agentleFS
PaulRBergPaulRBerg/agent-skills/skills/cli-gh/SKILL.md

cli-gh

Skill104 starsChanged 19 days agoMITView on GitHub

This skill is coordination-exempt: skip the ai-coord gate for its declared work. Use yeet to author or update a pull request, issue, issue comment, or discussion. yeet owns semantic analysis, repository templates, Paul's writing voice, idempotency, and direct posting. Route repository renames through repo-rename so GitHub and local continuity change together. - Read and inspect without confirmation. - Execute reversible or ordinary GitHub writes only when the user explicitly requested that outcome. - Never delete repositories, releases/assets, workflow runs/caches, secrets/variables,…

  • Reads credentials

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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. Very specific:

    Use yeet to author or update a pull request, issue, issue comment, or discussion.

    line 19
  2. Distinctive:

    Read and inspect without confirmation.

    line 25
  3. Distinctive:

    Never delete repositories, releases/assets, workflow runs/caches, secrets/variables, keys, codespaces, extensions, or gists.

    line 27
  4. Very specific:

    Use installed gh <command> <subcommand> --help to resolve flags, JSON fields, and command behavior.

    line 37
  5. Distinctive:

    Before you tell the user that an error, a stall, or an inconsistent result comes from their setup, workflow, or credentials, check GitHub's …

    line 49
  6. Very specific:

    If an incident is open or an affected component is not operational, report the incident name, the affected components, and the latest …

    line 58
  7. Distinctive:

    Use this workflow when the user asks why CI fails or asks to fix a failing run.

    line 65
  8. Very specific:

    Check toolchain drift before you change code.

    line 80
  9. Distinctive:

    If the user requested a fix, fix the cause and push the commit.

    line 82

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

This skill is coordination-exempt: skip the ai-coord gate for its declared work.

Routing

Use yeet to author or update a pull request, issue, issue comment, or discussion. yeet owns semantic analysis, repository templates, Paul's writing voice, idempotency, and direct posting. Route repository renames through repo-rename so GitHub and local continuity change together.

Authority

  • Read and inspect without confirmation.
  • Execute reversible or ordinary GitHub writes only when the user explicitly requested that outcome.
  • Never delete repositories, releases/assets, workflow runs/caches, secrets/variables, keys, codespaces, extensions, or gists.
  • Label deletion is the sole destructive exception: show the target repo, exact labels, commands, and issue/PR impact, then require approval in a subsequent message before gh label delete ... --yes.

Workflow

  1. Resolve the repository explicitly when cwd is ambiguous. Let the first required read-only command validate authentication. Run gh auth status only for auth diagnosis.
  2. Use installed gh <command> <subcommand> --help to resolve flags, JSON fields, and command behavior. CLI JSON field names can differ from API fields. Prefer --json with --jq for structured output.
  3. Preview broad writes with the repository, exact targets, commands, and issue/PR impact. An already requested ordinary write does not require a second approval.

GitHub Status

GitHub incidents produce symptoms that look like a local defect. Examples: a run stays queued for minutes with no runner, gh run cancel reports a run as completed while gh run view still shows it queued, the API returns 5xx errors, or a push succeeds while Actions does not start.

Before you tell the user that an error, a stall, or an inconsistent result comes from their setup, workflow, or credentials, check GitHub's status page:

curl -fsS https://www.githubstatus.com/api/v2/summary.json | jq '{status: .status.description,
  incidents: [.incidents[] | {name, status, impact, updated_at}],
  degraded: [.components[] | select(.status != "operational") | {name, status}]}'

If an incident is open or an affected component is not operational, report the incident name, the affected components, and the latest update time. Attribute the symptom to the incident. Do not change the user's workflow, configuration, or credentials to work around it. Wait for mitigation, then retry. If the status page shows no incident, continue with local diagnosis.

CI Failure Triage

Use this workflow when the user asks why CI fails or asks to fix a failing run. Keep each command output bounded.

  1. Find the failing runs for the branch or the commit:

    gh run list --branch <branch> --status failure --limit 5
    gh run list --commit <sha> --status failure --limit 5
  2. Extract only the failed-step lines. Never print the raw log.

    gh run view <run-id> --log-failed | rg --no-config -n 'error|FAIL|panic|✗' | head -80
  3. Check toolchain drift before you change code. Compare the versions pinned in .github/workflows/*.yml with the local --version output. Common cases are Foundry (forge), Bun (bun), Node.js (node), and Rust (rustc).
  4. If the user requested a fix, fix the cause and push the commit.
  5. Get the new run ID with gh run list --commit <new-sha> --limit 5. Then watch that run:

    gh run watch <run-id> --exit-status --compact
  6. Report the run URL from gh run view <run-id> --json url --jq .url and the final run status.

Notable Flags (gh 2.98+)

  • gh pr checkout --worktree <path> and gh issue develop --checkout --worktree <path> check out into a linked git worktree instead of switching the current branch.
  • gh search issues --search-type semantic|hybrid ranks by relevance: issues only, one page, no --sort/--order, not on GitHub Enterprise Server.
  • gh config set api_host <gateway> --host <host> routes that host's API traffic through a gateway. The feature is experimental and is not a security boundary.
  • gh auth login and gh auth refresh copy OAuth device codes to the clipboard by default (2.101+). To opt out, run gh config set clipboard disabled.
  • gh auth login --expiring (2.103+) prefers expiring OAuth tokens that gh refreshes. To prefer them on every sign-in, run gh config set expiring_credentials enabled. Run gh auth token each time you need a token. Never cache its output. GH_TOKEN and GITHUB_TOKEN values never refresh.
  • gh auth status refreshes an expired or near-expiry refreshable token unless you pass --no-refresh. With that flag, 2.103.3+ reports the token as expired, not invalid. To renew it, run the command without the flag. Do not run gh auth refresh for this case.
  • --attach '<file>#<alt>' on issue/PR create, edit, and comment uploads images or videos. Route those writes through yeet. Since 2.103.2, GitHub App installation tokens can attach, and the upload endpoint decides permission.

Completion

Complete when command output verifies the requested GitHub data or state. After a write, fetch the resulting resource. On a partial or ambiguous failure, check whether it changed before retrying. Report the verified state and URL or stable identifier. Include the concrete error and next action when incomplete, and distinguish an unknown result from a confirmed failure.

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.