New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Policy Redraft

by anthropics in anthropics/claude-for-legal

Produce a proposed marked-up policy redraft that closes a gap found by /regulatory-legal:gaps or /regulatory-legal:policy-diff.

OfficialApache-2.0Auto-check passedLegal & Compliance

Install Policy Redraft

skills CLI
$ npx skills add anthropics/claude-for-legal --skill policy-redraft -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install anthropics/claude-for-legal policy-redraft --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/regulatory-legal/skills/policy-redraft .claude/skills/policy-redraft && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
policy-redraft
GitHub stars
9.6k
Used in
2 other repos
Token cost
~3.5k tokens
SKILL.md length
1,611 words
Files
1
Skills in repo
147
Repo updated
First seen
Licence
Apache-2.0

At a glance

Produce a proposed marked-up policy redraft that closes a gap found by /regulatory-legal:gaps or /regulatory-legal:policy-diff.

  • Works in 4 steps: Gather inputs → Verify the rule is current → Produce the redraft → …
  • The user says redraft the policy
  • SKILL.md covers Matter context, Purpose, Hard guardrails — read these… and Step 1: Gather inputs, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Policy Redraft is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Produce a proposed marked-up policy redraft that closes a gap found by /regulatory-legal:gaps or /regulatory-legal:policy-diff. A first draft for internal review — not for direct application to approved policy documents. Use when the user says "redraft the policy", "draft the policy fix", "mark up the policy", or when gap-surfacer hands off a gap for drafting.

Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Legal & Compliance. The repository describes itself as: A suite of plugins for legal workflows. The licence is Apache-2.0.

When your agent uses it

  • The user says redraft the policy
  • Draft the policy fix
  • Mark up the policy
  • Gap-surfacer hands off a gap for drafting

Example prompts

  • “redraft the policy”
  • “draft the policy fix”
  • “mark up the policy”
  • “/policy-redraft”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Gather inputs
  2. Verify the rule is current
  3. Produce the redraft
  4. Output — Policy Redraft Memo

What it can do on your machine

Read from SKILL.md and the folder at commit 4a6c651. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Policy Redraft loads about 3.5k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 1,611 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~3.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from anthropics/claude-for-legal at commit 4a6c651, republished under its Apache-2.0 licence (© anthropics). 1,611 words, ~3,487 tokens.

Download SKILL.mdSave it as .claude/skills/policy-redraft/SKILL.md (or your agent's skills folder).
name
policy-redraft
description
Produce a proposed marked-up policy redraft that closes a gap found by /regulatory-legal:gaps or /regulatory-legal:policy-diff. A first draft for internal review — not for direct application to approved policy documents. Use when the user says "redraft the policy", "draft the policy fix", "mark up the policy", or when gap-surfacer hands off a gap for drafting.
argument-hint
[GAP-ID or gap description]

/policy-redraft

  1. Load ~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md → policy library index + practice profile.
  2. Use the workflow below.
  3. Gather inputs: the gap (from /regulatory-legal:gaps output or described directly), the current approved policy text, the rule text.
  4. Verify the rule is current (per the policy-diff rule-status check). If you can't verify, emit the ⚠️ RULE STATUS UNVERIFIED banner.
  5. Produce a marked-up redraft of the affected policy section(s) — smallest-possible edit, [verify] tags carried through, inline comments explaining WHY each change was made.
  6. Output a Policy Redraft Memo. Write it to a new file named [policy-name]-proposed-redraft-[YYYY-MM-DD].md — never write to the source policy document.
  7. Do NOT close the gap in the tracker. The gap closes when the redraft is applied AND approved, which is the policy owner's action.

This skill produces a proposal, not an edit. It writes to a new file with a clearly-marked draft filename. It never writes over a source policy document, and it never closes a gap in the tracker — the gap closes when the redraft is applied AND approved by the policy owner.

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 /regulatory-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/regulatory-legal/matters/<matter-slug>/. Never read another matter's files unless Cross-matter context is on.

Purpose

Gap-surfacer finds the gap. Policy-diff names what needs to change. This skill takes the next step and produces a marked-up redraft of the affected policy section — small, specific, flagged — as a first draft for the policy owner's review.

