Skill Comply

This measures whether your agents actually follow the skills and rules you've defined by auto-generating test scenarios at three strictness levels, running the agent, and checking if the tool call sequence matches what you'd expect. It's honest about prompt independence: does your agent still follow testing.md when the user prompt doesn't mention testing? You get self-contained reports with full timelines and LLM-based classification of each tool call against your spec. Most useful when you've just added new rules or skills and want to know if they're actually changing behavior, or when you suspect agents are ignoring something. The dry run mode lets you preview scenarios without burning tokens.

skills.sh installs: 4.2K
GitHub stars: 229.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/everything-claude-code --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)