zen-review
Skill1 starsChanged 27 days agoNo licenceView on GitHub
Review a change for correctness (does it work, and is what it says true) and for shape (is this the smallest system that does the job), then fix what it finds and have a fresh verifier check every fix. Use for review, code review, review my changes, hunt bugs, prove it with tests, check it holds at real data volumes, check it does what the spec asks, simplify, cleanup, boyscout, or challenge what an API or tool surface offers. Works mid-implementation, before a PR, on a branch, on a PR, or on code with no diff at all. Fixes by default unless you say "report only" or "review only". Light mode (one finder for all applicable correctness angles, one for all applicable shape angles) unless you say "full" or "full mode": then one finder per angle. Not for UI layout or visual design, though frontend code is in scope.
In this repository26 other files it gives its agents.
- agent-browserSkill
- brainstormingSkill
- broSkill
- clean-roomSkill
- copywritingSkill
- cut-stateSkill
- designingSkill
- design-knowledgeSkill
- design-reviewSkill
- distillSkill
- factsSkill
- grillingSkill
- interface-craftSkill
- marketing-psychologySkill
- planningSkill
- positioningSkill
- principlesSkill
- product-designSkill
- product-marketing-contextSkill
- readableSkill
- readbackSkill
- sharpenSkill
- show-meSkill
- stop-slopSkill
- thebarSkill
- writing-clearly-and-conciselySkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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
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.