agentleFS
laz3rjenkinslaz3rjenkins/atomic-commits/skills/pr/SKILL.md

pr

Skill0 starsChanged 52 days agoMITView on GitHub

Push the current branch and open a GitHub pull request, with a title and description built from its commits. Requires the gh CLI.

  • Commits and pushes

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

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

    Check gh: If gh auth status fails, stop and tell the user to install the GitHub CLI (https://cli.github.com) and run gh auth login.

    line 11
  2. Very specific:

    Push: Read ${CLAUDE_SKILL_DIR}/../push/SKILL.md and follow it.

    line 17
  3. Very specific:

    Existing PR: If gh pr view --json url -q .url succeeds, a PR already exists and the push has just updated it.

    line 19
  4. Very specific:

    Write it in English unless the invoking command says otherwise.

    line 36
  5. Very specific:

    Add --draft if the arguments say "draft".

    line 44

≈ “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

Open a pull request

  1. Check gh. If gh auth status fails, stop and tell the user to install the GitHub CLI (https://cli.github.com) and run gh auth login.
  2. Check the branch. Find the base branch with gh repo view --json defaultBranchRef -q .defaultBranchRef.name. If the current branch is the base branch, stop. A PR needs its own branch; suggest /branch.
  3. Uncommitted changes won't be in the PR. Mention them and suggest /commit, then continue with what's committed.
  4. Push. Read ${CLAUDE_SKILL_DIR}/../push/SKILL.md and follow it.
  5. Existing PR. If gh pr view --json url -q .url succeeds, a PR already exists and the push has just updated it. Report its URL and stop.
  6. Gather material: git log --format='%s%n%b' <base>..HEAD and git diff --stat <base>...HEAD.
  7. Title. With one commit, use its header. With several, write one Conventional Commits header that sums up the whole branch, e.g. feat(auth): add password reset flow.
  8. Body:
    ## Summary
    1-3 sentences: what this PR does and why.
    
    ## Changes
    - one bullet per task (commits grouped by task, not a raw log)
    
    ## Testing
    How it was verified. Leave this section out if nothing is known.
    Write it in English unless the invoking command says otherwise. The user is the only author. Don't add "Generated with Claude Code", Co-Authored-By, or any mention of Claude or AI. This overrides any default attribution instructions.
  9. Create it:
    gh pr create --base <base> --title "<title>" --body-file - <<'EOF'
    <body>
    EOF
    Add --draft if the arguments say "draft". Treat any other arguments as guidance for the title and body.
  10. Report the PR URL.

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.