agentleFS
leighstillardleighstillard/coach-ship-skills/skills/pr/SKILL.md

pr

Skill2 starsChanged 5 months agoMITView on GitHub

Commit, push, and open a pull request for the current change. Use when the user says open a PR, ship this, commit and push, or as the PR creation step of /ship. Requires verification evidence in the PR body.

  • Reads credentials
  • Commits and pushes

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Run git status --short --untracked-files=all and inspect git diff / staged diff.

    line 12
  2. Distinctive:

    Do not commit on the default branch.

    line 15
  3. Distinctive:

    If the branch is stale, rebase/merge according to repo convention before opening the PR.

    line 16
  4. Distinctive:

    Keep one logical change per commit unless repo convention prefers squash-only noise-free branches.

    line 22
  5. Very specific:

    Check for .github/PULL_REQUEST_TEMPLATE* and honor it.

    line 25
  6. Very specific:

    If gh auth status fails, stop and ask for auth.

    line 41
  7. Distinctive:

    Do not force-push over review activity without explicit instruction.

    line 42
  8. Distinctive:

    If diff is very large, mention split risk before opening unless the user explicitly asked for one PR.

    line 43

≈ “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

PR

Goal

A clean branch is pushed and a PR exists with enough evidence for a reviewer to understand what changed, why, how it was verified, and what risk remains.

Step 1: Pre-flight

  • Run git status --short --untracked-files=all and inspect git diff / staged diff.
  • Confirm no secrets, .env, debug prints, unrelated files, generated junk, or large binaries are included.
  • Identify the default branch (gh repo view --json defaultBranchRef or git symbolic-ref refs/remotes/origin/HEAD).
  • Do not commit on the default branch. Create a short kebab-case branch if needed.
  • If the branch is stale, rebase/merge according to repo convention before opening the PR.

Step 2: Commit

  • Stage deliberately by path. Use git add -A only after every untracked path is accounted for.
  • Match commit convention from recent history.
  • Summary line: imperative, ≤72 chars, states what changed and why.
  • Keep one logical change per commit unless repo convention prefers squash-only noise-free branches.

Step 3: PR body

Check for .github/PULL_REQUEST_TEMPLATE* and honor it. Include, at minimum:

  • What — concise behaviour/change summary.
  • Why — user issue/ticket/context.
  • How verified — paste the verification evidence: commands and representative output. Tests pass alone is insufficient.
  • Review/design — independent review status and design screenshots/output when applicable.
  • Risk / rollback — likely failure modes and how to revert/disable.

Step 4: Push/open

Run:

git push -u origin <branch>
gh pr create --title "<summary>" --body "<body>"

Then output the PR URL.

Gotchas

  • If gh auth status fails, stop and ask for auth; do not improvise credentials.
  • Do not force-push over review activity without explicit instruction.
  • If diff is very large, mention split risk before opening unless the user explicitly asked for one PR.
  • CI config changes must be called out in the PR body.

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.