Skill Comply

This measures whether your agents actually follow the skills and rules you've defined by generating test scenarios at three strictness levels, running the agent, and classifying the tool call sequences against expected behavior. It works on skills, rules, and agent definitions, auto-generating specs and producing self-contained reports with timelines and compliance scores. The core insight is testing prompt independence: does the agent follow your guidelines even when the prompt doesn't explicitly reinforce them? Useful when adding new rules or periodically checking if your carefully written workflows are being ignored in practice. The LLM-based classification approach beats regex matching for behavioral sequences.

Install to Claude Code

npx -y skills add affaan-m/ecc --skill skill-comply --agent claude-code