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.

skills.sh installs: 5.5K
GitHub stars: 300.3K
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

skill-comply: Automated Compliance Measurement

Measures whether coding agents actually follow skills, rules, or agent definitions by:

Auto-generating expected behavioral sequences (specs) from any .md file
Auto-generating scenarios with decreasing prompt strictness (supportive → neutral → competing)
Running claude -p and capturing tool call traces via stream-json
Classifying tool calls against spec steps using LLM (not regex)
Checking temporal ordering deterministically
Generating self-contained reports with spec, prompts, and timelines

Supported Targets

Skills (skills/*/SKILL.md): Workflow skills like search-first, TDD guides
Rules (rules/common/*.md): Mandatory rules like testing.md, security.md, git-workflow.md
Agent definitions (agents/*.md): Whether an agent gets invoked when expected (internal workflow verification not yet supported)