agentleFS
Sign inStart free
thrillmadethrillmade/agent-skills/skills/critical-issues-only/SKILL.md

critical-issues-only

Skill3 starsChanged 8 days agoMITView on GitHub

PR review discipline - flag only correctness, security, and performance issues. Skip nits.

2 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    When reviewing a pull request, only surface issues that fall into one of these buckets:

    line 11
  2. Distinctive:

    If the diff has no issues in the four buckets above, post a single short comment confirming that — don't invent problems.

    line 31

≈ “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

Critical issues only

When reviewing a pull request, only surface issues that fall into one of these buckets:

  1. Correctness bugs — the code does the wrong thing, mishandles a case, or breaks an existing contract.
  2. Security vulnerabilities — injection, auth bypass, secret exposure, unsafe deserialization, SSRF, etc.
  3. Performance problems — algorithmic blowups, N+1 queries, memory leaks, blocking calls in hot paths.
  4. Missing or broken test coverage for new code paths that meaningfully change behavior.

Do not surface

  • Style preferences, formatting, naming preferences.
  • Architectural rewrites unless the existing approach is actively broken.
  • "You could also..." suggestions that aren't bugs.
  • Nitpicks the author can fix in 30 seconds and don't change behavior.

How to phrase findings

  • One concrete issue per comment. No bundling unrelated nits.
  • Quote the specific line or block being criticized.
  • Say what's wrong, then what to do about it. Skip the throat-clearing.

If the diff has no issues in the four buckets above, post a single short comment confirming that — don't invent problems.

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