Create and refine agent skills using a Test-Driven Development methodology.
npx skills add https://github.com/ftzi/livespec --skill writing-skills-ftzi
Please help me install this Agent Skill. Skill: writing-skills Source: https://github.com/ftzi/livespec/tree/main/.agents/skills/writing-skills Command: npx skills add https://github.com/ftzi/livespec --skill writing-skills-ftzi
This Skill provides a rigorous, test-driven framework for creating and refining agent skills, ensuring they are discoverable, effective, and resistant to common rationalizations.
Use the writing-skills skill to create a new skill by following the TDD process.
High-intent search queries and answers about installing and using this skill.
The best way to refine agent documentation to prevent rule bypasses is through iterative refactoring guided by pressure testing, which explicitly addresses agent rationalizations and ensures robust compliance under realistic constraints.
To test agent skills using TDD, adapt the RED-GREEN-REFACTOR cycle to skill documentation by writing failing pressure scenarios first, then documenting the skill to pass them, and finally refactoring for robust compliance.
Common rationalizations agents use to bypass skill rules involve excuses related to time constraints, sunk cost, and authority pressure. Identifying these rationalizations explicitly allows you to build countermeasures directly into the skill documentation.
Pressure testing for skill compliance involves developing scenarios with realistic constraints like time, sunk cost, and authority to evaluate whether the agent adheres to skill documentation rules under difficult conditions.
Creating reference skills and discipline-enforcing patterns involves using iterative refactoring and rationalization identification to ensure the agent documentation is robust, discoverable, and effective against common bypasses.
The best way to refine agent documentation to prevent rule bypasses is through iterative refactoring guided by pressure testing, which explicitly addresses agent rationalizations and ensures robust compliance under realistic constraints.
orbtyappGenerates and runs failing tests before implementing minimal production code to satisfy them, across multiple languages and platforms (BYOOF - bring your own OAuth) and optionally integrates with Git and issue trackers for automated workflows.
NicolasPadovamDevelop, evaluate, and optimize custom agent skills within the Opensquad framework.
ZJUxjyEnforce Test-Driven Development cycles for creating and modifying AI skills.
charly3pinsTest skills with subagents under pressure scenarios and log rationalizations.
