agentleFS
sreejithramansreejithraman/SreeStack/skills/review-sweep/SKILL.md

review-sweep

Skill1 starsChanged 16 days agoMITView on GitHub

Validate supplied review or CI findings and implement accepted fixes. Use when local reviews, PR feedback, or checks need triage, repair, and explicit dispositions.

3 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

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Only Must-fix and Worth-fixing are accepted.

    line 20
  2. Distinctive:

    Repair and check: Use the working selection from agent routing.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 3 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 Sweep

Turn supplied findings into verified decisions and fixes. The caller owns input fetching, commits, publication, remote replies/resolution, and later review rounds.

  1. Account for input. Normalize every item with the finding schema. Preserve each source and ID, including model/assignment provenance. Merge duplicates without losing their sources; separate source noise and incomplete-review coverage gaps.
  2. Verify each claim. Inspect the actual location, owner, consumers, contracts, requirements, and relevant checks. Use verify when a real workflow resolves a dispute. Finish when every claim has evidence and a state: true, pre-existing, handled, contradicted, duplicate, or unjustified churn.
  3. Decide. Apply classification once per item. Only Must-fix and Worth-fixing are accepted. Record reasons for rejection, acknowledgment, or deferral, including the parent decision a deferral needs.
  4. Repair and check. Use the working selection from agent routing. Preserve intended behavior within the authorized scope; a changed product decision belongs to the parent. Run checks affected by accepted fixes, including relevant React Doctor diagnostics. Reuse proof while it remains valid. Missing implementation acceptance proof is itself a finding to resolve.

Finish when every input has a disposition and each accepted fix passes its checks, or report the precise blocker. Reopen settled findings only with new evidence. Return the grouped report: findings, fixes, checks, rejected/deferred reasons, coverage gaps, and remaining owners.

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.