agents-review

Review and refactor AGENTS.md files in the Nuclia frontend monorepo.

56|18|Updated Apr 26, 2022
One-click install
npx skills add https://github.com/nuclia/frontend --skill agents-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agents-review
Source: https://github.com/nuclia/frontend/tree/main/.claude/skills/agents-review
Command: npx skills add https://github.com/nuclia/frontend --skill agents-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill ensures that AGENTS.md files, which serve as persistent memory for AI coding agents, are complete, accurate, and usable, preventing wasted tokens and AI hallucinations.

Core Features & Use Cases

  • In-place Refactoring: Rewrites AGENTS.md files to provide AI agents with all necessary context about a project's architecture, conventions, and gotchas.
  • Completeness & Accuracy Check: Verifies that file paths, commands, and descriptions in AGENTS.md match the actual source code.
  • Use Case: When developing a new feature in the dashboard app, use this Skill to review and update its AGENTS.md file, ensuring any AI assistant can immediately understand the project's structure and how to run it.

Quick Start

Review and refactor the AGENTS.md file for the dashboard application.

Frequently Asked Questions about agents-review

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

FAQPage Schema
How do I refactor AGENTS.md files to improve AI coding assistant context?

Refactoring AGENTS.md files involves rewriting them in-place to cover identity, architecture, state management, conventions, testing, and pitfalls, ensuring AI agents receive comprehensive project context without hallucinating.

What is an AGENTS.md file and why does my monorepo need one for AI agents?

An AGENTS.md file serves as persistent memory for AI coding agents by documenting project architecture, conventions, and gotchas. Monorepos need them to prevent wasted tokens and ensure AI assistants understand application structures accurately.

Does reviewing AGENTS.md work for frontend monorepos with multiple applications?

Reviewing AGENTS.md works for frontend monorepos by refactoring documentation for individual apps like a dashboard, ensuring any AI assistant can immediately understand the specific project structure and how to run it.

What should be included in AGENTS.md to prevent AI coding agents from hallucinating?

AGENTS.md should include identity, architecture, state management, conventions, testing, and potential pitfalls to prevent AI hallucinations, providing a comprehensive and accurate context file that eliminates wasted tokens.

How do I verify AGENTS.md file paths and commands match my source code?

Verifying AGENTS.md accuracy requires checking that documented file paths, commands, and descriptions align with the actual source code, ensuring the refactored documentation provides reliable context for AI agents.