code-review
Skill0 starsChanged 6 months agoMITView on GitHub
Performs comprehensive code review using all specialized agents in parallel, generating detailed violation report with fixes. Use when user requests code review, audit code quality, check quality standards, review changes, find violations, review pull requests, or wants parallel specialist execution.
194 other projects use a version of this.
Adopted by
Most recently taken up by
- doggy8088/spec-kittheir own version, first seen Nov 9, 2026
- strelov1/freehiretheir own version, first seen Nov 9, 2026
- storybookjs/storybooktheir own version, first seen Nov 8, 2026
- codewithmukesh/dotnet-claude-kittheir own version, first seen Nov 8, 2026
- supabase/supabasetheir own version, first seen Nov 8, 2026
- The-Vibe-Company/quivrtheir 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
PydanticSkilladd-new-model
Add support for a newly-released language or image generation model in pydantic-ai (e.g. openai:gpt-5.6, anthropic:claude-sonnet-5, openai:gpt-image-2). Use when a provider ships a new model id and you need to wire literals, profile flags, adapters, and tests to recognize it. Handles SDK-lag, gateway list conventions, capability probing, and direct image-model geometry.
Also in 9 projects that use this
transitive-bullshitSkillcompare-screenshots
Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.
Also in 5 projects that use this
Microsoft AzureSkillazsdk-common-apiview-feedback-resolution
Analyze and resolve APIView review feedback on Azure SDK PRs. **UTILITY SKILL**. USE FOR: APIView comments, API review feedback, SDK API surface changes. DO NOT USE FOR: general code review, non-APIView feedback. INVOKES: azure-sdk-mcp:azsdk_apiview_get_comments, azure-sdk-mcp:azsdk_customized_code_update, azure-sdk-mcp:azsdk_typespec_delegate_apiview_feedback, azure-sdk-mcp:azsdk_run_typespec_validation, azure-sdk-mcp:azsdk_package_generate_code.
Also in 6 projects that use this
Microsoft AzureSkillazsdk-common-generate-sdk-locally
Generate and finalize Azure SDKs locally from TypeSpec, including build, checks, tests, changelog, metadata, and version updates by default. WHEN: "generate SDK locally", "build SDK", "run SDK tests", "run CI checks", "validate package", "run checks", "update changelog", "fix SDK build errors", "resolve SDK generation errors", "customize TypeSpec", "rename SDK client", "rename SDK model", "hide operation from SDK", "fix analyzer errors", "resolve customization drift", "create subclient", "update metadata", "update version". INVOKES: azsdk_verify_setup, azsdk_package_generate_code, azsdk_package_build_code, azsdk_package_run_check, azsdk_package_run_tests, azsdk_customized_code_update, azsdk_package_update_changelog_content, azsdk_package_update_metadata, azsdk_package_update_version.
Also in 6 projects that use this
- +4 more from dzhng
- +2 more from Azure
Other versions194 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 194
- mattpocock/skills★ 309ksame name
- TheAlgorithms/Python★ 226ksame name
- microsoft/vscode★ 195ksame name
- github/spec-kit★ 149ksame name
- ggml-org/llama.cpp★ 134ksame name
- supabase/supabase★ 115ksame name
- storybookjs/storybook★ 91ksame name
- shareAI-lab/analysis_claude_code★ 80ksame name
- shareAI-lab/learn-claude-code★ 80ksame name
- vectorize-io/hindsight★ 60ksame name
184 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 repository14 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- api-endpoint-creationSkill
- database-migrationsSkill
- local-dev-testingSkill
- testing-cqrs-securitySkill
- business-rule-additionSkill
- chrome-devtools-expertSkill
- context7-docsSkill
- domain-scaffoldingSkill
- markitdown-converterSkill
- playwright-automationSkill
- property-additionSkill
- serena-code-generatorSkill
- strategic-plannerSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 184 edited versions we read keep these.
2
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 69
Create violation report organized by:
- Distinctive: line 266
Add to CI/CD pipeline:
“Common” is measured: kept by at least 6 in 10 of the 184 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 Skill
Comprehensive multi-specialist code review workflow.
Step 1: Identify Scope
Ask user:
- Review entire codebase or specific domain?
- Focus areas (quality, performance, security, tests)?
- Priority (critical violations only or all issues)?
Default: Review specified domain or changed files.
Step 2: Initial Analysis
Gather context:
# Find PHP files
Glob: app/Domain/{Domain}/**/*.php
# Check current quality status
vendor/bin/phpstan analyse app/Domain/{Domain}
vendor/bin/phpcs app/Domain/{Domain}
vendor/bin/phpunit tests/Unit/Domain/{Domain} --coverage-textCreate baseline: Note current errors/violations/coverage.
