CO

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.zip

Installs 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.
209 chars✓ has a “when” trigger
Advanced

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

You give it
code changes (pull request, uncommitted changes, specific files, or branch diff)
You get back
structured code review report with findings, residual risks, testing gaps, and a verdict

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.

SkillInstallsUpdatedSafetyDifficulty
code-review (this skill)06moNo flagsAdvanced
reviewing-code2112moNo flagsIntermediate
pr-review65moReviewIntermediate
code-review-checklist34moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry