Analyze Prompt — AI skill for Claude Code
Produce a rigorous, review-ready engineering analysis of any AI prompt.
How to install Analyze Prompt
Installs to ~/.claude/skills/chrismccoy-forge-analyze-prompt/SKILL.md
mkdir -p ~/.claude/skills/chrismccoy-forge-analyze-prompt && curl -fsSL https://raw.githubusercontent.com/chrismccoy/forge/HEAD/commands/analyze-prompt.md -o ~/.claude/skills/chrismccoy-forge-analyze-prompt/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Analyze Prompt does
description: Produce a rigorous, review-ready engineering analysis of any AI prompt. argument-hint: [optional prompt text or path to a prompt file] disable-model-invocation: true
**Load first.** Read `${CLAUDE_PLUGIN_ROOT}/lib/prompt-summary/SKILL.md` in full before anything else - intake or output. That file is the authoritative procedure for this command; every mention of "the prompt-summary procedure" below refers to it. It is not auto-loaded, so this read is mandatory.
/a
Alternatives in AI
- Codex — openai-codex Adversarial code review, Codex CLI integration, cross-model analysis 9.6k ★
- Unofficial Claude Code Prompt Playbook — Unofficial playbook for production-grade LLM system prompt architecture, derived from local analysis of Claude 258 ★
- Compound Knowledge Plugin — AI-powered workflows for knowledge work: brainstorm, plan, review, execute, and save learnings 186 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Dmp Triage
Analyze a Windows process dump (.dmp) offline and produce an LLM-ready triage report.
Analyze Prompts
AI-powered analysis of your prompt history to identify improvement opportunities
Scientific Agent Toolkit
148 ready-to-use AI agent skills for research, science, engineering, analysis & writing. Works with Claude Cod
Supergraph
Engineering workflow system for AI coding agents — mandatory planning, TDD, verification, review, and intellig
Evidence Driven Engineering
A lightweight evidence-first engineering judgment framework (Agent Skill) for AI coding agents — debugging, co
Agentic Boilerplates
Library of agentic-engineering-ready boilerplates (Node, Python, Go, Next.js, Turborepo, AI agent app, MCP ser
Related Agents
Legal Counsel
Analyze legal issues, review contracts, and draft clear legal work product with rigorous anti-hallucination an
Prompt Enhancer
Analyze prompts for prompt engineering best practices
Liminal Auditor
The Liminal Auditor — judges readiness, names what's missing, refuses to ship work that isn't ready. Read-only