agentleFS
Sign inStart free
loganware05loganware05/captains-compass-cursor/.cursor/skills/pull-request-preparation/SKILL.md

pull-request-preparation

Skill2 starsChanged 32 days agoMITView on GitHub

Assembles PR description, evidence package, and completion report after validation

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    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. Very specific:

    If gh (or GitHub MCP) is authenticated, create the remote PR.

    line 28
  2. Distinctive:

    Update PROGRESS.md and CHANGELOG.md as needed.

    line 30
  3. Very specific:

    When closing out, load Skill execution-telemetry and record the run/Experience.

    line 31
  4. Distinctive:

    Do not deploy to production without explicit approval.

    line 43
  5. Distinctive:

    Do not omit failed or skipped validation from the report.

    line 44
  6. Distinctive:

    Do not fail the workflow solely because GitHub auth is unavailable.

    line 45

≈ “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

Pull Request Preparation

Use this Skill when

Implementation and validation are complete and the change is ready for Captain review.

Inputs

  • Approved IMPLEMENTATION_PLAN.md
  • Commits and branch
  • Validation evidence
  • Updated documentation

Procedure

  1. Confirm Definition of Done items are satisfied or explicitly waived.
  2. Summarize the change against acceptance criteria.
  3. Link issue, plan, and evidence paths.
  4. List test commands and results.
  5. Note risks, follow-ups, and rollback steps.
  6. Draft the pull request title and body.
  7. Load the github-integration Skill:
    • If gh (or GitHub MCP) is authenticated, create the remote PR.
    • Otherwise, leave a PR-ready description and local issue placeholder.
  8. Update PROGRESS.md and CHANGELOG.md as needed.
  9. When closing out, load Skill execution-telemetry and record the run/Experience.
  10. Produce a First Mate completion report.

See also: review-fix-loop when review feedback still needs iterative fixes before this Skill runs.

Output

PR (remote when possible) or PR-ready description, plus completion report for the Captain.

Prohibited actions

  • Do not auto-merge.
  • Do not deploy to production without explicit approval.
  • Do not omit failed or skipped validation from the report.
  • Do not fail the workflow solely because GitHub auth is unavailable.

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.

Check your setup, free