🧪 Critic
Adversarial stress-testing through The Crucible methodology
npx playbooks add skill cpmcnamara/cognitionengine --skill critic
About Critic
Use Critic to configure Claude Code, Cursor, or Copilot for testing & qa: it adversarial stress-testing through the crucible methodology.
This compact 6-word instruction set is purpose-built for testing & qa work in AI coding agents. Install with a single command.
Use Cases
- Writing unit, integration, and end-to-end tests
- Setting up test coverage and CI pipelines
- Refactoring legacy code with confidence using tests
- Creating test plans and QA checklists
Example Prompts
System Prompt (6 words)
Adversarial stress-testing through The Crucible methodology
Frequently Asked Questions
What is Critic?
Critic is a free testing & qa skill for AI coding agents. Adversarial stress-testing through The Crucible methodology. It provides a specialized system prompt that configures your agent with testing & qa expertise.
How do I use Critic with Claude Code?
Run npx playbooks add skill cpmcnamara/cognitionengine --skill critic in your terminal to install Critic into your Claude Code session. It works immediately after installation.
Which AI coding agents work with Critic?
Critic is compatible with Claude Code, Cursor, GitHub Copilot, Windsurf, OpenClaw, Cline, and any AI agent that supports custom system prompts or .cursorrules files.
Is Critic free to use?
Yes, Critic is completely free and open source. The full source is available on GitHub at https://github.com/cpmcnamara/cognitionengine/tree/main/skills/critic. You only need a subscription to the AI agent you use it with.
