review
Skill1 starsChanged 5 months agoApache-2.0View on GitHub
Multi-agent parallel code review against the base branch
192 other projects use a version of this.
Adopted by
Most recently taken up by
- dzhng/skillstheir own version, first seen Nov 15, 2026
- muxy-app/muxytheir own version, first seen Nov 15, 2026
- macro-inc/macrotheir own version, first seen Nov 15, 2026
- yagizdo/quivertheir own version, first seen Nov 15, 2026
- markmhendrickson/neotomatheir own version, first seen Nov 15, 2026
- felipeam86/pipe-skillstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use close-spec, daily-arxiv 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
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
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
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
- +5 more from Lambenthan
- +3 more from dzhng
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★ 142ksame name
- ansible/ansible★ 71ksame name
- docling-project/docling★ 71ksame name
- traefik/traefik★ 66ksame name
- ClickHouse/ClickHouse★ 51ksame name
- temporalio/temporal★ 24ksame name
- ccch1mneyyy/dsh-Go★ 24ksame name
- tisfeng/Easydict★ 15ksame name
- juicedata/juicefs★ 15ksame name
- elie222/inbox-zero★ 13ksame 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.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- auditSkill
- decomposeSkill
- dev-allSkill
- dev-investigateSkill
- devSkill
- digSkill
- investigateSkill
- prSkill
- tech-debtSkill
- update-docsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 156 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
Run each command individually — do NOT chain with &&
- Very specific: line 73
Check .claude/agents/ for project-specific reviewer agents (e.g., kmp-reviewer, ui-reviewer).
- Distinctive: line 78
Deduplicate: remove findings reported by multiple agents
“Common” is measured: kept by at least 6 in 10 of the 156 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 — Multi-Agent Code Review
Review the current branch's changes against the base branch using parallel review agents.
Step 0: Prepare
- Identify base branch (
mainormaster) and current branch git log— commits on this branchgit diff {base}...HEAD— full changesetgh pr view --json body— PR description (if available)- Run each command individually — do NOT chain with
&&
Step 1: Build Change Context
- Understand the intent from commit messages and PR description
- Categorize changed files: core logic, UI, infrastructure, tests
- Identify risk areas: complex changes, new integrations, security-sensitive code
Step 2: Multi-Agent Parallel Review
Launch two review agents in parallel (model: sonnet):
Agent A: Bug & Logic + Security
Review the changed files for bugs, logic errors, and security issues.
Read REVIEW.md (if exists) or .claude/rules/ for review criteria.
Focus areas:
- Null safety violations
- Concurrency issues
- Error handling gaps
- Security: hardcoded secrets, input sanitization, data exposure
- Platform compatibility
- Performance: memory leaks, main thread blocking, redundant calls
For each finding: [file:line] severity — description
Severity: Critical / Warning / Suggestion / NitAgent B: Architecture & Quality
Review the changed files for architecture and code quality.
Read REVIEW.md (if exists) or .claude/rules/ for review criteria.
Focus areas:
- Architecture: SRP, layer boundaries, dependency direction
- Design patterns: consistency with existing codebase
- Testing: changed code has corresponding test updates
- Naming and readability
- Unnecessary complexity or over-engineering
For each finding: [file:line] severity — description
Severity: Critical / Warning / Suggestion / NitProject-Specific Reviewers (if available)
Check .claude/agents/ for project-specific reviewer agents (e.g., kmp-reviewer, ui-reviewer). If found, launch them in parallel with Agents A and B.
Step 3: Merge Findings
- Collect findings from all agents
- Deduplicate: remove findings reported by multiple agents
- Assign final severity:
- Critical: crash, data loss, security vulnerability, incorrect behavior
- Warning: potential bug, performance issue, architecture violation
- Suggestion: improvement opportunity, non-blocking
- Nit: style/preference, optional
Step 4: Present Report
## Review Summary
**Branch:** {current} → {base}
**Files changed:** N
**Risk level:** Low / Medium / High
**Reviewed by:** Agent A (Bug/Security) + Agent B (Arch/Quality) + {project-specific}
### Critical (must fix)
- [file:line] description
### Warning (should fix)
- [file:line] description
### Suggestion (nice to have)
- [file:line] description
### Nit (optional)
- [file:line] descriptionDoes 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.

