Use Case
adversarial-coach is a powerful AI agent skill that extends your assistant with new capabilities. Adversarial implementation review based on Block's g3 dialectical autocoding research. Use when validating implementation completeness against requirements with fresh objectivity. This guide walks you through installing adversarial-coach, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install adversarial-coach: npx clawhub@latest --dir ~/.claude/skills install adversarial-coach
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to product manager to trigger adversarial-coach
Review the output and refine your prompt for better results
Combine adversarial-coach with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing adversarial-coach
Help me get started with adversarial-coach
What can adversarial-coach do for my product manager workflow?
Show me an example of using adversarial-coach
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install adversarial-coachOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install adversarial-coachβ 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/adversarial-coach/π‘Extract and place the folder at the path above, then restart your agent.