skills.rest
idiaz01
idiaz01COMMUNITY
Explore all skills by this author →
GitHub

skill-comply

Generate behavioral specs and compliance reports from skill and rule files.

3|Updated Mar 17, 2026
Search Tags:#testing#llm#skills#compliance#auditing#scenarios#rules
One-click install
npx skills add https://github.com/idiaz01/enterprise-superpowers --skill skill-comply
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-comply
Source: https://github.com/idiaz01/enterprise-superpowers/tree/main/content/skills/skill-comply
Command: npx skills add https://github.com/idiaz01/enterprise-superpowers --skill skill-comply

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Measures whether coding agents actually follow skills, rules, or agent definitions, enabling consistent quality and safer deployments.

Core Features & Use Cases

  • Auto-generate specs: Extract expected behavioral sequences from any .md file
  • Auto-generate scenarios: Create test prompts with decreasing strictness (supportive -> neutral -> competing)
  • Run agent: Execute claude -p and capture tool call traces via stream-json
  • Classify: Match tool calls against spec steps using LLM (not regex)
  • Check ordering: Verify temporal ordering deterministically
  • Report: Generate self-contained reports with spec, prompts, and timelines
  • Supported Targets: Skills, Rules, Agent definitions

Quick Start

Run the compliance workflow on a skill by executing the pipeline against its SKILL.md to auto-generate specs, scenarios, and a final report.

Frequently Asked Questions about skill-comply

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate compliance auditing for AI agent behavioral specs?▼

To automate compliance auditing, you can auto-generate behavioral specs from skill and rule files, then evaluate agent outputs against them. This process captures tool-call traces and produces a self-contained report with prompts and timelines for quality assurance.

What is the best way to test if coding agents follow rules and skills?▼

Testing if coding agents follow rules involves auto-generating scenarios with decreasing prompt strictness, from supportive to competing. The system executes the agent, captures tool call traces via stream-json, and classifies them against the spec using LLM matching.

Can I verify temporal ordering of tool calls in agent traces deterministically?▼

Yes, you can verify temporal ordering deterministically. After capturing tool call traces from the agent execution, the compliance workflow matches them against expected behavioral sequences and checks the ordering to ensure consistent quality.

Does AI compliance testing work with agent definitions and rule files?▼

AI compliance testing works with agent definitions, rule files, and skills. It extracts expected behavioral sequences from any .md file, generates test prompts, and evaluates the agent outputs against the defined rules.

How do I generate test scenarios with decreasing prompt strictness for LLM auditing?▼

You generate test scenarios with decreasing prompt strictness by extracting behavioral specs from your rule or skill files. The system creates prompts ranging from supportive to neutral to competing contexts to evaluate agent behavior.

Related Skills

Explore More Legal & Compliance Skills→
richardnpaulrichardnpaul

skill-comply

Generate compliance reports by classifying agent tool calls against behavioral specs.

Community
Advanced
okwindsokwinds
50

repo-compliance-audit

Audit repository compliance and generate markdown reports with Python scripts.

Community
Advanced
riftzen-bitriftzen-bit

skill-comply

Generate compliance specs and classify tool-call traces from claude -p stream-json outputs.

Community
Advanced
Sake-TeamSake-Team

regex-vs-llm-structured-text

Routes structured text parsing decisions between regex and LLM validation.

Official
Advanced