github – Coding skill for AI agents
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
Install the github skill with one command
Pick the tool you use, copy the command and paste it in your terminal. The skill lands in that tool's skills folder and is ready in your next session.
Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://skill.dn1nguoi.com/z/github-d70ee.tgz | tar xz -C ~/.claude/skills
Call it in Claude Code: /github – then describe the task you want done.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/github-d70ee.tgz | tar xz -C ~/.codex/skills
Call it in Codex: $github – then describe the task you want done.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/github-d70ee.tgz | tar xz -C ~/.hermes/skills
Call it in Hermes Agent: /github – then describe the task you want done.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/github-d70ee.tgz | tar xz -C ~/.deepcode/skills
Call it in DeepSeek: /github – then describe the task you want done.
SKILL.md content
GitHub
Work GitHub end to end with the gh CLI (REST fallback where noted): auth,
issues, the PR lifecycle, issue-to-PR delivery, code review, and repo
management. This skill consolidates six former skills; each workflow lives
complete in its reference file — ALWAYS read the matching reference before
starting that workflow, the body below only routes.
Routing
| Task | Read first |
|---|---|
| Auth broken / new machine / token or SSH setup / gh login | references/auth.md |
| Create, triage, label, assign, close issues | references/issues.md |
| Branch, commit, open PR, watch CI, merge | references/pr-workflow.md |
| Carry an ISSUE to a verified PR (full delivery loop) | references/issue-to-pr.md |
| Review someone's PR: diffs, inline comments, verdict | references/code-review.md |
| Clone/create/fork repos, remotes, releases | references/repo-management.md |
Supporting assets: scripts/gh-env.sh + scripts/git-credential-token.py
(auth helpers), templates/ (PR bodies, bug report, feature request),
references/ci-troubleshooting.md, references/conventional-commits.md,
references/github-api-cheatsheet.md, references/review-output-template.md.
Core discipline (applies to every workflow)
- Preflight once per session:
gh auth status— if it fails, go to
references/auth.md before anything else.
- Prefer
ghover raw REST; drop togh apionly for endpoints the
porcelain lacks (the cheatsheet lists them).
- Never report CI green without checking
gh pr checksyourself; never
claim merged without verifying state,mergedAt.
- Read full context before writing:
gh issue view --comments/
gh pr view --comments — decisions live in threads, not titles.
- Sweep for duplicates before creating anything:
gh pr list --search / gh issue list --search.
Verification
- The workflow's own reference file defines done for that task.
- Cross-cutting: every claim about remote state (CI, merge, release,
issue state) is backed by a fresh gh read, never memory.
Related skills
- literature-review – Conducts systematic, scoping, and narrative literature reviews using PubMed, arXiv…
- azure-ai-projects-java – Azure AI Projects SDK for Java. High-level SDK for Azure AI Foundry project management…
- yeet – Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull…
- hunt-nodejs – Hunt Node.js specific vulnerabilities — Prototype Pollution → RCE chains…
- google-workspace – Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
- azure-ai-vision-imageanalysis-java – Build image analysis applications with Azure AI Vision SDK for Java. Use when…
- azure-ai-voicelive-java – Azure AI VoiceLive SDK for Java. Real-time bidirectional voice conversations with AI…
- langchain-architecture – Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool…