduli stabilization, and effective-field-theory consistency through KKLT/LVS flux compactifications, KLT/CHY/BCFW amplitude methods, and AdS/CFT large-N holography while treating tadpole mismatches, runaway moduli, unstabilized de Sitter uplifts, and conjecture-as-theorem swampland overclaims as first-class failure modes. |
| Structural Biologist | wet-lab / X-ray crystallography / cryo-EM / NMR | structural-biologist/AGENTS.md |
Reasons from the phase problem, CTF, and gold-standard FSC; refines with CCP4/PHENIX/RELION/cryoSPARC; validates with MolProbity and OneDep while treating preferred orientation, twinning, and radiation damage as first-class failure modes. |
| Structural Engineer | analysis & design / LRFD-ASD limit states / seismic & wind lateral systems / connections & foundations / codes (ASCE 7, ACI 318, AISC 360/341, AASHTO) | structural-engineer/AGENTS.md |
Reasons from equilibrium, load-path continuity, ductility, and code-mandated safety formats through ASCE 7 load combinations, ETABS/SAP2000 models with independent hand checks, AISC 360/341 and ACI 318 capacity design, and ASCE 41 evaluation, while treating soft-story drift, brittle connection and anchor breakout failures, neglected serviceability, and progressive collapse as first-class failure modes. |
| Structural Geologist | field mapping / balanced cross sections / microstructural petrofabrics / active tectonics & paleoseismology / fault-slip inversion | structural-geologist/AGENTS.md |
Reasons from stress, strain, kinematics, and Mohr-Coulomb failure through stereonet fault-slip analysis, area-balanced cross sections in Move, quartz/calcite paleopiezometry on EBSD-indexed CPO, and geodetic-plus-trench slip-rate estimates while treating heterogeneous-fault paleostress inversion, map-pattern vergence errors, seismic processing artifacts as false faults, and outcrop-face shear-sense bias as first-class failure modes. |
| Superconductivity Scientist | experimental / computational / materials discovery & applied conductors | superconductivity-scientist/AGENTS.md |
Reasons from BCS/Eliashberg/GL order parameters, pairing symmetry, and vortex physics; validates Tc with Meissner/χ/C triads, phase-sensitive Josephson tests, ARPES/STM gaps, and EPW; uses SuperCon/3DSC and IEC 61788 Ic standards while treating filamentary transitions, pseudogap misreads, DAC flux trapping, and HTS quench detection gaps as first-class failure modes. |
| Supramolecular Chemist | wet-lab / host-guest binding / self-assembly / ITC + NMR titration / SCXRD | supramolecular-chemist/AGENTS.md |
Reasons from noncovalent binding free energies (ΔG = ΔH − TΔS), host-guest complementarity, and cooperative assembly through ITC, NMR titration with global fitting (Bindfit, SupraFit), Job's method, and SCXRD while treating wrong-stoichiometry K fits, kinetic traps mistaken for thermodynamic products, ITC dilution-dominated heats, and crystal packing assumed to dominate solution as first-class failure modes. |
| Surface Chemist | experimental / UHV & ambient surface analysis / colloid & interface science | surface-chemist/AGENTS.md |
Reasons from interfacial thermodynamics, Langmuir/BET/D-R adsorption, and Young–Dupré wetting through XPS (ISO 15472/18118, AdC vacuum-level alignment, SESSA), contact-angle SFE (OWRK/vOCG, ASTM D7490), QCM-D viscoelastic modeling, ToF-SIMS, SAMs, and ISO 20579 handling while treating adventitious carbon, charging, siloxane contamination, Cassie–Wenzel states, and tip convolution as first-class failure modes. |
| Surface Engineering Specialist | laboratory / deposition & surface treatment / tribology & corrosion qualification | surface-engineering-specialist/AGENTS.md |
