skill-lab
AGENTS.md0 starsChanged 10 days agoMITView on GitHub
Personal Claude Code skills. Source of truth is skills/; deployed copies live in ~/.claude/skills/ (edit here, then copy).
In this repository20 other files it gives its agents.
- examples/CLAUDE.mdCLAUDE.md
- api-and-interface-designSkill
- backlogSkill
- c4-architectureSkill
- change-recordSkill
- ci-cd-and-automationSkill
- competitive-briefSkill
- documentation-and-adrsSkill
- frontend-designSkill
- frontend-ui-engineeringSkill
- git-workflow-and-versioningSkill
- oss-release-readinessSkill
- performance-optimizationSkill
- security-and-hardeningSkill
- shipping-and-launchSkill
- synthesize-researchSkill
- user-researchSkill
- ux-copySkill
- webapp-testingSkill
- web-visual-designSkill
The file
Files
skill-lab
Personal Claude Code skills. Source of truth is skills/; deployed copies live in ~/.claude/skills/ (edit here, then copy).
- Tests: run each file on its own, e.g.
python -I tests/test_gate_cli.py(printsok). Skill lint:python -I tools/skill_audit.py local=skills.tests/test_gantt.pyneeds matplotlib (uv run --isolated --no-project --python 3.13 --with matplotlib python -I tests/test_gantt.py);tests/test_render.shneeds mermaid-cli and is not in CI (.github/workflows/test.yml). - Commits are checked by the tier gate (
.agent-gate,tools/gate.py): every commit needs aTier: T0–T3trailer; T2/T3 changes need a change file indocs/changes/. Format and rules: skillchange-record(skills/change-record/SKILL.md). - Architecture:
docs/architecture/ARCHITECTURE.md. Decisions:docs/changes/. - Public repo:
README.md/README.zh-TW.md,LICENSE(MIT;skills/third-party dirs keep their own),examples/CLAUDE.mdis the user-level rule file. Before any publish runskills/oss-release-readiness/scripts/release_check.py.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.