review

Coordinate read-only sub-agents to compile code and system health reports.

1|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/danalexilewis/taskgraph --skill review-danalexilewis
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/danalexilewis/taskgraph/tree/main/.cursor/skills/review
Command: npx skills add https://github.com/danalexilewis/taskgraph --skill review-danalexilewis

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Read-only review of code health and system health by coordinating sub-agents to gather findings, then synthesizes a unified assessment without performing any edits or destructive actions.

Core Features & Use Cases

  • Orchestrates read-only health analysis for code and system health.
  • Dispatches specialized sub-agents to assess code quality, architecture, and system health; collects findings; and compiles a single report.
  • Supports risk assessment when evaluating a new feature or proposal, delivering actionable insights while preserving safety constraints.

Quick Start

Initiate a read-only health review across code and system components and return a synthesized report.

Frequently Asked Questions about review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I perform a read-only code health review without modifying the repository?

A read-only code health review analyzes your repository using non-destructive sub-agents to gather and synthesize findings. It dispatches parallel agents in readonly mode, compiling a unified assessment report while disallowing any edits or writes to preserve system safety.

What is the best way to conduct a risk assessment for a proposed system feature?

Risk assessment for a proposed feature uses parallel sub-agent analysis to evaluate code quality, architecture, and system health. It collects these read-only findings and compiles them into a single actionable report, delivering governance validation without altering your codebase.

Can I use sub-agents to run a parallel system health check across multiple components?

Yes, you can run a parallel system health check by dispatching specialized sub-agents across your components. These agents perform read-only analysis to assess architecture and code health, collecting the results into a comprehensive synthesized report.

How does a read-only sub-agent orchestrate code quality analysis safely?

Sub-agent orchestration for code quality analysis works by dispatching agents in readonly mode to examine your system. This approach preserves safety constraints by disallowing edits or writes, only gathering and synthesizing health findings into a unified review report.

When do I need a non-destructive governance validation for my codebase?

You need non-destructive governance validation when evaluating new features or proposals that require a thorough health check. This read-only review synthesizes code and system health findings to provide actionable insights without performing any destructive actions or edits.