Reasons from tribological system design, Archard wear, Stribeck regimes, and Pourbaix/galvanic coupling; selects PVD/CVD/PEO/conversion stacks with HiPIMS etch and interlayers; validates with ISO 20502 scratch, ASTM G99/G133, G119 tribocorrosion, and ISO 14577 nanoindentation while treating delamination stress, arc macroparticles, pinhole galvanics, and cross-cut misuse on hard films as first-class failure modes. |
| Surface Physicist | UHV surface science / electron spectroscopy / scanning-probe microscopy / surface diffraction / catalysis & 2D epitaxy | surface-physicist/AGENTS.md |
Reasons from surface thermodynamics, adsorption coverage, work function, and probe escape depth through XPS/ARPES, LEED I(V) and CTR analysis, STM/AFM, TPD with Redhead analysis, and DFT slabs while treating adventitious-carbon contamination, differential charging, electron-beam and tip-induced damage, and UHV-to-operando extrapolation as first-class failure modes. |
| Surgeon-Scientist | clinical / research | surgeon-scientist/AGENTS.md |
Reasons from anatomy, pathophysiology, and the IDEAL stage of surgical innovation through IDE/IND pathways, NSQIP/STS registry risk-adjustment, CUSUM learning-curve analysis, and ischemia-timed biobank SOPs while treating unrisk-adjusted case series, indication-confounded surgeon-preference comparisons, cold-ischemia biomarker artifact, and conflated learning-curve and surgeon-volume effects as first-class failure modes. |
| Surveyor / Geomatics Engineer | field / office geodetic, cadastral, construction, hydro, and remote sensing | surveyor-geomatics-engineer/AGENTS.md |
Reasons from datum/epoch/geoid and NSRS 2022 migration, CSF grid–ground, Baarda/3D least squares, NGS 92/ALTA RPP/ASPRS RMSE and IHO S-44 TPU; treats prism constants, BIM Helmert, and mixed CRS as first-class failure modes. |
| Sustainability Scientist | sustainability reporting / GHG accounting (GHG Protocol, GRI/ISSB/ESRS) / planetary boundaries / circularity & nexus / scenario analysis | sustainability-scientist/AGENTS.md |
Reasons from measurable capitals, planetary-boundary safe operating space, and absolute-versus-intensity impact through GHG Protocol Scope 1/2/3 accounting, GRI/ISSB/ESRS disclosure, MCI circularity and MFA, and IPCC SSP/IEA/NGFS scenario analysis, while treating greenwashing offsets without additionality or permanence, Scope 3 EEIO collapse, masked SDG trade-offs and leakage, and intensity gains hiding absolute growth as first-class failure modes. |
| Synthetic Biologist | engineering biology / DBTL / genetic circuits + metabolic pathways / Golden Gate + Gibson assembly / SBOL-SBML standards / biosafety (NIH Guidelines, DURC) | synthetic-biologist/AGENTS.md |
Reasons from biological parts, the DBTL cycle, chassis context, and the central dogma as a wiring diagram through Golden Gate and Gibson assembly, SBOL/SBML encoding, RPU/MEFL-calibrated characterization, and FBA models while treating metabolic burden, genetic instability, plasmid loss, and resource competition as first-class failure modes. |
| Systems Biologist | computational / research | systems-biologist/AGENTS.md |
Reasons from network motifs, separation of structure from dynamics, mass-balance constraints, and multi-layer measurement coupling through COBRApy/FBA-pFBA-FVA, ODE/Boolean simulation (COPASI, BoolNet, CellNOpt), and MOFA+/mixOmics integration while treating batch artifacts, gap-filled reactions, parameter non-identifiability, and transcript-flux conflation as first-class failure modes. |
| Systems Engineer | requirements / architecture / integration / V&V / MBSE | systems-engineer/AGENTS.md |
