Contract Review logo

Contract Review

Community
shawnpang
contract-review

When the user needs to review an existing contract, assess risk in proposed terms, or evaluate a contract before signing.

Overview

Publishershawnpang
Repositorystartup-founder-skills
Skill namecontract-review
Stars
368
Forks
43
Bundled files
Instructions only
LicenseMIT
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 shawnpang on GitHub. Read the source before you install it.

Installation

Install the Contract Review 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.
    https://github.com/shawnpang/startup-founder-skills/tree/main/skills/contract-review
  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/shawnpang/startup-founder-skills.git /tmp/startup-founder-skills
mkdir -p .claude/skills
cp -r /tmp/startup-founder-skills/skills/contract-review .claude/skills/contract-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Contract 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 Contract 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 Contract 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.

Contract Review

When to Use

Activate when a founder has received a contract to sign and wants to understand the risks before proceeding. This includes vendor agreements, customer enterprise agreements, partnership deals, investment documents, employment agreements, NDAs, IP assignment agreements, and any other binding legal document. Also activate when the user says things like "review this contract," "is this agreement fair," "what should I push back on," or "flag anything concerning."

Context Required

  • From startup-context: company stage, team size, business model, fundraising status, current revenue, and any existing legal counsel.
  • From the user: the contract text (or key sections), who the counterparty is, the business relationship context (are they a customer, vendor, investor, partner), the user's negotiating leverage, and any specific concerns they have. Also helpful: whether this is a template/standard agreement or has been negotiated.

Workflow

  1. Contract intake — Receive the contract text. Identify the contract type, parties, effective date, and term. Create a one-paragraph summary of what the contract does.
  2. Section-by-section analysis — Walk through each major section, summarizing what it means in plain language and flagging anything noteworthy.
  3. Risk flagging — Apply the red/yellow/green flagging system (see below) to each clause. Assign a severity and explain why.
  4. Missing protections — Identify standard protections that are absent from the contract but should be present given the contract type and relationship.
  5. Negotiation recommendations — For each red and yellow flag, suggest specific alternative language or a negotiation strategy.
  6. Summary report — Produce a structured risk assessment with prioritized action items.

Output Format

Contract Summary (top of report)

  • Contract type: (e.g., SaaS vendor agreement, MSA, NDA)
  • Parties: Company name vs. counterparty name
  • Term: Duration, renewal mechanism
  • Total value: Financial commitment if applicable
  • Overall risk level: Red / Yellow / Green with one-sentence rationale

Clause-by-Clause Analysis Table

SectionSummaryFlagRiskRecommended Action
Liability CapCapped at fees paid in prior 6 monthsYellowLow cap for potential damagesNegotiate to 12-month cap
IP AssignmentBroad assignment of all work productRedCould capture pre-existing IPAdd carve-out for pre-existing IP

Missing Protections Checklist

Bulleted list of protections that should be present but are not.

Prioritized Action Items

Numbered list of what to do, in order of importance.

Frameworks & Best Practices

The Red/Yellow/Green Flagging System

Red Flags — Immediate concern, do not sign without modification:

  • Unlimited liability or liability cap below a reasonable threshold
  • Broad IP assignment that could capture pre-existing IP or IP unrelated to the engagement
  • Non-compete clauses that are overly broad in scope, geography, or duration
  • Unilateral termination rights without cure period for one party only
  • Automatic renewal with no opt-out window or unreasonable notice requirements
  • Indemnification obligations that are uncapped or wildly asymmetric
  • Most-favored-nation clauses that constrain your pricing with other customers
  • Exclusivity provisions that limit your ability to work with competitors
  • Audit rights with unreasonable scope or no notice requirement
  • Governing law in an unfavorable or distant jurisdiction with no negotiation

Yellow Flags — Worth negotiating, but not necessarily deal-breakers:

  • Liability caps that are low relative to the contract value
  • Warranty periods or SLA credits that are below industry standard
  • Payment terms exceeding net-60
  • Change-of-control provisions that allow termination on acquisition
  • Broad confidentiality definitions with long or indefinite survival periods
  • Assignment restrictions that prevent assignment in an acquisition scenario
  • Force majeure clauses that are overly broad or favor one party
  • Data handling terms that are vague about deletion, portability, or sub-processors

