agentleFS
Sign inStart free
SemanticMatterSemanticMatter/autonomous-development/skills/fix-findings/SKILL.md

fix-findings

Skill3 starsChanged 49 days agoMITView on GitHub

Triage the latest Codex review findings, fix evidence-backed issues, add regression tests, rerun verification, and prepare the implementation for a fresh independent review.

8 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use handoff.

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.
  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 3

    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:

    Add a regression test for every correctness, security, compatibility, or reliability defect when practical.

    line 25
  2. Distinctive:

    Do not automatically implement low-confidence stylistic suggestions.

    line 27
  3. Distinctive:

    Do not exceed the configured review-round budget.

    line 28

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

Triage and fix review findings

  1. Locate the latest review file and any prior triage files. Use controller.py status --json to find reviews[-1].path (resolved relative to the run directory), or run controller.py show-run to inspect the full run state. If an adversarial review ran, its threats are also in the cumulative ledger (T-<n> ids, alongside review findings' F-<n> ids) — triage's finding_id field accepts either.
  2. Classify every finding (and adversarial threat) as one of:
    • accepted;
    • rejected_with_evidence;
    • already_resolved;
    • out_of_scope_but_recorded;
    • requires_human_decision.
  3. Record the classification and repository evidence in triage-NN.md under the run directory.
  4. Fix accepted findings with the smallest coherent change.
  5. Add a regression test for every correctness, security, compatibility, or reliability defect when practical.
  6. Rerun all affected verification checks using the controller.
  7. Do not automatically implement low-confidence stylistic suggestions.
  8. Do not exceed the configured review-round budget; mark the run blocked when a safe resolution requires external product or operational authority.

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