Reasons from stakeholder needs, ISO/IEC/IEEE 15288 life-cycle processes, and V-model verification/validation through bidirectional requirements trace (DOORS/Polarion), MBSE SysML digital threads, ICD interface control, DSM integration sequencing, MCDA trade studies, and FMEA/FTA/STPA risk—while treating scope creep, gold plating, traceability gaps, and ICD mismatches as first-class failure modes. |
| Systems Neuroscientist | wet-lab / in vivo neurophysiology + behavioral neuroscience + computational analysis | systems-neuroscientist/AGENTS.md |
Reasons across circuits, Neuropixels/calcium imaging, behavior, optogenetics/chemogenetics, connectomics, and multi-timescale animal models—with rigor on sync, controls, and causal claims. |
| Taxonomist / Systematist | museum / field / lab / integrative alpha taxonomy & nomenclature | taxonomist-systematist/AGENTS.md |
Reasons from nomenclature–taxonomy separation and ICZN/Madrid Code typification (holotype/lectotype/neotype) through integrative delimitation (morphology, bPP/ASAP/BOLD), monograph and checklist workflows; uses ZooBank/IPNI/MycoBank, Darwin Core/GBIF IPT/COL, TaxonWorks/Specify, and BHL protologues while treating barcode-only species, syntype heterogeneity, inapplicable-state coding errors, and eDNA-only names as first-class failure modes. |
| Telecommunications Engineer | RAN/backhaul/core / link budgets / propagation modeling / spectrum compliance (3GPP, ITU-R, FCC Part 47) | telecommunications-engineer/AGENTS.md |
Expert profile for telecommunications engineer — see AGENTS.md for field-specific methods and failure modes. |
| Theoretical Chemist | dynamics theory / PES construction / TST & master-equation kinetics / quantum scattering | theoretical-chemist/AGENTS.md |
Reasons from Hamiltonians, partition functions, and flux through dividing surfaces using validated potential energy surfaces, variational transition state theory with Eckart and small-curvature tunneling (Polyrate), and master-equation falloff solvers (MESMER, MultiWell), while treating spurious saddle imaginary modes, spin contamination, recrossing, and silent single-surface MD across conical intersections as first-class failure modes. |
| Theoretical Computer Scientist | theoretical / complexity, algorithms, and formal proof | theoretical-computer-scientist/AGENTS.md |
Reasons from explicit models (TM, circuit, communication, query) and resource measures; audits Karp/parsimonious/gap/fine-grained reductions against ETH/SETH/#ETH and PCP/UGC/APX barriers; uses Complexity Zoo, ECCC/arXiv cs.CC, Coq/Lean/DRAT, Williams algorithms-for-lower-bounds, and Yao/IC lower bounds while treating wrong reduction direction, non-parsimony, APSP–3SUM conflation, oracle overclaim, and natural-proofs misuse as first-class failure modes. |
| Theoretical Physicist | analytic theory / QFT & EFT / lattice & many-body numerics / RG & critical phenomena / GR & gravitation | theoretical-physicist/AGENTS.md |
Reasons from symmetries, conservation laws, effective field theory, and limiting cases through Feynman-diagram and on-shell amplitude tools, renormalization-group flow, lattice and tensor-network numerics, and the conformal bootstrap, while treating gauge-dependent artifacts, unitarity and Ward-identity violations, scheme dependence, and lattice discretization errors as first-class failure modes. |
| Thermodynamics Engineer | energy-system analysis / cycle modeling / exergy & pinch / heat exchangers / acceptance testing (ASME PTC, AHRI) | thermodynamics-engineer/AGENTS.md |
Reasons from energy conservation, entropy generation, state properties, and exergy quality through cycle modeling on T-s/h-s diagrams, IAPWS-IF97/REFPROP/CoolProp property models, LMTD/ε-NTU and pinch analysis, and ASME PTC/AHRI acceptance protocols, while treating efficiency-above-Carnot claims, pinch violations, compressor surge, and inconsistent HHV/LHV bases as first-class failure modes. |
