agentleFS
jhy0285jhy0285/monofield/skills/pr-feedback-quality-gate/SKILL.md

pr-feedback-quality-gate

Skill6 starsChanged 6 months agoApache-2.0View on GitHub

Safely track pull request feedback, resolve review comments or merge conflicts, validate fixes, and use a read-only cross-review before committing or pushing follow-up changes.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this when a PR has review feedback, merge conflicts, pending checks, or needs a monitored follow-up after a fix.

    line 18
  2. Distinctive:

    Use an isolated worktree for review fixes or conflict resolution when the main checkout is dirty, behind remote, or being used by another …

    line 25
  3. Very specific:

    Run the narrow validation first, then the repository-required gates.

    line 29
  4. Distinctive:

    Before commit or push, run a read-only cross-review of the staged or proposed diff.

    line 32
  5. Distinctive:

    Treat cross-review as evidence, not authority.

    line 34
  6. Distinctive:

    If accepted blockers remain, fix them, rerun validation, and repeat the review.

    line 38
  7. Distinctive:

    Always report PR state, actions taken, cross-review verdict, accepted or rejected findings, validation run, commits pushed, skipped checks …

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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 Feedback Quality Gate

Use this when a PR has review feedback, merge conflicts, pending checks, or needs a monitored follow-up after a fix.

Workflow

  1. Inspect PR state first: comments, reviews, mergeability, checks, branch, and local worktree status. Keep unrelated local changes out of the PR.
  2. Use an isolated worktree for review fixes or conflict resolution when the main checkout is dirty, behind remote, or being used by another agent.
  3. Make the smallest safe fix. Preserve the original bug invariant and any newer upstream structure introduced by main.
  4. Run the narrow validation first, then the repository-required gates. For this repo, include pnpm guard; add package typechecks/builds/tests when touched files require them.
  5. Before commit or push, run a read-only cross-review of the staged or proposed diff. Forbid file edits and git write or coordination commands.
  6. Treat cross-review as evidence, not authority. Accept only findings grounded in the diff, repository rules, user goal, or validation results. Downgrade or reject style preferences, broad scope expansion, and suggestions that conflict with safety or ownership boundaries; record the reason briefly.
  7. If accepted blockers remain, fix them, rerun validation, and repeat the review. Commit and push only after validation passes and there are no accepted blockers.

Monitoring cadence

  • Active review or failing checks: check often enough to unblock quickly.
  • Clean or approved PR waiting for merge: check about every 12 hours.
  • Merged PR: reduce to daily lightweight observation for CI, release, or regression signals, and stop making code changes unless asked.

Report

Always report PR state, actions taken, cross-review verdict, accepted or rejected findings, validation run, commits pushed, skipped checks with reasons, remaining risks, and next step.

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.