github-flow-kit
AGENTS.md0 starsChanged 5 months agoMITView on GitHub
6 Claude Code skills for GitHub-native developers: pr-respond, release-notes, issue-triage, repo-tour, gh-pr-perm-audit, gh-repo-security-audit. Also hosts Zenn articles/books. A cloud session auto-installs deps (SessionStart hook) and loads this AGENTS.md + .claude/skills/. The 6 shipped skills live in their own top-level dirs (installed into a consumer's ~/.claude), while .claude/skills/run-tests is a repo-dev helper. MCP is local-only. See thinkyou0714/.github → docs/claude-code-web-readiness.md.
In this repository7 other files it gives its agents.
- run-testsSkill
- gh-pr-perm-auditSkill
- gh-repo-security-auditSkill
- issue-triageSkill
- pr-respondSkill
- release-notesSkill
- repo-tourSkill
The file
Files
AGENTS.md — github-flow-kit
6 Claude Code skills for GitHub-native developers: pr-respond, release-notes, issue-triage,
repo-tour, gh-pr-perm-audit, gh-repo-security-audit. Also hosts Zenn articles/books.
- Stack: Python skills (stdlib +
unittest) + Node/Zenn tooling forarticles/+books/. - Layout: one dir per skill (
pr-respond/,release-notes/, …) each withSKILL.md;tests/(Python unittest);scripts/. - Setup: deps auto-install via
.claude/bootstrap.shon SessionStart (npm cifor Zenn; Python tests need no install). Manual:npm ci. - Test:
npm test(→python3 -m unittest discover -s tests -p 'test_*.py'). - Zenn:
npm run preview/npm run new:article. - Conventions: each skill follows the SKILL.md frontmatter + trigger convention; see
CONTRIBUTING.md.
Claude Code on the web
A cloud session auto-installs deps (SessionStart hook) and loads this AGENTS.md + .claude/skills/.
The 6 shipped skills live in their own top-level dirs (installed into a consumer's ~/.claude), while
.claude/skills/run-tests is a repo-dev helper. MCP is local-only. See thinkyou0714/.github →
docs/claude-code-web-readiness.md.
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.

