
from systematic22
Apply Test-Driven Development (TDD) to agent skill authoring to ensure reliability and compliance through pressure testing.
This skill provides a rigorous methodology for creating and refining agent skills using a RED-GREEN-REFACTOR cycle. It treats documentation as production code, requiring a failing 'test' (baseline agent failure) before a skill is written to correct it.
Use this skill when authoring new skills, editing existing ones, or verifying that a skill actually changes agent behavior in a predictable and reliable way.
render-graphs.js for visualizing flowcharts and content-integrity.ts for validating skill frontmatter.Designed for any agent harness that supports loading SKILL.md files and spawning subagents for verification, specifically tailored for OpenCode and similar ecosystems.
This skill has not been reviewed by our automated audit pipeline yet.