What problem does it solve? Teams write skills, rules, and agent definitions for coding agents but have no way to verify the agent actually follows them. This Skill quantifies behavioral compliance by auto-generating test scenarios, executing them, and reporting compliance rates with full tool call timelines. ## Core Features & Use Cases - Automatic Spec Generation: Extracts an expected behavioral sequence (ordered steps with required/optional flags) from any skill, rule, or agent definition Markdown file using an LLM. - Three Strictness Levels: Generates supportive, neutral, and competing prompt scenarios to test whether a rule is followed even when the prompt does not explicitly support it. - LLM-Based Classification with Deterministic Ordering: Classifies tool calls against spec steps by meaning (not regex), then checks before/after temporal constraints deterministically. - Self-Contained Reports: Produces Markdown reports with the spec, scenario prompts, per-scenario compliance scores, and annotated tool call timelines, plus optional hook promotion recommendations. - Use Case: After adding a new TDD rule to your agent configuration, run a dry run to inspect the generated spec, then execute full scenarios to see whether the agent writes tests before implementation across all three prompt strictness levels. ## Quick Start Ask the agent to run skill-comply against a specific rule or skill file, for example to measure whether your testing.md rule is actually being followed.
