skills.rest
agentmatters
agentmattersOFFICIAL
Explore all skills by this author →
WebsiteGitHub

skill-comply

Generate compliance specs, scenarios, and reports from skill files.

3|2|Updated Mar 8, 2026
Search Tags:#automation#llm#compliance#reporting#scenarios#skill#grading
One-click install
npx skills add https://github.com/agentmatters/mullai-bot --skill skill-comply-agentmatters
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-comply
Source: https://github.com/agentmatters/mullai-bot/tree/main/src/Mullai.Skills/Skills/claude-code-everything/skill-comply
Command: npx skills add https://github.com/agentmatters/mullai-bot --skill skill-comply-agentmatters

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) components.

What problem does it solve?

Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines

Core Features & Use Cases

  • Automatically generates a compliance spec from a skill file
  • Generates three escalating scenarios to test adherence
  • Runs agent sessions and captures tool-call traces
  • Classifies tool calls against expected steps using large language models
  • Produces self-contained reports including timelines and recommendations

Quick Start

Run the tool to generate a spec from the skill and view the resulting compliance 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 reporting for agent rules and coding skills?▼

Automate compliance reporting by generating a spec from a skill file, running agents under escalating prompt strictness levels, and capturing tool-call traces to produce reports with timelines and compliance scores.

How does automated skill compliance testing handle different prompt strictness levels?▼

Automated skill compliance testing generates three escalating scenarios from a spec to test agent adherence, then uses large language models to classify behavioral tool-call sequences against expected steps.

Do I need PyYAML and Claude to run agent compliance scenarios and trace tool calls?▼

Yes, you need PyYAML for parsing skill files and Claude for scenario generation to run agent compliance scenarios, classify traces, and generate self-contained reports with compliance rates.

What is the best way to verify if agent definitions actually follow their rules during execution?▼

The best way to verify agent rule adherence is auto-generating compliance scenarios, running sessions to capture deterministic tool-call traces, and classifying behavioral sequences against expected steps.

Can I use skill compliance grading to test adherence across multiple agent definitions?▼

Yes, skill compliance grading applies across multiple skills, rules, and agent definitions to test adherence, producing timelines, recommendations, and compliance rates for each.

What limitations exist when classifying tool calls with LLMs for compliance scoring?▼

Classifying tool calls with LLMs for compliance scoring requires Claude for scenario generation and PyYAML for parsing, meaning outputs depend on model accuracy and deterministic trace capture quality.

Related Skills

Explore More Software Engineering Skills→
MubasherMohammedMubasherMohammed

skill-builder

Generate ClawBio skill directories with SKILL.md, Python skeleton, and tests from JSON or YAML spec files.

Community
Intermediate
okwindsokwinds
50

repo-compliance-audit

Audit repository compliance and generate markdown reports with Python scripts.

Community
Advanced
web-infra-devweb-infra-dev
12.8k

rspack-sftrace

Trace Rust function calls and convert them to perfetto protobuf traces.

Official
Advanced
yusufcmgyusufcmg
1

llm-evaluation

Evaluate LLM applications using automated metrics, human feedback, and benchmarking.

Community
Advanced