| Thin-Film Scientist | deposition (PVD/CVD/ALD) / thin-film metrology / stress & adhesion / optical coatings / semiconductor fab | thin-film-scientist/AGENTS.md |
Reasons from nucleation and growth modes, film stress, interfacial adhesion, and conformality across topography through spectroscopic ellipsometry, XRR, Stoney wafer-curvature, XPS/RBS, and standards like ASTM E2244 and ISO 9211 while treating columnar porosity, barrier pinholes, reactive-sputter hysteresis drift, and uncalibrated-QCM thickness error as first-class failure modes. |
| Tissue Engineer | wet-lab / regenerative medicine | tissue-engineer/AGENTS.md |
Reasons from the TE triad, Krogh transport limits, and Engler mechanobiology through perfusion bioreactors, dECM constructive remodeling, ASTM F2150/F1635 characterization, and ARRIVE/ISO 10993/21560 translation—treating hypoxic cores, acellular controls, and biological-vs-technical replicate inflation as first-class failure modes. |
| Topologist | proof-based / algebraic topology / low-dimensional & knot theory / TDA (persistent homology) | topologist/AGENTS.md |
Reasons from continuity, compactness, connectedness, homotopy, and manifold structure through invariants and tools like π₁ via Seifert-van Kampen, cellular/simplicial homology with ∂²=0 and Smith-normal-form torsion, Mayer-Vietoris, and SnapPy/GUDHI computation, while treating lost-Hausdorffness in quotients, torsion missed by rational coefficients, visual deformation without a homotopy or Reidemeister proof, and barcodes interpreted without filtration stability as first-class failure modes. |
| Toxicologist | regulatory / pharmaceutical / industrial chemical safety | toxicologist/AGENTS.md |
Reasons from dose–response, ADME/TK, MOA/AOP, and exposure context; separates hazard from risk; derives BMDL/DNEL/RfD PODs and interprets OECD/ICH batteries with vehicle, strain, S9, and histopath artifacts as first-class failure modes. |
| Traffic Engineer | operations / safety / signal & corridor analysis | traffic-engineer/AGENTS.md |
Reasons from LWR/CTM flow, HCM delay/v/c/LOS, K-D-PHF-DDHV volumes, ITE TGM 12th/MTIASD TIAs, Synchro/HCS/SIDRA/VISSIM workflows, and HSM SPF+CMF+EB safety — treating unc calibrated models, naive before–after crashes, and LOS-without-v/c as first-class failure modes. |
| Translational Researcher | preclinical / IND-IDE-enabling / early clinical PoC & biomarker translation | translational-researcher/AGENTS.md |
Reasons from T0–T4 stage gates, murine vs NHP translatability, PK/PD allometric bridging, MRSD/MABEL FIH dose selection, BEST/CLIA/CAP biomarker tiers, and CONSORT/SPIRIT/STROBE reporting while treating target-wrong, model-wrong, non-predictive biomarker, and preclinical irreproducibility as first-class failure modes. |
| Transportation Engineer | planning / demand modeling / geometric design / corridor evaluation | transportation-engineer/AGENTS.md |
Reasons from four-step and activity-based travel demand (CUBE/Visum/EMME), AASHTO Green Book geometry, HCM capacity, MPO LRTP and NEPA 23 CFR 771 project development, and multimodal corridor MOEs while treating unvalidated TDM forecasts and capacity-without-demand balance as first-class failure modes. |
| Tribologist | tribometry / contact mechanics & EHL / lubricant & coating selection / wear failure analysis / condition monitoring (ASTM G99, ISO 281/4406) | tribologist/AGENTS.md |
Reasons from contact mechanics, lubricant rheology, Stribeck-regime and λ ratio through Hamrock-Dowson EHL film estimates, pin-on-disk/four-ball/SRV/FZG bench tests and SEM-EDS/ferrography scar analysis while treating scuffing, rolling-contact pitting, three-body abrasion and DLC adhesive transfer as first-class failure modes. |
| Tunnel & Underground Engineer | geotechnical / NATM-SEM & TBM tunneling / rock-mass classification (Q/RMR/GSI) / ground-support convergence / fire-life safety (NFPA 502/130) | tunnel-underground-engineer/AGENTS.md |
Reasons from ground-structure-water-air interaction, convergence-support interaction, and face-stability limit states through Q/RMR/GSI classification, Hoek-Brown numerical models (PLAXIS, FLAC), Peck settlement troughs, and DAUB-ITA/NFPA 502 standards while treating face blowout, squeezing, invert heave, and TBM jam in mixed face as first-class failure modes. |
| Turbomachinery Engineer | rotating-equipment design / meanline-to-CFD / rotordynamics / performance test (ASME PTC 10, API 617) | turbomachinery-engineer/AGENTS.md |
Reasons from Euler work transfer, velocity triangles, decomposed loss correlations, and map-based off-design margin through meanline-to-throughflow-to-RANS/URANS analysis, Campbell and unbalance rotordynamics, and ASME PTC 10/PTC 6 and API 617 testing while treating surge and rotating stall, clearance rubs and tip leakage, pump cavitation below NPSHr, and seal cross-coupling instability as first-class failure modes. |
| Urban & Infrastructure Planner | policy / capital programming / asset management | urban-infrastructure-planner/AGENTS.md |
Reasons from comp plan–FLUM–zoning consistency through Euclidean/form-based overlays, CIP/TIP–STIP and ISO 55001/IIMM asset portfolios, ArcGIS Urban parcel workflows, and CEJST/AFFH/Justice40 equity screening while treating FLUM–zoning mismatch, CRS topology errors, and unfunded backlog as first-class failure modes. |
| Vaccinologist | translational / clinical development / regulatory CMC | vaccinologist/AGENTS.md |
Vaccine development expert for platform and adjuvant selection, validated immunogenicity (HAI/PRNT/OPA), CoP and immunobridging, VE/effectiveness trial design, CBER lot release, and Brighton AEFI reporting. |
| Vacuum Science & Technology Engineer | vacuum system design / UHV-XHV commissioning / leak & outgassing diagnostics / pump-conductance specification (ISO 27894, AVS, SEMI) | vacuum-science-technology-engineer/AGENTS.md |
Reasons from molecular flux (P = n k_B T), conductance-limited effective pumping speed, and surface outgassing through He mass-spectrometer leak detection, rate-of-rise tests, RGA fingerprinting, and Molflow+ conductance modeling while treating virtual leaks, H₂ permeation, ion-gauge contamination, and hydrocarbon backstreaming as first-class failure modes. |
| Veterinarian | clinical / companion & production animal medicine / One Health | veterinarian/AGENTS.md |
Reasons from species-specific physiology and pharmacology (Plumb's, AMDUCA, MDR1/PRiME), WSAVA 2024/AAHA/ISCAID 2025/CAPC guidelines, IDEXX/Cornell/eClinpath diagnostics, CMPS-SF/FGS pain and RECOVER 2024 CPR, and One Health zoonosis reporting while treating cat NSAID/acetaminophen toxicity, subclinical bacteriuria, greyhound lab artifacts, and human-dose extrapolation as first-class failure modes. |
| Veterinary Epidemiologist | field / observational / herd-health surveillance & infectious-disease modeling | veterinary-epidemiologist/AGENTS.md |
Reasons from herd-level units, Rogan–Gladen prevalence, R₀/SIR transmission models, and WOAH freedom-from-disease surveillance through outbreak line lists, SaTScan clusters, cluster field trials (REFLECT), and STROBE-Vet/AHSURED reporting while treating pseudo-replication, test-biased apparent prevalence, reporting-intensity clusters, and mis-specified generation intervals as first-class failure modes. |
| Veterinary Microbiologist | diagnostic bacteriology-mycology-virology / reference lab & herd surveillance | veterinary-microbiologist/AGENTS.md |
Reasons from pre-analytic specimen quality, CLSI VET01 AST, MALDI-TOF/PCR/WGS, and ISCAID significance thresholds through ACVM/AAVLD/WOAH workflows, NARMS/Vet-LIRN AMR surveillance, and One Health zoonoses while treating wound-swab contaminants, PCR-without-viability, human breakpoints on veterinary isolates, DTM false positives, MRSP biofilm, and Brucella BSL-3 exposure as first-class failure modes. |
| Vibration & Dynamics Engineer | experimental modal / machinery diagnostics / rotordynamics | vibration-dynamics-engineer/AGENTS.md |
Reasons from FRF/coherence, MAC, and damping identification through impact/shaker EMA, spectral ODS, FFT windowing, Campbell/critical-speed rotordynamics, and ISO 20816/API 610 diagnostics while treating double-hit, mass-loading, ODS–mode conflation, oil whirl/whip, and leakage as first-class failure modes. |
| Virologist | wet-lab / clinical / viral genomics | virologist/AGENTS.md |
Reasons from Baltimore groups, replication-cycle kinetics, and ICTV/MSL41 taxonomy; runs plaque/TCID50/PRNT, MIQE qPCR, ARTIC Illumina/Nanopore surveillance, antiviral TOA, VLP platforms, and BEI Resources while treating DI particles, subgenomic RNA, pseudovirus cytotoxicity, and IFN/MHC evasion as first-class failure modes. |
| Viticulturist / Enologist | field viticulture / cellar enology / sensory & wine chemistry | viticulturist-enologist/AGENTS.md |
Reasons from source–sink canopy balance, terroir as water/nitrogen-mediated ripening, sugar–acid–phenolic trajectories, glucophilic AF and Oenococcus MLF, molecular SO₂ at pH, FOSS/OIV analytics, ISO 4120/QDA sensory, and NDVI selective harvest while treating stuck ferment (YAN/fructose), smoke glycoside release, pH-blind SO₂, and mineral-terroir folklore as first-class failure modes. |
| VLSI / Chip Design Engineer | RTL-to-GDSII / MCMM STA signoff / DFT-ATPG / physical verification (DRC/LVS) / tapeout | vlsi-chip-design-engineer/AGENTS.md |
Reasons from PPA tradeoffs, timing slack, on-chip variation, and foundry rule decks through MCMM STA with OCV/POCV in PrimeTime/Tempus, UPF power intent, SpyGlass/JasperGold CDC, and Calibre DRC/LVS while treating clock-domain crossings, post-CTS hold violations, IR drop, and TT-only signoff as first-class failure modes. |
| Volcanologist | field / observational / computational volcanology & hazard assessment | volcanologist/AGENTS.md |
Reasons from mush reservoirs, volatile exsolution, and conduit fragmentation through WOVOdat/GVP unrest synthesis, MultiGAS–DOAS CO₂/SO₂, melt-inclusion thermobarometry, GACOS/ERA5 InSAR, LP/VLP/VOISS-Net seismology, BET_EF probabilistic forecasting, and LaMEVE recurrence while treating atmospheric InSAR artefacts, MI H₂O diffusion loss, open-vent gas misread, and deterministic eruption countdowns as first-class failure modes. |
| Water Resources Engineer | design / engineering / hydrology & floodplain | water-resources-engineer/AGENTS.md |
Watershed hydrology through HEC-HMS into HEC-RAS floodplain and stormwater BMP design — catchment balance, DSS coupling, FEMA products, and quantity/quality detention with defensible calibration. |
| Water Resources Scientist | hydrologic modeling / groundwater-surface coupling / water-budget allocation / remote sensing (GRACE, OpenET) / climate-water planning | water-resources-scientist/AGENTS.md |
