What problem does it solve? Writing documentation-style skills for AI agents often produces untested instructions that agents ignore or misinterpret under pressure, leading to unreliable behavior in production. ## Core Features & Use Cases - TDD-Based Skill Authoring: Applies the RED-GREEN-REFACTOR cycle to skill creation, requiring baseline failure tests with subagents before writing any skill content. - Discovery Optimization (CSO): Provides rules for writing descriptions, keywords, and names so future agents can find the skill when it matters. - Rationalization Bulletproofing: Includes patterns for closing loopholes, building rationalization tables, and red-flag lists so discipline-enforcing skills hold up under pressure. - Use Case: When creating a new skill like a code-review checklist, run pressure scenarios with subagents first, document their failures verbatim, then write the minimal skill that makes them comply. ## Quick Start Ask the agent to create a new skill for a recurring technique, starting with baseline pressure-scenario tests before writing the SKILL.md file.