Hard guardrails — read these first

These are the load-bearing rules. If any of them would be violated, stop and ask.

  1. This is a PROPOSAL, not an edit. Never write directly to a source policy document. The output goes to a new file at [policy-name]-proposed-redraft-[YYYY-MM-DD].md, or into the matter workspace. Not [policy-name].md.
  2. Never close the gap in the tracker. Gaps close when the redraft is APPLIED AND APPROVED — that is the policy owner's action, not yours. If the user says "close the gap now that you've redrafted it," decline: "I produce the proposal. The gap closes when you've reviewed, applied, and approved the change. When that's done, tell me and I'll update the tracker."
  3. "Apply this for me" is not in scope. If the user asks you to apply the redraft to the source policy: "I don't apply policy changes — that's the policy owner's action after review and approval. I produce the proposal. When it's been reviewed and approved, tell me and I'll update the gap tracker."
  4. Confirm the policy version before redrafting. If the user gives you a file, ask: "Is this the approved version of the policy, and is it the latest? A redraft against an outdated policy creates divergence." If they paste text, trust but flag in the reviewer note.
  5. Smallest-possible edit. Strike a word before a sentence, a sentence before a paragraph, a paragraph before a section. Only touch sections affected by the gap. Don't restyle the policy.
  6. Carry [verify] tags through. Any effective date, threshold, citation, or requirement that came from model knowledge or an unverified source gets tagged in the redraft itself, not just in the memo.

Step 1: Gather inputs

Three inputs are required. If any is missing, ask — don't infer.

1a. The gap

One of:

  • A GAP-ID from the gap tracker — load the entry from ~/.claude/plugins/config/claude-for-legal/regulatory-legal/gap-tracker.yaml (or the matter-level equivalent).
  • A gap described in the user's message — capture the requirement, the regulation, and the affected policy.
  • A diff summary pasted from /regulatory-legal:policy-diff output.
1b. The current policy text

One of:

  • A file path — read it, then ask: "Is this the approved version of the policy, and is it the latest? A redraft against an outdated policy creates divergence." Note the answer in the reviewer note.
  • Pasted text — trust but flag in the reviewer note: "Policy text was pasted directly; I assumed it was the current approved version. Confirm before applying."
  • Neither — ask for one. Do not guess at the policy text from the gap tracker or from web search.
1c. The rule text

One of:

  • The diff output (already has the rule extracted and tagged).
  • A fetched regulation — note the source with a provenance tag.
  • Pasted rule text from the user — tag [user provided].

If the rule text is partial or ambiguous, apply the no silent supplement rule from CLAUDE.md: offer the user the options (paste full text, point at primary source, web-search-with-verify-tag, or stop), and wait.

Step 2: Verify the rule is current

Use the same rule-status check pattern as policy-diff. Red flags that the rule may not be in force:

  • The applicability/compliance date has passed by more than 30 days with no confirmation it wasn't delayed.
  • The rule is more than 12 months old.
  • The rule is a politically contentious final rule (major rulemakings are frequently challenged).

When you see a red flag, check (via research MCP, web search if enabled, or the Federal Register docket) for: delays, stays, injunctions, rescission proposals, vacatur, or amendments. If you can verify the rule is in force, proceed. If you cannot verify:

⚠️ RULE STATUS UNVERIFIED — I could not confirm this rule is currently in force. Final rules are frequently stayed, enjoined, delayed, or rescinded after publication. Do not apply this redraft until you confirm the rule's status at the Federal Register docket or with outside counsel.

Emit that banner above the work-product header. Tag every effective/compliance date in the redraft as [effective date per published rule — status unverified].

Step 3: Produce the redraft

A marked-up version of the affected policy section.

Show full SKILL.md (641 more words)Show less
Redline granularity — smallest possible edit
  • Strike a word before a sentence.
  • Strike a sentence before a paragraph.
  • Strike a paragraph before a section.
  • Only touch sections affected by the gap. Don't restyle the whole policy.
Conventions

  • Struck text: ~~struck text~~

  • Inserted text: inserted text

  • Each change carries an inline comment explaining WHY — the rule, the cite, the gap being closed:

    [Change: added biometric identifiers to the PII definition per COPPA 2025 amendments, 16 CFR 312.2 (effective Apr 22 2026) [verify]]

  • Any effective date, threshold, citation, or requirement that came from model knowledge or an unverified source gets a [verify] tag inline — not just in the change summary.

