GitHub Platform Skill

Faithful, task-routed guidance for working with GitHub the platform: repositories and branch protection, pull requests, issues and Projects, GitHub Actions, the gh CLI, and the REST/GraphQL APIs.

Part of Agent Kaizen — Agent Kaizen is designed to support reliable AI agent workflows, context engineering, and AI systems engineering in VS Code, Codex, and Claude Code. Build reusable agent skills, reduce unnecessary context loading, add validation loops, and apply Spec → Verifier → Environment scaffolding to new and existing projects.

This repository is the github skill: a reusable, trigger-rich task handbook that an AI coding agent (OpenAI Codex, Claude Code) loads on demand when a task matches its triggers.

What this skill covers

It covers GitHub the platform layer on top of git: creating and managing repositories, branch protection and rulesets, required reviews, status checks, and the default branch; opening, reviewing, and merging pull requests (merge vs squash vs rebase, CODEOWNERS, draft PRs); issues, labels, milestones, issue templates/forms, and Projects (v2). It also covers authoring and debugging GitHub Actions workflows under .github/workflows/*.yml — on, jobs, runs-on, uses, with, permissions, matrix, contexts, GITHUB_TOKEN, caching, artifacts, and reusable workflows — plus the gh CLI (gh pr/issue/run/workflow/release/api), the REST and GraphQL APIs, GitHub Apps and webhooks, authentication and security (PATs, SSH keys, Dependabot, CodeQL, secret scanning), Pages, Packages (ghcr.io), Codespaces, and organization/repository roles. It also fires when you edit files under .github/ or paste a workflow error, even without naming "GitHub" — and defers core git mechanics to the git skill.

What's inside

• SKILL.md — frontmatter (name + trigger-rich description) and a lean body.
• references/ — right-sized topic files the agent loads only when relevant (plus INDEX.md and topics.json).
• GOTCHA.md — known pitfalls and edge cases.

Use it

This skill is one git repo inside the Agent Kaizen skills store. The store nests two folders on purpose: the outer SKILLS\ is a VS Code project for building and maintaining skills (its own workspace + tooling), and the inner lowercase skills\ holds every skill as its own repo. That split lets a project pull skills two ways — the whole skills\ folder at once (loads everything — not recommended) or one skill at a time (recommended: load only what a task needs and stay under Claude Code's skill-listing budget).

Paths below use %DEVROOT% — the DEVROOT environment variable pointing at the folder that contains SKILLS\. Set it once by running SetDevRoot.cmd in the SKILLS repo root (no admin); a new shell then resolves %DEVROOT% automatically.

Link just this skill (recommended) — a Windows directory junction, no admin:

mklink /J .agents\skills\github  "%DEVROOT%\SKILLS\skills\github"
mklink /J .claude\skills\github  "%DEVROOT%\SKILLS\skills\github"

Or link the whole store at once (loads every skill — not recommended outside a skills-dev project):

mklink /J .agents\skills  "%DEVROOT%\SKILLS\skills"
mklink /J .claude\skills  "%DEVROOT%\SKILLS\skills"

Remove a link (the store copy is untouched):

rmdir .agents\skills\github
rmdir .claude\skills\github

The agent (OpenAI Codex, Claude Code) then auto-loads this skill whenever a task matches its triggers. Built and validated with skill-drafting to the Agent Kaizen gold standard.

License

Licensed under AGPL-3.0, matching the Agent Kaizen project.