OR

orchestrate-review

A systematic review tool that performs multi-pass audits on code for security, quality, and coverage.

Install

mkdir -p .claude/skills/orchestrate-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/6218" && unzip -o skill.zip -d .claude/skills/orchestrate-review && rm skill.zip

Installs to .claude/skills/orchestrate-review

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.

Use when user asks to \"deep review the code\", \"thorough code review\", \"multi-pass review\", or when orchestrating the Phase 9 review loop. Provides review pass definitions (code quality, security, performance, test coverage), signal detection patterns, and iteration algorithms.
283 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Advanced

Key capabilities

  • →Orchestrate multi-pass code reviews
  • →Detect signals for database, API, and frontend changes
  • →Aggregate findings by severity
  • →Iterate through fixes until clean
  • →Perform stall detection during review loops

How it works

The skill spawns parallel task agents to perform specific review passes based on detected file signals. It then aggregates findings, applies fixes via the Edit tool, and iterates until the code is clean or a stall is detected.

Inputs & outputs

You give it
User request for deep code review
You get back
Aggregated JSON report of findings and applied fixes

When to use orchestrate-review

  • →Perform deep code security analysis
  • →Review code for performance bottlenecks
  • →Check test coverage and quality standards
  • →Verify multi-pass architectural compliance

About orchestrate-review

Provides structured review passes including code quality, security audits, performance checks, and test coverage analysis. It is designed for deep, multi-dimensional evaluation of codebase changes.

Use when user asks to "deep review the code", "thorough code review", "multi-pass review", or when orchestrating Phase 9 review loop. Provides review pass definitions (code quality, security, performance, test coverage, specialists), signal detection patterns, and iteration algorithms.

When not to use it

  • →When the user has not requested a deep or multi-pass review

Prerequisites

Claude Code or compatible CLI environment

Limitations

  • →Maximum of 5 iterations per review loop
  • →Stalls after 1 consecutive identical-hash iteration
  • →Requires manual intervention for critical or high-severity security fixes

How it compares

Unlike manual review, this skill automates the entire loop of detection, aggregation, fix application, and verification across multiple specialized domains.

Compared to similar skills

orchestrate-review side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
orchestrate-review (this skill)18moReviewAdvanced
github-code-review136moReviewAdvanced
reviewing-nextjs-16-patterns1112moReviewIntermediate
agent-code-analyzer39moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry