[ DO NOT MERGE ] Side quest/co scientist#963
Draft
FriederikeHanssen wants to merge 35 commits into
Draft
Conversation
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Remove em-dash elaborations and backtick process names in the overview. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Normalize run-status casing to lowercase, add a dataset prompt and checkpoint to the explore-platform page, and flag the chat URL and status casing for verification. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Renumber pages to make room for an agent-literacy page and rename the testing page to cover skills. Update nav, cross-links, objectives, and time estimate (~3h). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add verify-the-change and verify-the-diff/PR steps to development and fix pages, and remove em-dash elaborations from the agent-literacy page. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Distinguish grounding from intent, flag the MCP log-reading claim, fix checkpoint tense, clarify the skill-file copy step, and trim a redundant verify sentence. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The CoScientist docs do not describe MCP as CoScientist's internal transport. Scope MCP to the Seqera MCP Server (the interface for external AI assistants) in the concept page, neutralize MCP-as-mechanism claims elsewhere to 'directly / on your behalf', and reframe the skills section as 'Enhance CoScientist with your own skills'. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Resolve flags from authoritative sources: exact seqera ai CLI (install, login, goal mode), documented SKILL.md format under .agents/skills/, sourced MCP explanation, and the AWS/Bedrock enterprise model. Fix the non-existent "test profile" (use -profile docker), make the QUANT break exact (withName memory = 10.MB, OOM exit 137), specify real rnaseq-nf output files in the snapshot table, and ship a SKILL.md plus an illustrative QUANT nf-test under solutions/. Ground the capabilities tour in documented modes, commands, approval, and sessions. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Merge orientation + meet-coscientist + explore-platform into a single "Meet CoScientist" lesson (7 sections: connect, confirm, capabilities, MCP, survey, add pipeline, inspect CE), preserving all content except the enterprise/foundational-model note, which moves to the wrap-up. Drop the not-yet-true "connected GitHub account" claim and the /seqera-mcp CLI reference from the web-first lesson. Renumber remaining pages to six lessons and fix nav, cross-links, and the get-started button. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Replace AI-style section headers and aphorisms (binary contrasts, the "search box" simile, "drifts"/"grounded"/"course-correct" metaphors, the tricolon takeaway) with the plainer imperative voice used across the other side quests. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Rebuild lesson 2 around a concrete user-level exercise: launch rnaseq-nf with a bad transcriptome parameter, then practise prompting for intent, verifying the diagnosis against the real error, and redirecting the agent to fix the launch parameter without touching pipeline code. Every section now has an action and a checkpoint instead of pure prose. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Make explicit that rnaseq-nf ships its default transcriptome, so the fix is dropping the bad override rather than sourcing data. Avoids implying CoScientist needs separate data access. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
✅ Deploy Preview for nextflow-training ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
Contributor
|
Nextflow linting complete!
💡 Tip: Click filename locations to go directly to that code. View all 70 issuesView formatting changes
|
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Replace the contrived QUANT out-of-memory break/debug/fix arc with a constructive developer journey, removing the redundant second failure (the user-level debugging journey in lesson 2 is the only staged failure). New CLI-based arc: - 03 Develop on the CLI: switch to the CLI (why-CLI + install), fork rnaseq-nf, add a fastp step via an nf-core module, run it. - 04 Test, add CI, and open a PR: nf-tests (goal mode, snapshot stability), an nf-test GitHub Actions workflow, open the PR. - 05 Build a reusable skill: package the nf-test workflow as a skill. Delete the old development/debugging/fix-and-pr/testing-and-skills lessons; update nav, cross-links, and objectives. Also from review: remove the unsupportable MCP-as-transport claim from lesson 1, deduplicate the lesson 2 intro, and add the bi-directional "Explain with AI" round-trip (Platform to CoScientist) to lesson 2. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Web-first developer journey then an explicit CLI switch, plus content fixes from Slack review, a structure/content review, and validation against the real seqera CLI: - Lessons: 01 Meet CoScientist (web; adds a pipeline overview + mermaid DAG, drops the redundant "how it reaches assets" section), 02 Working with the agent (web; user-level failure fix, bidirectional "Explain with AI"), 03 Develop with CoScientist (web; GitHub key, fork, add a fastp step via an nf-core module, open a PR), 04 Move to the CLI (why-CLI, install, pipeline-level nf-test, snapshot stability, goal mode, GHA workflow, update the PR), 05 Build a reusable skill. - Rename/replace old development/debugging/fix/testing lessons; update nav, cross-links, and objectives. - Remove the unsupportable MCP-as-transport claim; move the enterprise foundational-model note to the wrap-up; motivate each lesson intro. - Make the skill scope-agnostic (process or pipeline) to match the pipeline-level test; ship solutions/pipeline.nf.test and an updated SKILL.md. CLI facts validated against seqera 1.10.0 (seqera ai/-c, approval modes, /goal, Plan/Goal modes, SKILL.md, /nextflow-config). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Confirm the chat URL and embed the landing screenshot (img/chat-landing.png) - Name the Workspace selector in the top nav; drop its flags (visible in landing shot) - Embed the Explain with AI screenshot (img/explain-with-ai.png) - Narrow the lesson-2 failure flag (fast INDEX failure confirmed; overridden-param launch still to verify) - Lesson 3 step 2: the user forks rnaseq-nf manually rather than via CoScientist Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Skills (lesson 5): SKILL.md files are loaded as SESSION CONTEXT, not exposed as slash commands (only backend skills are). Rewrite "Use the skill" so you don't /-invoke it; you ask for a test and it follows your rules. Add the mkdir+touch step. (Confirmed against the actual docs.) - Lesson 4: restructure into "Fork the repository" (clone + checkout the fastp branch) and "Install the CLI"; restore admonition formatting a formatter had mangled; ground the branch-name pattern. - Resolve TODOs: Launchpad screenshot (#5), overridden-param launch (#6), GitHub token mechanism (#8/#9), fastp/PR flow (#10), PR screenshot (#13). Remaining: web goal mode (#11), generated GHA workflow (#12), Typeform (#14). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
PR currently purely to make commenting easier. Do not merge to master!