agentleFS
bntvllntbntvllnt/agent-skills/github/SKILL.md

github

Skill16 starsChanged 8 months agoMITView on GitHub

Manage GitHub via GitHub CLI (gh): repos, issues, pull requests, Actions, releases, secrets/variables, projects, gists, searches, and API access. Auto-activates on: "gh", "github cli", "github issue", "github pr", "pull request", "github actions", "workflow", "run", "github release", "release", "gh api", "github repo", "github secret", "github variable", "ci status", "monitor ci", "check ci", "watch ci", "pr dashboard", "pr overview", "open prs", "my prs", "pr status".

  • Commits and pushes

166 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use taskflow-inbox-triage, BlueBubbles and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AtomicBot-aiSkill

    taskflow-inbox-triage

    Also in 6 projects that use this

  • jiulingyunSkill

    BlueBubbles

    为Clawdbot构建或更新BlueBubbles外部通道插件(扩展包,REST发送/探测,webhook入站)。

    Also in 20 projects that use this

  • hkyutongSkill

    node-connect

    Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale, or plugins.entries.device-pair.config.publicUrl.

    Also in 18 projects that use this

  • molt-botSkill

    discord-e2e

    Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and Gateway evidence from manual user interactions.

    Also in 10 projects that use this

  • molt-botSkill

    openclaw-repair-sweep

    Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.

    Also in 10 projects that use this

  • clawdbotSkill

    openclaw-performance

    Performance work in OpenClaw: a slow or heavy flow (latency, CPU, memory, SQL, RPC, renders), writing or reviewing a perf PR, or adding a cache. Count the work, delete waste first, cache last.

    Also in 7 projects that use this

  • +2 more from molt-bot

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 151 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never upload secrets as assets.

    line 45
  2. Very specific:

    Treat gh api as powerful: confirm before any write operation.

    line 46
  3. Distinctive:

    Never delete or move published releases/tags unless explicitly requested.

    line 47
  4. Very specific:

    When creating PRs, always set an assignee: default to @me unless the user explicitly names someone else.

    line 48
  5. Very specific:

    When creating PRs, apply relevant existing labels when possible.

    line 49
  6. Very specific:

    If labels must be created, retrieve existing labels first (gh label list), propose the minimal set consistent with repo naming, and confirm …

    line 50
  7. Distinctive:

    Read-only commands are always OK.

    line 54

“Common” is measured: kept by at least 6 in 10 of the 151 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

GitHub

GitHub operations via gh.

Router

User saysLoad referenceDo
help / gh help / flags / optionsreferences/cli-help.mdshow CLI help safely
auth / login / tokenreferences/auth.mdauthenticate gh
repo / clone / fork / syncreferences/repo.mdrepository operations
issue / issuesreferences/issue.mdissue triage and management
pr / pull request / reviewreferences/pr.mdPR create/review/merge workflows
actions / workflow / runreferences/actions.mdGitHub Actions (workflows + runs)
ci / monitor ci / check ci / ci status / watch cireferences/ci-monitor.mdmonitor CI checks with live polling (if user says bare "ci", ask: monitor checks or view workflows?)
pr dashboard / pr overview / open prs / my prs / pr statusreferences/pr-dashboard.mdPR overview with status classification
release / publish releasereferences/release.mdreleases + assets + verification
release strategy / release format / versioningreferences/release-strategy.mdversioning, title/description format, generation protocol
secrets / variablesreferences/secrets-vars.mdmanage secrets and variables
projectreferences/projects.mdprojects operations
gistreferences/gists.mdgist operations
searchreferences/search.mdsearch repos/issues/prs/code
apireferences/api.mdgh api (advanced)
extensionreferences/extensions.mdmanage gh extensions
configreferences/config.mdgh config basics

Safety Rules

  • Confirm before any state-changing operation (create/edit/delete/merge/close).
  • Never upload secrets as assets.
  • Treat gh api as powerful: confirm before any write operation.
  • Never delete or move published releases/tags unless explicitly requested.
  • When creating PRs, always set an assignee: default to @me unless the user explicitly names someone else.
  • When creating PRs, apply relevant existing labels when possible; auto-pick from PR context (title/body/branch + changed paths) and avoid creating new labels unless truly necessary.
  • If labels must be created, retrieve existing labels first (gh label list), propose the minimal set consistent with repo naming, and confirm before gh label create.

Confirmation Policy

Read-only commands are always OK.

Require confirmation:

  • gh issue create/edit/close/reopen/delete
  • gh pr create/edit/close/merge/review
  • gh repo create/edit/rename/archive/delete/sync
  • gh release create/edit/delete, gh release upload, gh release delete-asset
  • gh secret set/delete, gh variable set/delete
  • gh run rerun, gh run cancel
  • gh api calls that mutate state (POST/PATCH/PUT/DELETE)

Read-Only (No Confirmation Needed)

gh auth status
gh release list
gh release view <tag>
gh release view <tag> --web
gh help
gh pr checks <number> --json ...
gh run list --branch <branch> --json ...
gh run view <run-id>
gh run view <run-id> --log-failed

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.