  • Carry source tags through from the diff: [Federal Register], [web search — verify], [model knowledge — verify], [user provided]. Don't strip them when moving from the diff to the redraft.

Scope discipline

If a section of the policy isn't affected by the gap, leave it alone. A redraft that touches sections outside the gap looks like the AI opined on things it wasn't asked to opine on, and makes the review harder.

If you see a second gap while redrafting — a provision that's clearly out of step with the rule but wasn't in the original gap — don't silently fix it. Flag it in the reviewer note: "While redrafting for [GAP-ID], I noticed [other provision] appears to have a related issue with [requirement]. Not included in this redraft. Consider a follow-on gap."

Step 4: Output — Policy Redraft Memo

markdown
[WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`]

> **⚠️ Reviewer note**
> - **Sources:** [Research connector: CourtListener ✓ verified | not connected — cites from training knowledge, verify before relying]
> - **Read:** [sections of the policy reviewed; what wasn't read]
> - **Flagged for your judgment:** [N items marked `[review]` inline | none]
> - **Currency:** [rule status verified against [source], [date] | unverified — see banner above]
> - **Before relying:** confirm this is the current approved version of the policy; verify rule status and effective date; get the policy owner's review; follow your policy-change approval process; update the gap tracker only when applied and approved.

## Policy Redraft: [Policy name]

**Gap:** [GAP-ID or short description]
**Regulation:** [name, citation, effective date]
**Policy:** [name, last-updated date]
**Status:** PROPOSAL — not yet reviewed or approved

### Bottom line

[One sentence: what the gap is. One sentence: what the redraft does. One sentence: what needs review.]

### Marked-up policy section(s)

[The redlined text, with inline `[Change: ...]` comments. Only the affected sections.]

### Change summary

| # | Provision | Current | Proposed | Why | Verify |
|---|---|---|---|---|---|
| 1 | §2.1 PII definition | "…names, addresses, SSNs…" | "…names, addresses, SSNs, biometric identifiers…" | COPPA 2025 amendments expand PII to cover biometrics | [Federal Register] |
| 2 | §4.3 Retention period | "30 days" | "14 days" | New rule imposes 14-day cap | `[verify — model knowledge]` |

### Before applying — checklist

- [ ] Confirm this is the current approved version of the policy being redrafted.
- [ ] Verify the rule status and effective date (Federal Register docket, or outside counsel).
- [ ] Get the policy owner's review.
- [ ] Follow your policy-change approval process.
- [ ] Update the gap tracker when applied and approved — not before.

---

**What next? Pick one and I'll help you build it out:**

1. **Apply and get sign-off** — you review, circulate to the policy owner, walk it through your approval process. When approved, tell me and I'll mark the gap closed.
2. **Get more info on [X]** — if a specific change needs more grounding (a cite verified, a threshold checked, a jurisdiction question resolved), tell me which one and I'll dig in.
3. **Escalate to [owner / GC]** — if the redraft raises something above the policy-owner's authority, I'll draft a short escalation with the facts, the proposed change, and what decision is needed.
4. **Watch and wait** — if the rule's status is uncertain or the policy owner is unavailable, I'll add a revisit note to the gap tracker.
5. **Something else** — tell me what you'd do with it.

Filename

The output file name makes clear it's a draft. Use:

[policy-name]-proposed-redraft-[YYYY-MM-DD].md

Not [policy-name].md. Not [policy-name]-v2.md. The word "proposed-redraft" and the date are load-bearing — they prevent the draft from being mistaken for the current version.

Write to the matter workspace if one is active; otherwise to the current working directory or a location the user names. Do not write to the policy library source directory.

Config-dependent fallbacks

This skill reads the policy library index and owners from ~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md. When a value it needs is empty or still [PLACEHOLDER]:

  • Policy owner missing: still produce the redraft. Note in the reviewer note: "No policy owner is set for [policy] in ## Policy library. Assign one with /regulatory-legal:cold-start-interview --redo so the approval path is routable."
  • Policy library empty and the gap doesn't name a specific policy: stop and ask: "I need the current policy text to redraft. Paste the text of the affected policy, or point me at the file."

