Review

OrganizationPopular

anthropics

review

Review a vendor agreement, NDA, or SaaS subscription against your playbook. Identifies the agreement structure from titles, routes to the right review skill (vendor-agreement-review, nda-review, saas-msa-review), and integrates the output into a single memo. Use when the user says "review this contract", "check this MSA", "is this NDA okay", "look at this SaaS agreement", or attaches an inbound agreement for review.

Overview

Publisher	anthropics
Repository	`claude-for-legal`
Skill name	`review`
Stars	9.5K
Forks	1.8K
Bundled files	Instructions only
License	Apache-2.0
Links	Skill source Repository

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
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.

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/commercial-legal/skills/review .claude/skills/review

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Review 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 Review 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 Review 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.

/review

Reviews an inbound agreement against the playbook in ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md. Identifies the agreement structure from titles, selects the appropriate skill(s), and — if confirm_routing is enabled — checks with the user before proceeding.

Instructions

Load ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md. If placeholders present, stop and prompt: "Run /commercial-legal:cold-start-interview first — I need to learn your playbook before I can review against it."

Also read ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md → ## Review preferences → confirm_routing. If the field is missing, treat it as true.
Get the agreement: From file path, Drive link, [CLM ID], or pasted text. If none provided, ask.
Read the document structure — titles first.

Before reading the body, extract:
- The main agreement title (e.g., "Master Services Agreement", "Non-Disclosure Agreement")
- All exhibit, schedule, addendum, and attachment titles (e.g., "Exhibit A — Data Processing Addendum", "Schedule 1 — Subscription Order Form", "Annex B — Service Level Agreement")
This is the routing signal. Do not rely on body keywords alone — a 40-page MSA with "confidential" throughout is not an NDA.

Select the skill(s) based on document structure.

Map each identified document or section to a skill:

Document / section title contains	Skill
Non-Disclosure, NDA, Confidentiality Agreement (as the main agreement)	nda-review
Master Services Agreement, Professional Services, Statement of Work, Consulting Agreement	vendor-agreement-review
Subscription, SaaS, Cloud Services, Order Form with auto-renewal, Software License with recurring fees	saas-msa-review (overlay on vendor-agreement-review)
Data Processing Addendum, DPA, Data Processing Agreement (as exhibit or standalone)	note for vendor-agreement-review → data protection section
Service Level Agreement, SLA (as exhibit)	note for saas-msa-review → SLA section

Multiple skills may apply. Common combinations:

MSA + DPA exhibit → vendor-agreement-review, with DPA noted
SaaS subscription + Order Form + SLA exhibit → saas-msa-review (covers all three)
MSA + Order Form with auto-renewal → vendor-agreement-review + saas-msa-review overlay

When the structure is genuinely ambiguous after reading titles (e.g., a document titled "Agreement" with no exhibits listed), read the first two pages of the body to resolve it — then stop and route.

Confirm routing if enabled.

If confirm_routing is true in ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md (or field is absent):


I'm going to review this as: [agreement type(s)].

Documents identified:
- [Main agreement title] → [skill]
- [Exhibit A title] → [how it will be handled]
- [Exhibit B title] → [how it will be handled]

Sound right? (yes / no — or tell me what I got wrong)

Wait for confirmation before proceeding. If the user corrects the routing, apply their instruction and proceed.

If confirm_routing is false: proceed silently. Log the routing decision at the top of the review memo so the user can see what was applied.

Run the skill(s). Follow each skill's workflow fully. If multiple skills apply, run them in sequence and integrate the output into a single memo — don't produce separate memos.
Check for escalations: If any issue exceeds the reviewer's authority per the ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md matrix, invoke escalation-flagger to route and draft the ask.
Offer follow-ups:
- Stakeholder summary for the business owner
- Redline .docx with tracked changes
- [CLM] record creation (if connected)
- Add to renewal register (if auto-renewal found)

Configuring confirm_routing

Add to ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md → ## Review preferences:

markdown
## Review preferences

confirm_routing: true   # Set to false to skip routing confirmation and proceed automatically

The cold-start interview should ask about this preference. Default is true — confirmation on. As trust builds, the user can set it to false.

Examples


/commercial-legal:review vendor-msa.pdf


/commercial-legal:review https://drive.google.com/file/d/ABC123


/commercial-legal:review
[paste agreement text]

Output

Full review memo per the skill's format. Routing decision logged at the top. Deviation-by-deviation, specific redline language, named approver. Saved where ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md → House style says work product goes.

Frequently asked questions

What does the Review AI skill do?

Why use Review on TypingMind?

Because you install it once and use it with any model. Review 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 Review in TypingMind?

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

Which AI models can use Review?

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 Review?

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

Is the Review 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

Events

coreyhaines31

CommunityPopular

When the user wants to plan, run, sponsor, speak at, or get pipeline from events — webinars, conferences, trade shows, meetups, dinners, workshops, virtual summits, or user conferences. Also use when…

Advisor Orchestrator Worker

Shubhamsaboo

CommunityPopular

Use when a task is too large for one model pass, needs parallel research or generation across many subtasks (like researching a dozen competitors at once), or the user asks to orchestrate multiple…

Cavecrew

When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is…

Dashboard

Admin / analytics dashboard in a single HTML file. Fixed left sidebar, top bar with user/search, main grid of KPI cards and one or two charts. Use when the brief asks for a "dashboard", "admin",…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

/review

Instructions

Configuring confirm_routing

Examples

Output

Frequently asked questions

Related AI Skills

Set up your own AI workspace now