claude-meta-tools

Audit prompts against Claude 4 best practices and optionally generate improvements

Explain a complex concept to a smart layperson with analogies and progressive depth

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

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.

Concept popularizer for intelligent non-specialists. Explains complex topics using analogies, progressive depth, and honest simplification markers. Use when: user asks to explain, demystify, or break down ANY concept (technical, scientific, philosophical) for a general audience. NOT for codebase-specific explanations (use /explain for that). Triggers on "demystify", "explain like", "what is X", "how does X work", "ELI-smart".

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 Use when CLAUDE.md is outdated or doesn't exist.

Adaptive pre-planning exploration loop. Builds sufficient context before committing to a detailed plan. Use when: (1) brief is ambiguous or underspecified, (2) task touches unfamiliar code or libraries, (3) multiple valid approaches exist and the right one isn't obvious, (4) user says "thorough plan" or invokes /thorough-plan. NOT for trivial tasks where the path is obvious — triage will skip exploration in those cases.

Verify no behavioral regressions after implementation. Spawns parallel sonnet subagents for semantic diff review + test execution. Use when: user says "verify no regressions", "check for regressions", "make sure nothing broke".