agentleFS
IvanCamposIvanCampos/agents/skills/github/SKILL.md

github

Skill5 starsChanged 9 months agoMITView on GitHub

Use the GitHub CLI (`gh`) to inspect and manage repositories, pull requests, issues, workflows, releases, and API calls from the terminal. Use when a user asks to use `gh`/GitHub CLI, run GitHub repo or PR workflows, automate GitHub Actions from shell, or troubleshoot `gh` authentication and configuration.

  • 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

8 rules. 0 are common, 2 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 151 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use gh for day-to-day GitHub operations from the terminal.

    line 9
  2. Distinctive:

    Check installation and auth:

    line 12
  3. Very specific:

    If not in the target repository, pass -R owner/repo to commands.

    line 21
  4. Very specific:

    Use --json with --jq or --template for automation-friendly output.

    line 22
  5. Very specific:

    Run scripts/gh_preflight.sh before multi-step operations.

    line 27
  6. Very specific:

    Use list, view, and status subcommands before changing anything.

    line 29
  7. Very specific:

    Avoid destructive flags (--delete-branch, force flags) unless explicitly requested.

    line 79
  8. Distinctive:

    Use JSON output when parsing or summarizing results:

    line 83

“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 CLI

Overview

Use gh for day-to-day GitHub operations from the terminal. Prefer read-only commands first, then run mutating commands only after clear user intent.

Quick Start

  1. Check installation and auth:
gh --version
gh auth status
  1. Establish repository context:
scripts/gh_preflight.sh --repo owner/repo
  1. If not in the target repository, pass -R owner/repo to commands.
  2. Use --json with --jq or --template for automation-friendly output.

Workflow

  1. Establish context first.
  • Determine GitHub host (github.com by default), repository, and branch.
  • Run scripts/gh_preflight.sh before multi-step operations.
  1. Read current state.
  • Use list, view, and status subcommands before changing anything.
  1. Apply requested mutation.
  • For create/edit/merge/delete actions, restate the operation and require explicit confirmation unless the user already asked clearly.
  1. Report stable identifiers.
  • Return URLs and IDs for created or changed objects (PR number, issue number, run URL, release tag).

Common Commands

  • Repository:
    • gh repo view
    • gh repo clone owner/repo
    • gh repo create
    • gh repo set-default owner/repo
  • Pull requests:
    • gh pr list
    • gh pr view <number>
    • gh pr checkout <number>
    • gh pr create
    • gh pr review <number> --approve|--request-changes|--comment
    • gh pr merge <number>
  • Issues:
    • gh issue list
    • gh issue view <number>
    • gh issue create
    • gh issue comment <number> --body "..."
    • gh issue close <number>
  • Actions:
    • gh workflow list
    • gh workflow run <workflow>
    • gh run list
    • gh run watch <run-id>
    • gh run view <run-id> --log
  • Releases:
    • gh release list
    • gh release view <tag>
    • gh release create <tag> [assets...]
    • gh release upload <tag> <file>
  • API:
    • gh api repos/{owner}/{repo}/pulls --paginate

For broader command coverage, read references/command-map.md.

Safety Defaults

  • Confirm before commands that change remote state:
    • gh pr create|merge|close|reopen|ready
    • gh issue create|edit|close|reopen|delete
    • gh repo create|edit|archive|delete
    • gh release create|edit|delete
    • gh secret set|delete
    • gh variable set|delete
    • gh workflow run
  • Avoid destructive flags (--delete-branch, force flags) unless explicitly requested.
  • Show exact command before bulk updates and prefer smallest safe scope.

Structured Output

Use JSON output when parsing or summarizing results:

gh pr list --json number,title,url --jq '.[] | "\(.number)\t\(.title)\t\(.url)"'
gh issue list --json number,title,labels --template '{{range .}}{{printf "#%v %v\n" .number .title}}{{end}}'

Troubleshooting

  • Auth errors: gh auth login or gh auth refresh.
  • Wrong account/host: gh auth status --hostname github.com, then gh auth switch.
  • Unknown command options: gh <command> <subcommand> --help.
  • Manual reference: https://cli.github.com/manual/.

Resources

scripts/

  • scripts/gh_preflight.sh: Check gh availability, auth status, and repository context.

references/

  • references/command-map.md: Command map for repo, PR, issue, actions, release, and API operations.

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.