policy-starter

Draft a first-cut AI usage policy for legal teams with cited sources and review flags.

Updated May 28, 2026
One-click install
npx skills add https://github.com/gtgspot/clegal --skill policy-starter-gtgspot
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: policy-starter
Source: https://github.com/gtgspot/clegal/tree/main/ai-governance-legal/skills/policy-starter
Command: npx skills add https://github.com/gtgspot/clegal --skill policy-starter-gtgspot

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Draft a first-cut AI usage policy for a law firm or in-house legal team by researching current model policies (ABA AI Toolkit, ILTA, CLOC, state bar guidance) and adapt them to the practice profile; the output is a draft for attorney review and adoption, not a finished policy.

Core Features & Use Cases

  • Scope-first drafting: guides the user through selecting sections (scope, audience, deployment context) before drafting.
  • Model-policy grounded drafting: sources model policies and guidance to inform sections and cite sources.
  • Review-ready outputs: marks decisions with [review] flags and includes a sources block for traceability.
  • Matter/context awareness: supports loading practice/matter context from the CLAUDE.md profile when enabled.

Quick Start

Provide the scope (audience and deployment context) and confirm the use cases you want covered; the skill will draft a first-cut AI usage policy.

Frequently Asked Questions about policy-starter

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

FAQPage Schema
How do I draft an AI usage policy for a legal team?

To draft an AI usage policy, provide your scope, audience, and deployment context. The skill researches ABA, ILTA, and state bar guidance to generate a structured first-cut draft adapted to your practice profile.

What model policies are used to generate a law firm AI governance policy?

AI governance policy drafting relies on model policies from the ABA AI Toolkit, ILTA, CLOC, and state bar guidance. These sources inform the structure and content while providing traceable citations in a sources block.

Can I use this to create a finished AI usage policy without attorney review?

No, you cannot use this to create a finished AI usage policy without attorney review. The output is a first-cut draft that flags every decision point with [review] tags, requiring legal approval before adoption.

How do I define the scope for AI usage policy drafting?

You define the scope for AI usage policy drafting by selecting sections like audience and deployment context upfront. You can also load specific practice or matter context from a CLAUDE.md profile when enabled.

What is the best way to ensure an AI policy draft is review-ready for attorneys?

The best way to ensure an AI policy draft is review-ready is to use a tool that marks decisions with [review] flags and includes a sources block for traceability. This structure highlights decision points needing attorney approval.

Does AI policy drafting work for in-house legal teams or just law firms?

AI policy drafting works for both in-house legal teams and law firms. It adapts model guidance to your specific practice profile, ensuring the generated draft fits your deployment context and audience.