review-diff
Skill1 starsChanged 3 months agoMITView on GitHub
Review the most recent diff for correctness, security, and performance. Use when the user asks for a review of what just changed — "review this", "review the last diff", "check my changes", "look over what you just wrote", "anything wrong with this?", "does this look right", "sanity check this", "did I break anything", "go over the diff", "spot anything", "second pass on this", "any bugs here", "is this safe". Use it for any request to inspect recent work rather than change it.
20 other projects use a version of this.
Adopted by
Most recently taken up by
- giacomo-ciro/skillstheir own version, first seen Nov 14, 2026
- anorth/agent-skillstheir own version, first seen Nov 11, 2026
- jisuzzzz/haechitheir own version, first seen Nov 8, 2026
- Hy0sh/claude-skillstheir own version, first seen Nov 3, 2026
- tounsils/claude-code-skillstheir own version, first seen Oct 25, 2026
- nesnilnehc/ai-cortextheir own version, first seen Oct 25, 2026
Used with
Projects with it also use grilling.
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.
GoogleSkillgrilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Also in 3 projects that use this
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- faizkhairi/claude-code-blueprint★ 73same name
- huytd/skills★ 19same name
- bbvch-ai/aihub-core★ 17same name
- jisuzzzz/haechi★ 17same name
- nesnilnehc/ai-cortex★ 8same name
- tardigrde/agent-skill-eval★ 4same name
- Hy0sh/claude-skills★ 2same name
- Pradnyeshp/Claude-Skills★ 2same name
- anorth/agent-skills★ 1same name
- erikediner/skills★ 1same name
10 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- build-newSkill
- debug-failureSkill
- explain-codeSkill
- plan-approachSkill
- update-featureSkill
- write-testsSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 20 edited versions we read keep these.
1
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
- Distinctive: line 13
Default to the uncommitted working tree (git diff), plus staged changes (git diff --staged).
“Common” is measured: kept by at least 6 in 10 of the 20 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.
Files
Review the last diff
Review the last diff for correctness, security, and performance.
Scope
Default to the uncommitted working tree (git diff), plus staged changes
(git diff --staged). If the working tree is clean, review the last commit
(git show HEAD). If $ARGUMENTS names a different range, branch, or path, review that
instead.
What to look for
Correctness — off-by-one and boundary errors, unhandled nil/null/undefined, error paths that swallow failures, race conditions, changed behaviour the existing tests do not cover.
Security — untrusted input reaching a query, path, shell, or deserializer; secrets or tokens in source or logs; authz checks that were moved or dropped; new dependencies pulled in for something trivial.
Performance — work inside a loop that belongs outside it, N+1 queries, an accidental O(n²), unbounded reads of data that could be large.
Rules
- Review only what the diff touches. Pre-existing problems in surrounding code are out of scope unless the diff makes them reachable.
- For each finding, give the concrete failure: specific input or state → wrong output or crash. A finding you cannot make concrete is a guess — label it as one or drop it.
- Cite
file:lineso each finding is clickable. - Order findings most severe first. If the diff is clean, say so plainly instead of manufacturing nits.
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.

