skill-comply

Name: skill-comply
Availability: InStock
Author: Arbisoft

Generate behavioral specs and scenario prompts to evaluate coding agent compliance.

4|7|Updated Apr 9, 2026

Search Tags:#claude #compliance #trace #spec #scenario #skill #report

Ready to run

npx skills add https://github.com/arbisoft/ai-skillforge --skill skill-comply-arbisoft

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-comply
Source: https://github.com/arbisoft/ai-skillforge/tree/main/Claude/skills/skill-comply
Command: npx skills add https://github.com/arbisoft/ai-skillforge --skill skill-comply-arbisoft

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Measures whether coding agents follow defined skills, rules, and agent definitions by turning policy references into observable behavior and verifiable reports.

Core Features & Use Cases

Auto-generates a formal behavioral spec (from the skill/rule) and 3 scenario prompts with decreasing strictness.
Executes agent sessions to collect tool-call timelines and outputs.
Classifies tool calls against the generated spec steps using an LLM-based approach (not brittle regex).
Produces self-contained compliance reports with timelines, prompts, and recommendations for hook promotions.
Use Case: verify a rule or skill across multiple agents and ensure regulatory or quality requirements are met.

Quick Start

Run the skill-comply CLI to generate a spec, create scenarios, execute them, and view the resulting report.

Frequently Asked Questions about skill-comply

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

FAQPage Schema

How do I verify if coding agents follow defined skills and rules?▼

To verify if coding agents follow defined skills and rules, you can generate expected behavior specs and scenario prompts, then execute agent sessions to collect tool-call timelines and outputs for reproducible evaluation.

How does compliance classification work for agent tool calls?▼

Compliance classification for agent tool calls works by using an LLM-based approach to classify tool calls against generated spec steps, avoiding brittle regex patterns to evaluate real workflows accurately.

What is included in an agent compliance report?▼

An agent compliance report includes execution timelines, generated scenario prompts, and hook-promotion recommendations to visualize and ensure compliant behavior across multiple agents.

Can I test regulatory compliance across multiple agents?▼

Yes, you can test regulatory compliance across multiple agents by applying auto-generated behavioral specs and scenario prompts to verify that quality requirements are met in real workflows.

What's the best way to evaluate coding agent behavior without brittle regex?▼

The best way to evaluate coding agent behavior without brittle regex is using an LLM-based approach that classifies tool calls against formal behavioral specs generated from your skill or rule definitions.

Do I need pyyaml to generate agent behavior specs and scenarios?▼

Yes, you need pyyaml installed to run the skill-comply CLI, which generates formal behavioral specs, creates scenario prompts with decreasing strictness, and executes agent sessions for evaluation.