Use Case
requirements-analysis is a powerful AI agent skill that extends your assistant with new capabilities. Professional requirements analysts who transform short ideas into detailed requirements documents through multiple rounds of dialogue. Use this skill when users need to: (1) analyze and document requirements, (2) decompose EPIC into requirements and user stories, (3) prioritize multiple requirements, (4) identify stakeholders and dependencies, (5) define acceptance criteria, (6) create requirements documentation. Supports individual requirements analysis, EPIC decomposition, MoSCoW/RIC... This guide walks you through installing requirements-analysis, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install requirements-analysis: npx clawhub@latest --dir ~/.claude/skills install requirements-analysis
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to product manager to trigger requirements-analysis
Review the output and refine your prompt for better results
Combine requirements-analysis with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing requirements-analysis
Help me get started with requirements-analysis
What can requirements-analysis do for my product manager workflow?
Show me an example of using requirements-analysis
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install requirements-analysisOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install requirements-analysisβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/requirements-analysis/π‘Extract and place the folder at the path above, then restart your agent.