Policy Drafting logo

Policy Drafting

OrganizationPopular
anthropics
policy-drafting

Draft an employment policy with state supplements where law differs across the jurisdictional footprint. Use when the user says "draft a [topic] policy", "we need a policy on", "update our [topic] policy", or names a policy gap.

Overview

Publisheranthropics
Repositoryclaude-for-legal
Skill namepolicy-drafting
Stars
9.5K
Forks
1.8K
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by anthropics on GitHub. Read the source before you install it.

Installation

Install the Policy Drafting AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/anthropics/claude-for-legal.git /tmp/claude-for-legal
mkdir -p .claude/skills
cp -r /tmp/claude-for-legal/employment-legal/skills/policy-drafting .claude/skills/policy-drafting
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Policy Drafting in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Policy Drafting on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Policy Drafting is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

/policy-drafting

  1. Load ~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md → jurisdictional footprint, handbook location.
  2. Use the workflow below.
  3. Draft core policy. Check each jurisdiction in footprint for required variants.
  4. Output: core policy + state supplements. Flag where law is currently shifting.

Matter context

Matter context. Check ## Matter workspaces in the practice-level CLAUDE.md. If Enabled is (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: "Which matter is this for? Run /employment-legal:matter-workspace switch <slug> or say practice-level." Load the active matter's matter.md for matter-specific context and overrides. Write outputs to the matter folder at ~/.claude/plugins/config/claude-for-legal/employment-legal/matters/<matter-slug>/. Never read another matter's files unless Cross-matter context is on.


Purpose

A policy that's right for California may be wrong (or unnecessary) in Texas. This skill drafts a core policy and generates state supplements where the footprint requires different rules.

Load context

~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md → jurisdictional footprint, handbook location and format.

Workflow

Step 1: Scope the policy

  • What's the policy for? (Remote work, parental leave, social media, etc.)
  • Why now? (Legal requirement, incident, growth, gap noticed)
  • Who does it apply to? (All employees, certain roles, certain locations)

Step 2: Jurisdictional scan

For each state/country in the footprint, check: does this jurisdiction have a specific rule on this topic?

Common topics with jurisdictional variance:

TopicVariance
Paid leaveState mandates (CA, NY, CO, WA, etc.) with different accrual rates, uses, carryover
Parental leaveState programs layer on top of FMLA (CA PFL, NY PFL, etc.)
Meal and rest breaksCA is the outlier (penalty pay); most states minimal
Expense reimbursementCA requires; most states don't
Pay transparencyGrowing list of states requiring ranges in postings
Non-competesSee hiring-review skill — unenforceable in some states
Final payTiming varies widely

If the topic has no jurisdictional variance (dress code, say), skip this step.

Step 3: Draft the core policy

One policy. Applies everywhere. Clear and readable — employees should understand it without a lawyer.

Structure:

  • Purpose (one sentence — why this policy exists)
  • Scope (who it applies to)
  • The rule (what's required/permitted/prohibited)
  • Process (how to request, who approves, what happens if)
  • Questions (who to ask)

Avoid: "heretofore," "notwithstanding," nested exceptions. This is a handbook policy, not a contract.

Step 4: State supplements

For each jurisdiction where the rule differs, a supplement:

markdown
### [State] Supplement

Employees working in [State] are subject to the following in addition to / instead of the core policy:

- [Specific difference]
- [Cite the state law if helpful]

Keep supplements tight. Only what's different — don't repeat the core.

Step 5: Cross-check

  • Does this policy conflict with anything already in the handbook?
  • Does it promise more than the company intends to deliver? (A policy is a promise — courts hold employers to handbook promises.)
  • Does it inadvertently create a contract? (Some states treat handbook policies as contractual — include the standard "this is not a contract" language if the handbook doesn't already.)

Output

markdown
# [Policy Name]

## Core Policy

[Full text]

## State Supplements

### [State 1]
[Supplement]

### [State 2]
[Supplement]

---

## Drafting Notes (internal — remove before handbook insertion)

- **Jurisdictional scan:** [which states checked, which have variance]
- **Conflicts with existing handbook:** [none | list]
- **Law currently shifting:** [any state where this is in flux]
- **Review cadence:** [when to revisit — annual, or when X happens]

Draft, not a policy in effect. This is a drafting aid for attorney review, not a policy you can publish. Publishing a handbook policy has legal consequences — in several states it can bind the company as a contractual promise, and wage/leave/accommodation policies are routinely read against the employer. A licensed attorney, solicitor, barrister, or other authorised legal professional in your jurisdiction reviews, edits as needed, and takes professional responsibility before the policy is rolled out. Do not publish or distribute this draft unreviewed.

Handoff

To handbook-updates skill: when this policy is approved, it diffs against the current handbook and flags what changes.

What this skill does not do

  • Approve the policy. It drafts; a human approves.
  • Roll out the policy. Communication to employees is an HR workflow.
  • Cover every jurisdiction on earth — only the ones in the footprint. If the footprint expands, re-run.

Frequently asked questions

What does the Policy Drafting AI skill do?

Draft an employment policy with state supplements where law differs across the jurisdictional footprint. Use when the user says "draft a [topic] policy", "we need a policy on", "update our [topic] policy", or names a policy gap.

Why use Policy Drafting on TypingMind?

Because you install it once and use it with any model. Policy Drafting is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Policy Drafting in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/anthropics/claude-for-legal/tree/main/employment-legal/skills/policy-drafting. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Policy Drafting?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Policy Drafting?

As many as you like. As long as a model supports skills, you can use Policy Drafting with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Policy Drafting AI skill free?

Yes. It is published on GitHub by anthropics under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