Requesting Code Review
About
This skill dispatches a code-reviewer subagent to analyze implementations against plans or requirements before proceeding. It should be used after completing tasks, implementing major features, or before merging to verify work meets specifications. The review process helps catch issues early and includes templates, examples, and severity guidelines.
Quick Install
Claude Code
Recommended/plugin add https://github.com/bobmatnyc/claude-mpmgit clone https://github.com/bobmatnyc/claude-mpm.git ~/.claude/skills/Requesting Code ReviewCopy and paste this command in Claude Code to install this skill
Documentation
Requesting Code Review
Dispatch code-reviewer subagent to catch issues before they cascade.
Core principle: Review early, review often.
When to Request Review
Mandatory:
- After each task in subagent-driven development
- After completing major feature
- Before merge to main
Optional but valuable:
- When stuck (fresh perspective)
- Before refactoring (baseline check)
- After fixing complex bug
Quick Start
1. Get git SHAs:
BASE_SHA=$(git rev-parse HEAD~1) # or origin/main
HEAD_SHA=$(git rev-parse HEAD)
2. Dispatch code-reviewer subagent:
Use Task tool with code-reviewer type, fill template at Code Reviewer Template
Required placeholders:
{WHAT_WAS_IMPLEMENTED}- What you just built{PLAN_OR_REQUIREMENTS}- What it should do{BASE_SHA}- Starting commit{HEAD_SHA}- Ending commit{DESCRIPTION}- Brief summary
3. Act on feedback:
| Severity | Action |
|---|---|
| Critical | Fix immediately, don't proceed |
| Important | Fix before next major task |
| Minor | Note for later, can proceed |
See severity guidelines for details.
Integration with Workflows
Subagent-Driven Development:
- Review after EACH task
- Catch issues before they compound
- Fix before moving to next task
Executing Plans:
- Review after each batch (3 tasks)
- Get feedback, apply, continue
Ad-Hoc Development:
- Review before merge
- Review when stuck
Pushing Back on Reviews
If reviewer wrong:
- Push back with technical reasoning
- Show code/tests that prove it works
- Reference plan requirements
- Request clarification
Common Mistakes
Never:
- Skip review because "it's simple"
- Ignore Critical issues
- Proceed with unfixed Important issues
- Argue without technical justification
Always:
- Provide full context in review request
- Fix Critical issues immediately
- Document why you disagree (if you do)
- Re-review after fixing Critical issues
Examples
Need examples? See Review Examples & Workflows for:
- Complete review output examples
- Good vs bad review requests
- Review workflows for different scenarios
- How to act on different severity levels
- When and how to push back
Need template? See Code Reviewer Template for the complete subagent dispatch template.
GitHub Repository
Related Skills
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
evaluating-llms-harness
TestingThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
content-collections
MetaThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
llamaguard
OtherLlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.