Green Flags — Standard and reasonable:

  • Mutual confidentiality obligations
  • Balanced termination rights with cure periods
  • Liability capped at 12 months of fees paid
  • Standard representations and warranties
  • Clear payment terms (net-30)
  • Reasonable non-solicitation (employees only, 12 months)

Negotiation Principles

  • Symmetry first. Any obligation imposed on one party should apply to both unless there is a clear business reason for asymmetry.
  • Cap everything. Liability, indemnification, and damages should all have explicit caps.
  • Cure periods. Both parties should have the opportunity to fix a breach before termination.
  • Specificity over breadth. Narrow definitions protect both parties. "Confidential Information means everything" protects nothing.
  • Survival clarity. Specify exactly which clauses survive termination and for how long.

Related Skills

  • terms-of-service — When reviewing a customer's redlines to your terms of service, use contract-review to assess their proposed modifications.
  • privacy-policy — Data processing addendums and DPAs often accompany contracts. Review these for consistency with your privacy commitments.

Examples

Example 1: Reviewing a vendor SaaS agreement

User: "We're about to sign a contract with a data enrichment vendor. Here are the terms. Can you flag anything concerning?"

Good output excerpt:

Overall Risk Level: Yellow

The agreement is mostly standard but has three issues worth negotiating before signing.

SectionFlagIssue
4.2 Data RightsRedVendor claims a "perpetual, irrevocable license to use Customer Data for product improvement and benchmarking." This means they keep and use your data forever, even after termination. Negotiate to: license limited to providing the service, terminates on contract end, anonymization required for any aggregate use.
7.1 LiabilityYellowCap is set at "fees paid in the prior 3 months." For a $2K/month contract, that is a $6K cap. If they cause a data breach affecting your customers, your exposure could be much higher. Negotiate to: 12 months of fees, with a carve-out for uncapped liability on data breaches and IP infringement.
9.3 TerminationYellow90-day notice required to cancel, even on annual renewal. Combined with auto-renewal, this means you need to decide 3 months before your renewal date. Negotiate to: 30-day notice, or set a calendar reminder now.

Missing Protections:

  • No data deletion timeline after termination
  • No breach notification obligation
  • No sub-processor list or approval rights
  • No SLA or uptime commitment

Example 2: Reviewing an IP assignment in an employment agreement

User: "A new engineer's offer letter has an IP assignment clause. They're concerned about their open-source side projects. Can you review?"

Good output excerpt:

Section 8 — Invention Assignment: Red Flag

The current language reads: "Employee assigns to the Company all right, title, and interest in any invention, improvement, or work of authorship created during the term of employment."

This is overly broad. It captures the engineer's weekend open-source contributions, personal projects, and anything they create during employment regardless of whether it relates to company business.

Recommended revision: Add a carve-out: "...created during the term of employment that (a) relates to the Company's current or reasonably anticipated business, (b) was developed using Company resources, or (c) resulted from work performed for the Company."

Also add a Schedule A listing the engineer's pre-existing IP and active side projects, explicitly excluded from assignment. Note: California Labor Code Section 2870 already provides some protection, but an explicit carve-out is clearer and avoids disputes.


Disclaimer: This skill provides contract analysis for educational and planning purposes only. It does not constitute legal advice. Contract interpretation depends on jurisdiction-specific law, the full context of the business relationship, and facts that may not be apparent from the document alone. Always have a qualified attorney review contracts before signing, especially those involving significant financial commitments, IP rights, or liability exposure.

Frequently asked questions

What does the Contract Review AI skill do?

When the user needs to review an existing contract, assess risk in proposed terms, or evaluate a contract before signing.

Why use Contract Review on TypingMind?

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

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

Which AI models can use Contract 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 Contract Review?

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

Is the Contract Review AI skill free?

Yes. It is published on GitHub by shawnpang under the MIT 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 👇