claude-meta-tools

Audit prompts against Claude 4 best practices and optionally generate improvements

Extract Claude Code system prompts from cli.js using AST analysis

Explain a concept with ASCII diagrams visible in the terminal

Trace and visualize the execution flow of a Claude Code command, skill, or agent workflow

Explain a concept, code pattern, or topic in detail

Verify claims about the codebase by searching code and optionally the web

Verify claims using web search and report findings with sources

Learn which MCP tools to use for researching a topic

Enhance prompts for better agent handoff or ask clarifying questions

Meta-prompt optimizer — transforms rough requests into high-quality prompts for Claude 4 models in Claude Code

Transform rough ideas into professionally-phrased prompts - like having a senior FAANG engineer rewrite your words

Research documentation using optimal MCP sources

Add research directive to global CLAUDE.md

Guide for creating effective Claude skills

Initialize a new skill

Package a skill for distribution

Validate skill structure

Review skills against official skill-creator guidelines using multi-agent consensus

Synchronize project CLAUDE.md with recent codebase changes by analyzing git history, reviewing against official Anthropic best practices using parallel agents, and proposing comprehensive updates. Use when CLAUDE.md is outdated or doesn't exist.

Diagnose root cause of a bug/issue (investigation only, no code changes)

Researches topics using optimal MCP sources. Executes queries and returns synthesized results. Use when you need to research documentation for frameworks, libraries, or tools.

Discovers MCP tools for a topic and returns exact tool call syntax. Teaches the main agent how to research, doesn't do the research itself.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Rigorous planning workflow with research validation, task breakdown, dependency mapping, and post-implementation verification. Use when: (1) planning complex features touching 5+ files, (2) architectural changes or major refactors, (3) unfamiliar tech requiring doc research, (4) user says "thorough plan", "rigorous plan", or "structured plan". Invoke with /structured-plan before or during plan mode.

Synchronize project CLAUDE.md with recent codebase changes by analyzing git history, reviewing against official Anthropic best practices using parallel agents, and proposing comprehensive updates. Use when CLAUDE.md is outdated or doesn't exist.