code-review
Coordinates specialist agent personas to perform comprehensive code reviews, focusing on architecture, security, and performance.
Install
mkdir -p .claude/skills/code-review-noodlemind && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15921" && unzip -o skill.zip -d .claude/skills/code-review-noodlemind && rm skill.zipInstalls to .claude/skills/code-review-noodlemind
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Multi-agent code review with confidence-scored findings, persona synthesis, and action routing. Use when reviewing PRs, changes, or branches. Not for single-domain review — delegate to the specialist directly.Key capabilities
- →Coordinate multiple specialist personas for code review
- →Merge and deduplicate findings based on severity and confidence
- →Route findings by action type
- →Determine review scope from pull requests, current changes, specific files, or branch comparisons
- →Select personas and checks based on diff content and project type
- →Synthesize findings into a structured report with a verdict
How it works
The skill coordinates multiple specialist personas and checks, dispatches them with review context, and then synthesizes their structured findings into a single report.
Inputs & outputs
When to use code-review
- →Reviewing pull requests
- →Analyzing code changes
- →Auditing code quality
- →Verifying branch readiness
About code-review
Uses a pipeline to analyze code changes from multiple perspectives. Merges and deduplicates findings based on severity and confidence.
Multi-agent code review with confidence-scored findings, persona synthesis, and action routing. Use when reviewing PRs, changes, or branches. Not for single-domain review — delegate to the specialist directly.
When not to use it
- →Reviewing for security issues only
- →Checking if Java code is idiomatic
- →Reviewing a plan document
Limitations
- →Does not perform single-domain reviews; delegates to specialists directly for those cases
- →Requires a plan file with YAML frontmatter for pipeline mode validation
- →Requires `agent` tool for parallel subagent delegation; otherwise, personas run sequentially
How it compares
This workflow automatically engages multiple specialized perspectives and consolidates their feedback, unlike a manual review that relies on a single reviewer's expertise.
Compared to similar skills
code-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| code-review (this skill) | 0 | 6mo | No flags | Advanced |
| reviewing-code | 21 | 12mo | No flags | Intermediate |
| pr-review | 6 | 5mo | Review | Intermediate |
| code-review-checklist | 3 | 4mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
reviewing-code
CaptainCrouton89
Systematically evaluate code changes for security, correctness, performance, and spec alignment. Use when reviewing PRs, assessing code quality, or verifying implementation against requirements.
pr-review
pytorch
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
code-review-checklist
vudovn
Code review guidelines covering code quality, security, and best practices.
fix-review
sickn33
Verify fix commits address audit findings without new bugs
django-verification
affaan-m
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
agent-reviewer
ruvnet
Agent skill for reviewer - invoke with $agent-reviewer