agentleFS
cogine-aicogine-ai/cogine-dev-skillset/skills/babysit-pr/SKILL.md

babysit-pr

Skill3 starsChanged 5 months agoApache-2.0View on GitHub

Follow a GitHub PR through CI and review to a requested outcome, including as part of takeover.

60 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use html-communication, why and 2 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Solly922Skill

    html-communication

    Create self-contained HTML artifacts for plans, architecture maps, comparisons, reports, timelines, diagrams, and technical explainers when visual structure improves understanding. Use for complex or spatial information; do not use for short, linear answers that are clearer in Markdown.

    Also in 3 projects that use this

  • jaydubya818Skill

    why

    Use when design rationale must be recovered from source history and available records.

    Also in 6 projects that use this

  • jaydubya818Skill

    how

    Use for runtime, ownership, layering, code-walkthrough, and placement questions.

    Also in 4 projects that use this

  • Hugging FaceSkill

    simplify

    Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 59 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when following an existing PR is part of the user's request.

    line 8
  2. Distinctive:

    Follow CodeRabbit as the primary automated reviewer where used.

    line 17
  3. Very specific:

    Verify each actionable finding against the current code.

    line 21
  4. Very specific:

    Follow the PR in the current task using one watcher.

    line 25
  5. Distinctive:

    Stop when the requested outcome is reached, the PR closes, or a decision outside the granted scope is needed.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 59 edited versions of this file we could read. “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

Babysit PR

Use when following an existing PR is part of the user's request. Default to following through required checks and review, then report any remaining approval. Fix, push, post replies, resolve threads, or merge within the user's authorization for those actions.

  1. Resolve the live PR, head SHA, and base. Read existing checks and review feedback before waiting. Use gh pr view for review and merge state and gh pr checks for PR checks. Use --required for reported required checks and verify the repository rules if an expected check is missing.
  2. Follow CodeRabbit as the primary automated reviewer where used. Include QA, human reviews, and other bots as configured or requested. Use the repository rules and the user's request to determine what must finish. Keep optional results separate and distinguish pending, failed, and completed reviews.
  3. Verify each actionable finding against the current code. Focus authorized fixes on real issues, test before pushing, and use leaving-pr-comments for any authorized reply. Preserve the context of existing review threads.
  4. Follow the PR in the current task using one watcher. For reported pending required checks, use gh pr checks --required --watch --fail-fast. Refresh the live PR periodically when waiting for review. Re-read reviews and checks after each push and whenever the head or relevant base changes.
  5. Stop when the requested outcome is reached, the PR closes, or a decision outside the granted scope is needed. Report CI, review, and any remaining approval separately. Check GitHub's live review decision and merge state before saying a PR is ready.

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.