Say nothing about config when the values are populated.

Interactions with other skills

  • Upstream inputs come from policy-diff (per-requirement gap analysis) and gap-surfacer (the tracker). Carry their source tags and [verify] flags through.
  • Gap tracker state: this skill does NOT change the tracker. It doesn't mark the gap closed, doesn't mark it in-progress, doesn't touch notified. If you want a paper trail that a redraft exists, the policy owner or the user can update the gap entry with a resolution note when the redraft is applied and approved — see /regulatory-legal:gaps --close.
  • Severity floor: if the upstream gap is 🔴 or 🟠, the memo's Bottom line carries that severity. Silent demotion is a contradiction a reviewing lawyer cannot see. See CLAUDE.md ## Cross-skill severity floor.

Close with the next-steps decision tree

Included in the output template above. Customize the options to what the redraft actually produced — if the rule status is unverified, option 2 (get more info) moves up; if the policy owner isn't set, option 3 (escalate) gets specific.

What this skill does not do

  • Apply the redraft to the source policy. That's the policy owner's action.
  • Close the gap in the tracker. Gaps close when the redraft is applied and approved.
  • Rewrite the whole policy. Smallest-possible edit to close the gap.
  • Produce multi-policy redrafts. One gap, one policy, one memo. A :package command for multi-policy fan-out is a future skill.
  • Produce the "apply" workflow. An :apply command with an approval gate is a future skill.

© anthropics, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in regulatory-legal/skills/policy-redraft of anthropics/claude-for-legal.

Open the folder on GitHubat commit 4a6c651

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in anthropics/claude-for-legal, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Policy Redraft next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Policy Redraft compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Policy Redraft this skillanthropics/claude-for-legal9.6k2 repos~3.5kAutomated safety check: PassApache-2.0
Paper to Chinese Patent DrafterYuan1z0825/nature-skills47k1 repos~1.1kAutomated safety check: PassApache-2.0
C15tc15t/c15t1.9k1 repos~1.6kAutomated safety check: PassApache-2.0
Contract Reviewevolsb/claude-legal-skill4641 repos~3.6kAutomated safety check: PassMIT
Paper To Cn Patentsnipp-zha/Paper-to-patent-Skill1071 repos~959Automated safety check: PassNone
Employment Contract Templatesynulihao/AgentSkillOS61812 repos~4.1kAutomated safety check: PassNone

Similar skills

  • Paper to Chinese Patent Drafter

    Yuan1z0825/nature-skills

    Drafts Chinese invention patent applications and technical disclosures from research papers or inventor materials, tying each claim feature to source evidence.

    47k GitHub starsUsed in 1 repo~1.1k tokens
    Legal & ComplianceAuto-check passed

  • C15t

    c15t/c15t

    Work with c15t consent management docs, APIs, and integrations for Next.js, React, and JavaScript.

    1.9k GitHub starsUsed in 1 repo~1.6k tokens
    Legal & ComplianceAuto-check passed

  • Contract Review

    evolsb/claude-legal-skill

    Review legal contracts, NDAs, employment agreements, SaaS terms, and M&A documents.

    464 GitHub starsUsed in 1 repo~3.6k tokens
    Legal & ComplianceAuto-check passed

  • Paper To Cn Patent

    snipp-zha/Paper-to-patent-Skill

    Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts.

    107 GitHub starsUsed in 1 repo~959 tokens
    Legal & ComplianceAuto-check passed

  • Employment Contract Templates

    ynulihao/AgentSkillOS

    Create employment contracts, offer letters, and HR policy documents following legal best practices.

    618 GitHub starsUsed in 12 repos~4.1k tokens
    Legal & ComplianceAuto-check passed

  • Commercial Legal Pl

    apiotrowski-afk/commercial-legal-pl

    Skill do analizy i tworzenia umów według polskiego prawa, ze szczególnym uwzględnieniem umów B2B, IP i IT (body leasing, NDA, wdrożenia, SaaS, przeniesienie praw autorskich, ugody).

