agentleFS
Sign inStart free
thrillmadethrillmade/agent-skills/skills/evidence-based-review/SKILL.md

evidence-based-review

Skill3 starsChanged 9 days agoMITView on GitHub

Every PR review claim must quote the specific code being criticized. No hand-waving.

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:

    Every claim in your review must be backed by evidence the PR author can verify in seconds.

    line 11
  2. Distinctive:

    Before posting a comment, ask: if the author asked "show me", could I point at the exact line and exact failure case?

    line 30

≈ “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

Evidence-based review

Every claim in your review must be backed by evidence the PR author can verify in seconds.

Required for every finding

  • Quote the exact line or block you're talking about (use a fenced code block or gh pr inline-comment anchor).
  • Cite the file and line range so the author can navigate directly there.
  • State the failure mode concretely: what input produces what wrong output, or what attacker action exploits what gap.

Banned phrasings

These are red flags that you're hand-waving instead of reviewing:

  • "This might cause issues" → say which issue, with the input that triggers it.
  • "Consider refactoring this" → either it has a bug, or it doesn't. Not your call to redesign their code.
  • "This doesn't follow best practices" → cite which practice and why it matters here.
  • "You should add tests" → name the specific code path that isn't covered.

Verifying your own claims

Before posting a comment, ask: if the author asked "show me", could I point at the exact line and exact failure case? If not, delete the comment.

A short, specific review of three real issues beats a long, vague review of fifteen maybes.

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