agentsclimarketplace

Cli gh

Skill PaulRBerg/agent-skills/skills/cli-gh

PRB's collection of agent skills

Install
npx -y skills add PaulRBerg/agent-skills --skill cli-gh

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

4.1 KB, as published. Nobody here has run it

GitHub CLI

Route GitHub CLI work through current gh help and load only the reference for the active task.

Boundary with yeet

Use yeet when the requested outcome is to create or update a pull request, issue, issue comment, or discussion. yeet owns semantic analysis, repository templates, Paul's writing voice, idempotency, and direct posting. Use this skill for read-only GitHub inspection, command syntax, searches, workflow operations, codespaces, releases, configuration, and other GitHub automation.

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.
  • Route repository renames through repo-rename so GitHub and local continuity change together.

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. Inspect gh <command> <subcommand> --help for the installed version before relying on flags or JSON fields. Prefer --json plus --jq for machine-readable results.

  3. Load only the relevant reference:

    TaskReference
    Workflow runs, checks, logsreferences/workflows-actions.md
    Releasesreferences/releases.md
    Searchreferences/search.md
    JSON fields and jqreferences/json-output.md
    Labelsreferences/labels.md
    Codespacesreferences/codespaces.md
    Discussions syntax (not authored contribution workflow)references/discussions.md
    Gistsreferences/gists.md
    Aliases, API, extensions, org/projects, secrets, rulesetsreferences/advanced-features.md
    Reusable automation patternsreferences/automation-workflows.md
    Failures and auth/rate limitsreferences/troubleshooting.md
  4. Preview commands that have broad write scope. After a requested write, fetch the resulting resource and report its URL or stable identifier.

Completion requires the requested GitHub state or data plus command/output evidence. On a partial or ambiguous write failure, check whether the resource changed before retrying.

User-Facing Output

Use ### ⚠️ GitHub write preview for broad writes, showing the repository, exact targets, and issue/PR impact in a compact table, with each exact command in its own fenced block; an already requested ordinary write does not require a second approval. For label deletion, use ### ⛔ Destructive approval required and ask for approval in a later message. After a verified write, use ### ✅ GitHub operation complete with the action, repository, resource, and URL or stable ID. On failure, state the attempted operation, verified resulting state, concrete error, and next action without implying a write succeeded. Keep commands, JSON, identifiers, diagnostics, and output intended for piping undecorated.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.