claude-code-skills / rules
Cursor rule1 starsChanged 11 days agoMITView on GitHub
Review uncommitted or branch-local changes for defects, ranked by severity, with a concrete failure scenario behind every finding. Use when asked to review code, review a diff, review my changes, check this before I commit, look over this branch, or do a pre-PR pass. Reviews the change, not the whole repository.
We split this review-diff.mdc into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Read @skills/review-diff/SKILL.md in full before starting, then follow it.
≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule 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.
Files
--- description: Review uncommitted or branch-local changes for defects, ranked by severity, with a concrete failure scenario behind every finding. Use when asked to review code, review a diff, review my changes, check this before I commit, look over this branch, or do a pre-PR pass. Reviews the change, not the whole repository. globs: alwaysApply: false --- <!-- Generated by scripts/generate-harnesses.mjs from skills/. Do not edit by hand. --> Read @skills/review-diff/SKILL.md in full before starting, then follow it. It is the procedure for this task rather than a summary, and the steps most often skipped are the ones that make the result trustworthy. Report what you did not do, and report test pass, fail, and skip counts.
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 3,978 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/audit-security.mdcCursor rule
- .cursor/rules/bump-deps.mdcCursor rule
- .cursor/rules/onboard-repo.mdcCursor rule
- .cursor/rules/perf-hunt.mdcCursor rule
- .cursor/rules/restructure.mdcCursor rule
- .cursor/rules/root-cause.mdcCursor rule
- .cursor/rules/ship-pr.mdcCursor rule
- .cursor/rules/test-gaps.mdcCursor rule
- .cursor/rules/triage-ci.mdcCursor rule
- audit-securitySkill
- bump-depsSkill
- onboard-repoSkill
- perf-huntSkill
- restructureSkill
- review-diffSkill
- root-causeSkill
- ship-prSkill
- test-gapsSkill
- triage-ciSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