Step 3: Parallel Specialist Review
Invoke ALL specialists in PARALLEL:
Domain Layer Review
ddd-specialist→ Review entities, value objects, aggregatescqrs-specialist→ Review commands, queries, events, handlersphp-specialist→ Review PHP 8.3+ usage, types, modern featuresclean-code-specialist→ Review method length, complexity, DRYphpstan-specialist→ Review type safety, annotationstest-specialist→ Review test coverage, test quality
Infrastructure Layer Review
codeigniter4-specialist→ Review models, migrations, controllers
Code Standards Review
slevomat-specialist→ Review coding standards compliance
Each specialist provides:
- List of violations found
- Severity (critical, high, medium, low)
- Specific file locations
- Recommended fixes
Step 4: Consolidate Findings
Create violation report organized by:
- Critical Issues (breaks, security, data loss)
- High Priority (quality violations, missing tests)
- Medium Priority (style issues, minor optimizations)
- Low Priority (suggestions, nice-to-haves)
Format:
## Critical Issues (MUST FIX)
### DDD Specialist
- [ ] app/Domain/Cookie/Entities/Cookie.php:45 - Anemic domain model
- Issue: Public setter bypasses business rules
- Fix: Change to command method: updatePrice(CookiePrice $newPrice)
### PHPStan Specialist
- [ ] app/Infrastructure/Persistence/Repositories/CookieRepository.php:78 - Type safety violation
- Issue: Mixed type returned from database
- Fix: Add array shape annotation
## High Priority (SHOULD FIX)
### Clean Code Specialist
- [ ] app/Controllers/Domain/Cookie/CookieController.php:25 - Method too long
- Issue: store() method has 35 lines
- Fix: Extract to private methods
...Step 5: Generate Fix Plan
For each violation:
- Identify responsible specialist
- Determine fix complexity (simple, moderate, complex)
- Estimate impact (low, medium, high)
- Suggest fix approach
Prioritize:
- Critical: Fix immediately
- High: Fix before merge
- Medium: Fix in next sprint
- Low: Tech debt backlog
Step 6: Auto-Fix Where Possible
Automatically fix:
# Auto-fix coding standards
vendor/bin/phpcbf app/Domain/{Domain}
# Re-check
vendor/bin/phpcs app/Domain/{Domain}Report: "Auto-fixed X violations, Y remain manual."
Step 7: Manual Fix Guidance
For each manual fix needed:
- Show violation:
// ❌ Current code (violation) - Show fix:
// ✅ Corrected code - Explain why:
- What pattern/rule is violated
- Why it matters
- What the fix achieves
Step 8: Validation After Fixes
After fixes applied:
vendor/bin/phpstan analyse --level=8
vendor/bin/phpcs
vendor/bin/phpunit --coverage-textQuality gates:
- PHPStan: 0 errors
- Slevomat: 0 violations
- Tests: 90%+ coverage, all passing
Step 9: Generate Summary Report
Final report includes:
# Code Review Summary
## Scope
- Domain: {Domain}
- Files Reviewed: {count}
- Specialists Involved: {list}
## Findings
- Critical Issues: {count} (ALL FIXED)
- High Priority: {count} ({fixed} fixed, {remaining} remaining)
- Medium Priority: {count}
- Low Priority: {count}
## Quality Metrics
### Before Review
- PHPStan Errors: {count}
- Slevomat Violations: {count}
- Test Coverage: {percentage}%
### After Review
- PHPStan Errors: 0 ✅
- Slevomat Violations: 0 ✅
- Test Coverage: {percentage}% ✅
## Specialist Recommendations
### DDD Specialist
{Key findings and suggestions}
### CQRS Specialist
{Key findings and suggestions}
### Clean Code Specialist
{Key findings and suggestions}
...
## Action Items
- [ ] {Remaining high-priority fix}
- [ ] {Remaining medium-priority fix}
## Approval Status
{APPROVED / CHANGES REQUESTED / BLOCKED}Review Checklist
Domain Layer:
- Value objects are immutable and self-validating
- Entities use factory methods (create/reconstitute)
- Business logic in domain, not controllers
- Ubiquitous language used
- Invariants protected
CQRS Layer:
- Commands are immutable readonly DTOs
- Queries are immutable readonly DTOs
- Events are past tense, immutable
- One handler per command/query
- Handlers delegate to entities
- Events dispatched after state changes
Code Quality:
- All methods <= 20 lines
- No else after return
- Early returns used
- No duplicate code (DRY)
- Magic numbers extracted to constants
Type Safety:
- declare(strict_types=1) in all files
- All parameters typed
- All return types declared
- Array shapes documented
- === used for comparisons
Tests:
- All value objects tested
- All entities tested
- All handlers tested (with mocks)
- Repository tested (with database)
- Controller tested (feature tests)
- 90%+ coverage maintained
Integration with CI/CD
Add to CI/CD pipeline:
code-review:
script:
- composer check # Runs PHPStan + Slevomat + PHPUnit
allow_failure: false # Block merge if failsUse this skill for pull request reviews and periodic code quality audits.
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.

