agentleFS
davidvornholtdavidvornholt/mailbox/.agents/skills/review-fix/SKILL.md

review-fix

Skill2 starsChanged yesterdayMITView on GitHub

Use when asked to review a pull request and fix its findings in the same review loop.

11 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Run one review-and-fix cycle on a pull request, with at most three reviews, then report and stop.

    line 8
  2. Distinctive:

    Run the full gate after the last change.

    line 37
  3. Very specific:

    Run gh pr ready unless an ask is open.

    line 51

“Common” is measured: kept by at least 6 in 10 of the 9 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

Review and fix

Run one review-and-fix cycle on a pull request, with at most three reviews, then report and stop. Reviewing a fix always turns up something, so never add a review or repair beyond the ones below.

Work in a dedicated worktree on a draft pull request. Add commits rather than amending or force-pushing. Note the time you start, because the report gives the total time.

Reviewers

Reviewers use GPT-6 Astra at high effort unless the user names another model. Use delegate_task if your harness can't run it. If nothing can, stop and say why. Never substitute a model.

Each reviewer is a separate read-only agent that follows the review skill and looks for one kind of failure:

  • Behavior: correctness, error paths, edge cases, and whether the tests can fail.
  • Premise: whether the change solves the problem its description states and fits the architecture and operational contracts. This reviewer also owns documentation cuts and anything no other reviewer covers.

A prose-only change gets only the premise reviewer, and any other change gets both. Add a reviewer for each specific risk the diff exposes, such as outbound mail or concurrency.

Review

Reuse a gate that passed on this exact commit, or run it once, and fix only mechanical failures the pull request introduced.

Give each reviewer the range from base to head, the pull request's description, the gate result, its kind of failure, and the other reviewers' kinds. Retry one that doesn't report. If it still doesn't report, stop, because a partial review isn't a safe basis for fixes.

Reviewers propose a label for each finding, and you decide the final one. Put each ask to the user yourself, as AGENTS.md describes, rather than in the report.

Fix

A worker on your own model fixes each blocker: it reproduces the failure, makes the smallest correction, adds the recommended test, and runs focused checks. If it can't reproduce the failure, don't fix it on speculation, and relabel the finding. Then make all cuts in one commit.

One reviewer then reads only the fix commits, unless they change only prose or tests. If it finds a blocker the fixes left or a defect they introduced, repair it once. Review that repair the same way only if you judge that a reviewer could find a bug in it that someone would otherwise run into. If that review finds a defect, repair it once more and confirm that repair with tests alone. Defer or drop anything that was already there.

Run the full gate after the last change.

Report

File an issue with the issues skill for each deferred finding that someone would otherwise run into.

Post one comment on the pull request, leaving out any part with nothing in it:

  • A table with one row per review, including skipped ones: what it reviewed, its reviewers, its findings by label, and the outcome.
  • One line with the final gate result and the total time.
  • One table row per finding: its file and line, what goes wrong, every reviewer that reported it, its label, and the commit that fixed it or why it wasn't fixed. Naming the reviewers shows which ones find what the others miss.
  • Each label you changed, and why.
  • Any risk that remains. If it would show only after deployment, name the check that covers it or file an issue for one.

Run gh pr ready unless an ask is open. If the user asked you to land the pull request when you're confident, and you are, land it as the prs skill describes. Otherwise report CI as pending, and stop.

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.