agentleFS
ci4meci4me/CQRSTemplate/.claude/skills/code-review/SKILL.md

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

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.
  • dzhngSkill

    close-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

  • dzhngSkill

    design-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

  • PydanticSkill

    add-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-bullshitSkill

    compare-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 AzureSkill

    azsdk-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 AzureSkill

    azsdk-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

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
  1. Distinctive:

    Create violation report organized by:

    line 69
  2. Distinctive:

    Add to CI/CD pipeline:

    line 266

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Code Review Skill

Comprehensive multi-specialist code review workflow.


Step 1: Identify Scope

Ask user:

  1. Review entire codebase or specific domain?
  2. Focus areas (quality, performance, security, tests)?
  3. 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-text

Create 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, aggregates
  • cqrs-specialist → Review commands, queries, events, handlers
  • php-specialist → Review PHP 8.3+ usage, types, modern features
  • clean-code-specialist → Review method length, complexity, DRY
  • phpstan-specialist → Review type safety, annotations
  • test-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:

  1. Critical Issues (breaks, security, data loss)
  2. High Priority (quality violations, missing tests)
  3. Medium Priority (style issues, minor optimizations)
  4. 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:

  1. Identify responsible specialist
  2. Determine fix complexity (simple, moderate, complex)
  3. Estimate impact (low, medium, high)
  4. 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:

  1. Show violation:
    // ❌ Current code (violation)
  2. Show fix:
    // ✅ Corrected code
  3. 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-text

Quality 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 fails

Use this skill for pull request reviews and periodic code quality audits.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.