agentleFS
sreejithramansreejithraman/SreeStack/skills/pr/SKILL.md

pr

Skill1 starsChanged 16 days agoMITView on GitHub

Draft PR text, prepare or publish a PR, fix review feedback, babysit CI and reviews, or merge when requested.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Watch/babysit/feedback: start with CI and reviews.

    line 14
  2. Distinctive:

    Prepare/publish: use the delivery workflow below.

    line 17
  3. Distinctive:

    Follow CI and reviews through fixes, waiting, and readiness.

    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

PR

Resolve the target PR or branch, its immediate base, intended changes, and requested outcome. Exclude unrelated local work from review inputs and fixes.

  • Title/body: inspect the diff and evidence, then use PR body. Return text locally unless asked to update the remote description. This route does not commit, push, or run the delivery workflow.
  • Watch/babysit/feedback: start with CI and reviews. For comments and threads, read PR feedback. An unchanged PR needs no local review or publication.
  • Prepare/publish: use the delivery workflow below.
  • Merge: reuse applicable delivery evidence; complete missing preparation below, then hand off to merge.

Publish ready for review unless the user requests a draft. Merge only when requested; /pr yolo or a later “merge” for this PR authorizes landing after required fixes and checks. A draft request takes precedence. Ask for the target if a merge request could refer to several PRs. Stack operations belong to gh-stack.

Thread registration

In T3, call link_pull_request immediately for each PR taken over, created, or pushed, including every stack layer. Follow live host rules for registration; background mentions and read-only reviews need no link. Report registration failures separately from publication.

Deliver changes

  1. Invoke Show, Don't Tell on the complete PR diff against the immediate base, including docs-only changes. Then run review-fix-loop over the resulting complete diff. Reuse matching preparation and review evidence. Record that review included this pass and tie readiness evidence to the published head/base. Continue after review and verification pass.
  2. Publish the owned changes and record the remote head and base.
  3. Follow CI and reviews through fixes, waiting, and readiness.

At readiness, hand off unless merging was requested. For preparation requested by Merge, return the PR, verified head/base, readiness evidence, related issues, and task resources to that original caller; it retains the full merge set and landing responsibility. For a direct PR merge request, pass the same evidence and resources to merge; it owns landing, issue completion, and cleanup.

Report the PR link, current head, verification, readiness or merge result, and remaining blockers. Include issue and cleanup results when merging.

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.