    176 GitHub starsUsed in 1 repo~4.1k tokens
    Legal & ComplianceAuto-check passed

More from anthropics/claude-for-legal

All 147 skills in this repo

  • Legal Clinic Client Intake

    anthropics/claude-for-legal

    Official

    Structures a legal clinic client intake interview and produces a case summary with cross-area issue spotting, conflict flags and triage classification.

    9.6k GitHub starsUsed in 3 repos~3.2k tokens
    Auto-check passed

  • Supervisor Review Queue

    anthropics/claude-for-legal

    Official

    Holds student work in a queue for a legal clinic professor to approve, edit-then-approve or return before anything reaches clients or courts.

    9.6k GitHub starsUsed in 3 repos~1.1k tokens
    Auto-check passed

  • Tabular Document Review

    anthropics/claude-for-legal

    Official

    Builds a review grid with one row per document and one column per data point, each cell cited to a verbatim quote, built for M&A diligence and other batch reviews.

    9.6k GitHub starsUsed in 3 repos~4.3k tokens
    Auto-check passed

  • Product Launch Legal Review

    anthropics/claude-for-legal

    Official

    Runs a category-by-category legal review of a product launch from a PRD or tracker ticket, calibrated to your team's framework, and writes a review memo in house format.

    9.6k GitHub starsUsed in 2 repos~5k tokens
    Auto-check passed

  • Legal Skills Registry Browser

    anthropics/claude-for-legal

    Official

    Searches watched registries for community legal skills, shows matches with descriptions and offers the full SKILL.md before anything is installed.

    9.6k GitHub starsUsed in 2 repos~620 tokens
    Auto-check passed

  • Contract Renewal Tracker

    anthropics/claude-for-legal

    Official

    Shows which contracts renew soon and when notice must be sent by, working from a maintained renewal register, and warns about missed cancellation windows.

    9.6k GitHub starsUsed in 2 repos~3.1k tokens
    Auto-check passed

Categories

Questions about Policy Redraft

What does Policy Redraft do?

Produce a proposed marked-up policy redraft that closes a gap found by /regulatory-legal:gaps or /regulatory-legal:policy-diff. Policy Redraft is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Produce a proposed marked-up policy redraft that closes a gap found by /regulatory-legal:gaps or /regulatory-legal:policy-diff.

When should I use Policy Redraft?

Policy Redraft fits situations like: the user says redraft the policy; draft the policy fix; mark up the policy; gap-surfacer hands off a gap for drafting.

How do I install Policy Redraft in Claude Code?

Run `npx skills add anthropics/claude-for-legal --skill policy-redraft -a claude-code`. Or copy the skill folder (regulatory-legal/skills/policy-redraft in anthropics/claude-for-legal) into .claude/skills/policy-redraft in your project. Claude Code loads it when a task matches its description.

How do I install Policy Redraft in Codex?

Run `npx skills add anthropics/claude-for-legal --skill policy-redraft -a codex`. Or copy the skill folder (regulatory-legal/skills/policy-redraft in anthropics/claude-for-legal) into .agents/skills/policy-redraft in your project. Codex loads it when a task matches its description.

Can I use Policy Redraft in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add anthropics/claude-for-legal --skill policy-redraft -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/policy-redraft, .gemini/skills/policy-redraft, .github/skills/policy-redraft and .opencode/skills/policy-redraft in your project.

What does Policy Redraft need to run?

SKILL.md names no scripts, command-line tools or credentials: Policy Redraft is instructions for the agent only.

Does Policy Redraft access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Policy Redraft safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Policy Redraft use?

Policy Redraft is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Policy Redraft use?

About 3.5k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Policy Redraft?

Skills that share tags, products or a category with Policy Redraft: Paper to Chinese Patent Drafter (Yuan1z0825/nature-skills, 47k stars), C15t (c15t/c15t, 1.9k stars), Contract Review (evolsb/claude-legal-skill, 464 stars) and Paper To Cn Patent (snipp-zha/Paper-to-patent-Skill, 107 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Policy Redraft?

anthropics (a GitHub organization, an official publisher) maintains it in anthropics/claude-for-legal, which has 9,633 GitHub stars. The repository holds 147 skills in this directory. The repository was last updated on September 29, 2026.

Source: anthropics/claude-for-legal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.