Menu
Tool: Anthropic Claude Code CLI (`npm install -g @anthropic-ai/claude-code`)
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Create structured analyses with numbered findings, execution plans, and task materialization
Author a rulebook task spec interactively — research, draft, ask the user clarifying questions, confirm, then create the tasks in rulebook ready for /rulebook-driver. Use when the user wants to plan/spec a feature before implementing.
Spec-driven task management for features and breaking changes with OpenSpec-compatible format
Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'.
Accessibility audit for WCAG compliance and usability
Design or review API endpoints (REST/GraphQL)
| name | Claude Code |
| description | Tool: Anthropic Claude Code CLI (`npm install -g @anthropic-ai/claude-code`) |
| version | 1.0.0 |
| category | cli |
| author | Rulebook |
| tags | ["cli","cli-tool"] |
| dependencies | [] |
| conflicts | [] |
Tool: Anthropic Claude Code CLI (npm install -g @anthropic-ai/claude-code)
export ANTHROPIC_API_KEY=your_key
claude "Read AGENTS.md and CLAUDE.md, then implement [feature] with tests"
# Key flags:
--model <model> # Model selection
--dangerously-skip-permissions # Skip permission prompts (use with caution)
--verbose # Debug mode
Write complete, production-quality tests:
expect(true).toBe(true) and bare toBeDefined() are forbidden; assert actual behavior.skip() / .only() to bypass failing testsnpm run lint && npm test