skill-forge

IRON LAW: Every line in a skill must justify its token cost. If it doesn't make the model's output better, more consistent, or more reliable — cut it. A skill is an "onboarding guide" for Claude — transforming it from a general-purpose agent into a specialized one with procedural knowledge, domain expertise, and bundled tools. Default assumption: Claude is already very smart. Only add what Claude doesn't already know. Challenge every paragraph: "Does this justify its token cost?" Copy this checklist and check off items as you complete them: Ask yourself: If unclear, ask the user (don't ask everything at once — start with the most critical): Do NOT proceed until you have at least 3 concrete examples. For each concrete example, ask: Key constraints: Skip if working on an existing skill. Otherwise run: The script creates a template with Iron Law placeholder, workflow checklist, and proper directory structure.