review
Skill2 starsChanged 3 months agoMITView on GitHub
Review code changes for flaws, bugs, security issues, and potential problems
192 other projects use a version of this.
Adopted by
Most recently taken up by
- microsoft/veronatheir own version, first seen Nov 8, 2026
- microsoft/FluidFrameworktheir own version, first seen Nov 8, 2026
- charliee1w/consolidation-memorytheir own version, first seen Nov 8, 2026
- jisuzzzz/haechitheir own version, first seen Nov 8, 2026
- apokamo/kajitheir own version, first seen Nov 8, 2026
- dirien/yet-another-agent-harnesstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use close-spec, design-with-images and 10 more.
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.
dzhngSkillclose-spec
When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).
Also in 5 projects that use this
dzhngSkilldesign-with-images
Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.
Also in 5 projects that use this
LambenthanSkilldaily-arxiv
每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新
Also in 5 projects that use this
LambenthanSkillexp-eval
实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
Also in 5 projects that use this
- +3 more from dzhng
- +5 more from Lambenthan
Other versions192 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 192
- garrytan/gstack★ 141ksame name
- ansible/ansible★ 71ksame name
- docling-project/docling★ 70ksame name
- traefik/traefik★ 65ksame name
- ClickHouse/ClickHouse★ 51ksame name
- temporalio/temporal★ 24ksame name
- tisfeng/Easydict★ 15ksame name
- juicedata/juicefs★ 15ksame name
- elie222/inbox-zero★ 13ksame name
- gitkraken/vscode-gitlens★ 10ksame name
182 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 repository12 other files it gives its agents.
- battle-testSkill
- choicesSkill
- commitSkill
- frontend-verifySkill
- init-agentsSkill
- loopableSkill
- loopitSkill
- review-deepSkill
- security-auditSkill
- sessionsSkill
- thermo-nuclear-code-quality-reviewSkill
- vulgarizeSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 157 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
If $ARGUMENTS contains "staged": only git diff --cached
- Very specific: line 15
If $ARGUMENTS contains "unstaged": only git diff
- Very specific: line 16
If $ARGUMENTS contains "last-commit": git rev-parse HEAD~1 >/dev/null 2>&1 && git diff HEAD~1 || git diff $(git hash-object -t tree …
- Distinctive: line 27
Do loops and iterations behave correctly?
- Distinctive: line 45
Do error paths leave the app in a consistent state?
- Distinctive: line 55
Read CLAUDE.md (if it exists) for project-specific constraints and verify changes don't violate them.
- Distinctive: line 82
If no issues are found, say so clearly.
“Common” is measured: kept by at least 6 in 10 of the 157 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
Code Review
Perform a thorough code review of the current changes. Act as a senior developer reviewing a pull request.
Steps
- Gather changes based on scope:
- If
$ARGUMENTScontains "staged": onlygit diff --cached - If
$ARGUMENTScontains "unstaged": onlygit diff - If
$ARGUMENTScontains "last-commit":git rev-parse HEAD~1 >/dev/null 2>&1 && git diff HEAD~1 || git diff $(git hash-object -t tree /dev/null)(falls back to the empty tree on a repo's first commit) - Otherwise: both
git diffandgit diff --cached(all pending changes) - Also run
git statusfor context
- If
- Read full files: For every file that has changes, read the COMPLETE file (not just the diff) to understand the full context around the modifications.
- Analyze each change against this checklist:
Logic & Correctness
- Are there logic errors, off-by-one mistakes, or wrong conditions?
- Are edge cases handled (null, undefined, empty arrays, missing fields)?
- Do loops and iterations behave correctly?
- Are return values used correctly?
Security
- Any injection risks (SQL, command, XSS)?
- Is user input validated and sanitized?
- Are there exposed secrets or credentials?
- Are auth checks present where needed?
Data & State
- Are data operations correct (correct methods, field names, query parameters)?
- Is state managed correctly (component state, query cache)?
- Are race conditions possible?
- Is data transformed correctly between layers?
Error Handling
- Are async operations properly awaited?
- Are errors caught where they should be?
- Do error paths leave the app in a consistent state?
- Are failures observable - is the error logged with enough context (ids, operation), and do logs avoid leaking secrets/PII?
Performance
- Any unnecessary re-renders or re-fetches?
- N+1 query problems?
- Large data sets loaded without pagination?
- Missing memoization for expensive computations?
Project Constraints
- Read CLAUDE.md (if it exists) for project-specific constraints and verify changes don't violate them.
Breaking Changes
- Could this change break existing functionality?
- Are API contracts preserved?
- Are backwards-incompatible changes flagged?
- Produce the review report in the following format:
Output Format
For each issue found, report:
[SEVERITY] Category — File:line Description of the issue and why it matters. Suggested fix (if applicable).
Severity levels:
- CRITICAL: Bugs, security holes, data corruption risks — must fix before shipping
- WARNING: Potential problems, edge cases, code smells — should fix
- INFO: Minor suggestions, style issues, improvements — nice to have
At the end, provide a Summary with:
- Total issues by severity
- Overall assessment (safe to ship / needs fixes / needs major rework)
- The single most important thing to address
If no issues are found, say so clearly.
$ARGUMENTS
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.

