diff-review
Skill0 starsChanged 46 days agoMITView on GitHub
Use after any code change, before committing. Reviews the working diff for correctness, security (injection, secret and data leaks, auth gaps), and performance (N+1 queries, unbounded fetches).
19 other projects use a version of this.
Adopted by
Most recently taken up by
- moisesrj97/skillstheir own version, first seen Nov 8, 2026
- pranataa-labs/Workflow-Mastertheir own version, first seen Nov 8, 2026
- MidnightDarling/collatetheir own version, first seen Nov 1, 2026
- Hakkadaikon/hymmetheir own version, first seen Oct 26, 2026
- scottlivingston/claude-skillstheir own version, first seen Oct 25, 2026
- rosslevinsky/portable-agent-skillstheir own version, first seen Oct 15, 2026
Used with
Projects with it also use test-design.
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.
shabarabaSkilltest-design
Automatically design comprehensive E2E test cases for newly implemented vibing.nvim features. Use immediately after completing feature implementation (Phase 5.4) and before running E2E tests. Generates test scenarios covering Happy paths, Error cases, Edge cases, and Integration points with priority ranking (Critical/High/Medium/Low) and ready-to-use test code templates using e2e_helper.lua.
Also in 3 projects that use this
Other versions19 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 19
- ClickHouse/ClickHouse★ 51ksame name
- ComplyEaze/bridge★ 35same name
- lamemustafa/bridge★ 35same name
- rosslevinsky/portable-agent-skills★ 12same name
- yasunori0418/skills★ 9same name
- MidnightDarling/collate★ 8same name
- dprakash2101/dotnet-production-agent-skills★ 4same name
- Lixiuxiu559/AgentForge★ 4same name
- declancowen/skills★ 2same name
- pranataa-labs/Workflow-Master★ 2same name
9 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 repository9 other files it gives its agents.
- brainstormingSkill
- commit-messageSkill
- dev-verifySkill
- env-doctorSkill
- fix-bugSkill
- git-workflowSkill
- refactorSkill
- ship-featureSkill
- workSkill
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 10 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 10
Run this against every diff before committing.
“Common” is measured: kept by at least 6 in 10 of the 10 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
Diff review
Run this against every diff before committing.
git diff --staged # or: git diffSecurity
Work through ${CLAUDE_PLUGIN_ROOT}/conventions/security.md — the full
checklist lives there so it can't drift between this skill and the
code-quality-reviewer agent. Headline items:
- Injection: SQL, HTML/XSS, command, path traversal
- Secrets or PII in logs, error messages, client bundles, or committed files
- Auth: new routes have the access control they should, and verify identity server-side rather than trusting a client-supplied id
Correctness
- Logic errors, off-by-one, unhandled edge cases
- Error paths: empty input, null, network failure
- Does this break callers elsewhere? Grep for usages before deciding it doesn't.
Performance
- N+1 queries; redundant loops or recomputation; needless re-renders
- Unbounded fetches — missing pagination or limits
- Memoization only where clearly warranted; don't over-apply
Scope
- Files changed that shouldn't have been
- New dependencies — flag every one, with what it's for
- Debug leftovers: stray logging, commented-out code, hardcoded test values
Reporting
- Flag issues with
file:line. - If nothing is found, say so explicitly — silence reads as "not checked".
- Call out security issues even when you also fix them. A silent patch means the user never learns the pattern was there.
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.