Reasons from hydrologic-cycle mass and energy balance, green-versus-blue water, and nonstationarity through MODFLOW, SWAT/HEC-RAS, WEAP, Budyko closure, and multi-objective KGE/NSE calibration while treating equifinality, unaccounted return flows and stream depletion, single-drought-year safe yield, and efficiency-rebound effects as first-class failure modes. |
| Weed Scientist | field efficacy trials / herbicide resistance / dose-response (drc/GR50) / IWM / MOA stewardship (HRAC/WSSA) | weed-scientist/AGENTS.md |
Reasons from the weed seed bank, population dynamics, and herbicide mode-of-action biology through log-logistic dose-response (GR50/GR90 in R drc), replicated RCB field trials with susceptible checks, molecular resistance assays (ALS sequencing, EPSPS copy number), and HRAC/WSSA-based MOA rotation while treating drift and carryover, tank-mix antagonism and water-quality failures, and late-escape seed rain as first-class failure modes. |
| Welding & Joining Engineer | fabrication / procedure qualification / NDT & distortion control | welding-joining-engineer/AGENTS.md |
Reasons from heat input, t8/5, HAZ metallurgy, and restraint/shrinkage through AWS D1.1 prequalified vs qualified WPS, ASME IX/ISO 15614 PQR essential variables, RT/UT acceptance (static vs cyclic), FSW wormhole/kissing-bond windows, and neutron/XRD/hole-drilling residual stress while treating prequalification overreach, planar-UT mis-disposition, and cold-FSW root bonds as first-class failure modes. |
| Wetland Scientist | field / regulatory delineation / mapping / restoration & assessment | wetland-scientist/AGENTS.md |
Reasons from the three-parameter delineation test (1987 Manual + Regional Supplements, NWPL, FISM), Cowardin/NWI/LLWW mapping, HGM function and Level 1–2–3 RAM, compensatory mitigation/RIBITS, and wetland carbon–GHG flux while treating legacy hydrology, 50/20 cover errors, relict redox nodules, NWI≠jurisdiction, and short well records as first-class failure modes. |
| Wildlife Biologist | field / population monitoring / telemetry / management science | wildlife-biologist/AGENTS.md |
Reasons from detectability-aware abundance (Distance/mrds, MARK/RMark CJS, secr/oSCR, unmarked occupancy), Camtrap DP and Movebank/amt telemetry, ASM/MBTA/ESA permitting, and MIEM/FAIRe eDNA while treating index-effort bias, closure violation, bait aggregation, apparent-survival emigration, and collar/fix pseudoreplication as first-class failure modes. |
| Wind Engineering Specialist | BLWT / CWE / structural wind loads / pedestrian comfort | wind-engineering-specialist/AGENTS.md |
Reasons from ABL exposure, ASCE 7-22/EN 1991-1-4 wind actions, ASCE 49 BLWT Method 3, rigid vs flexible G/Gf, MWFRS vs C&C, and DAD directionality; treats enclosure GCpi, short-fetch exposure, and aeronautical-tunnel misuse as first-class failure modes. |
| X-ray / Synchrotron Scientist | beamline / scattering & spectroscopy (SAXS/WAXS, XAS, RIXS) / synchrotron & XFEL imaging / operando & time-resolved | x-ray-synchrotron-scientist/AGENTS.md |
Reasons from photon-matter cross sections, reciprocal-space Q, absorption edges, and absorbed dose through pyFAI, GSAS-II, Athena/Artemis, BornAgain, and foil/silver-behenate calibration while treating fluorescence self-absorption, substrate Bragg misindexing, beam damage and radiation-induced reduction, and Fourier-termination ripples as first-class failure modes. |
| Zoologist | field / museum / lab / integrative animal biology | zoologist/AGENTS.md |
Reasons from Bauplan, homoplasy, and voucher-backed ICZN taxonomy through COL/WoRMS/GBIF IPT, VertNet/Arctos curation, Folmer COI/BOLD BIN, geomorph GPA, IQ-TREE phylogenetics, and Distance/MARK occupancy–abundance models while treating trap selectivity, checklist drift, barcode-only species, and morphometric digitizing noise as first-class failure modes. |