Conduct AI agents like a CEO — orchestrate, delegate, ship.
Managing AI agents today feels like conducting an orchestra without a score. Zenith gives you the score — a growing library of battle-tested Claude Code skills that turn your agent into an executive command center.
Install a skill. Delegate the work. Stay in command.
# Install all Zenith skills
npx skills add openqa-labs/zenith
# Or install a single skill
npx skills add openqa-labs/zenith --skill project-kickoff| Skill | What it does |
|---|---|
project-kickoff |
Start any project from zero — interview, naming, repo setup, CI, README, first task |
Coming soon: project-monitor, status-report, product-ideation, feature-dev, product-marketing
Once installed, trigger a skill directly in Claude Code:
/project-kickoff I want to build a SaaS for tracking team productivity
Claude conducts a structured intake, researches the competitive landscape, sets up the repo, configures CI, writes the README, and creates your first task — end to end.
- End-to-end workflows — each skill owns a complete job, not just a step
- CEO-level thinking — skills ask the right strategic questions up front
- Opinionated defaults — sensible choices baked in, easy to override
- Quality-gated — every skill is validated by CI on every commit
We welcome new skills. The bar is high — each skill must handle a complete workflow end-to-end, not just wrap a single command.
git checkout -b feat/my-skill
# Create skills/my-skill/SKILL.md with name + description frontmatter
bash scripts/validate.sh # must pass before opening PRSee CONTRIBUTING.md for the full skill authoring guide.
MIT — see LICENSE for details.