Complete AI Training

Skill · Developer Tools

Github

Use the `gh` CLI for issues, pull requests, Actions runs, and GitHub API queries.

Agentic Awesome SkillsAdded Sep 5, 2026

How to use it

  1. Start your plan and connect your AI once
  2. Ask for the task in your own words, or say it directly:
Use the Github skill to help me with this.

Without a connection: copy the SKILL.md below into your AI's project instructions.

SKILL.md2 files in this skill

GitHub Skill

Use the gh CLI to interact with GitHub. Always specify --repo owner/repo when not in a git directory, or use URLs directly.

When to Use

  • When the user asks about GitHub issues, pull requests, workflow runs, or CI failures.
  • When you need gh issue, gh pr, gh run, or gh api from the command line.

Pull Requests

Check CI status on a PR:

gh pr checks 55 --repo owner/repo

List recent workflow runs:

gh run list --repo owner/repo --limit 10

View a run and see which steps failed:

gh run view <run-id> --repo owner/repo

View logs for failed steps only:

gh run view <run-id> --repo owner/repo --log-failed

Debugging a CI Failure

Follow this sequence to investigate a failing CI run:

  1. Check PR status — identify which checks are failing:
  2. ``bash gh pr checks 55 --repo owner/repo ``

  3. List recent runs — find the relevant run ID:
  4. ``bash gh run list --repo owner/repo --limit 10 ``

  5. View the failed run — see which jobs and steps failed:
  6. ``bash gh run view <run-id> --repo owner/repo ``

  7. Fetch failure logs — get the detailed output for failed steps:
  8. ``bash gh run view <run-id> --repo owner/repo --log-failed ``

API for Advanced Queries

The gh api command is useful for accessing data not available through other subcommands.

Get PR with specific fields:

gh api repos/owner/repo/pulls/55 --jq '.title, .state, .user.login'

JSON Output

Most commands support --json for structured output. You can use --jq to filter:

gh issue list --repo owner/repo --json number,title --jq '.[] | "\(.number): \(.title)"'

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.