Contract Clause Extractor logo

Contract Clause Extractor

Organization
Amazon-Quick
contract-clause-extractor

Extracts, classifies, and risk-scores key clauses from contracts and legal agreements. Identifies standard vs non-standard terms, flags high-risk provisions (unlimited liability, broad indemnification, auto-renewal), and produces structured clause inventories with plain-language summaries. Use when asked to 'review this contract', 'extract key clauses', 'flag risky terms', 'contract risk assessment', 'what are the key provisions', or 'summarize this agreement'.

Overview

PublisherAmazon-Quick
RepositoryAmazon-Quick-official-catalog
Skill namecontract-clause-extractor
Stars
50
Forks
4
Bundled files
1
LicenseMIT-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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Amazon-Quick on GitHub. Read the source before you install it.

Installation

Install the Contract Clause Extractor 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/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/legal/contract-clause-extractor
  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/Amazon-Quick/Amazon-Quick-official-catalog.git /tmp/Amazon-Quick-official-catalog
mkdir -p .claude/skills
cp -r /tmp/Amazon-Quick-official-catalog/skills/legal/contract-clause-extractor .claude/skills/contract-clause-extractor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Contract Clause Extractor 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 Clause Extractor 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 Clause Extractor 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.

Overview

Reads a contract document, extracts individual clauses by category, assigns risk scores with reasoning, and produces a structured inventory report. Every extraction preserves exact original language alongside a plain-language summary. This is an informational tool only and does not constitute legal advice.

Workflow

<Definition - Risk Levels> Each extracted clause receives one of four risk ratings:

  • Standard: Language consistent with market norms for this contract type. No action needed beyond awareness.
  • Notable: Slightly outside typical terms but not inherently problematic. Worth flagging for review during negotiation.
  • High-Risk: Materially one-sided or imposes significant obligations. Requires legal review before signing. Examples: unlimited liability, broad indemnification with no cap, unilateral amendment rights.
  • Critical: Provisions that could expose the party to severe financial, operational, or legal consequences. Immediate legal counsel required. Examples: personal guarantee language, waiver of jury trial combined with inconvenient venue, uncapped consequential damages. </Definition - Risk Levels>

<Definition - Common Clause Types> The standard taxonomy for clause classification:

  • Liability: Limitation of liability, liability caps, exclusions of damages
  • Indemnification: Hold harmless, defense obligations, indemnity triggers and carve-outs
  • Termination: Term length, renewal conditions, termination for cause, termination for convenience, cure periods
  • Payment: Pricing, payment terms, late fees, price escalation, audit rights
  • Confidentiality: Definition of confidential information, exclusions, duration, permitted disclosures
  • Intellectual Property: Ownership, assignments, licenses, work product, pre-existing IP
  • Data and Privacy: Data handling, breach notification, compliance obligations, data retention
  • Non-compete/Non-solicit: Scope, duration, geographic limitations
  • Governing Law and Dispute Resolution: Jurisdiction, venue, arbitration, choice of law
  • Force Majeure: Triggering events, notice requirements, termination rights during force majeure
  • Representations and Warranties: Scope, survival periods, knowledge qualifiers
  • Assignment: Consent requirements, change of control provisions
  • Insurance: Coverage requirements, minimum limits, additional insured
  • Auto-renewal: Notice periods, opt-out mechanics, renewal term length </Definition - Common Clause Types>

<Definition - Plain-Language Summary> Each clause extraction includes a summary written in accessible language. Requirements:

  • Maximum 2 sentences
  • No legal jargon unless defining it in parentheses
  • State who bears the obligation and what the practical consequence is
  • Avoid hedging language; be direct about what the clause does
  • Example: "If the vendor's software causes you a loss, the most you can recover is what you paid in the last 12 months. Losses from lost profits or data are excluded entirely." </Definition - Plain-Language Summary>

<Workflow - Contract Clause Extraction description="End-to-end contract analysis producing a structured clause inventory with risk scores." tools=[file_read, file_read_pdf, file_write, run_python, open_in_session_tab] triggers=["review this contract", "extract key clauses", "flag risky terms", "contract risk assessment", "what are the key provisions", "summarize this agreement", "analyze this contract"]

  1. [Agent] Read the contract document using the appropriate file reader based on format (file_read_pdf for PDFs, file_read for text/DOCX). If the document exceeds 10,000 characters, read in chunks using offset pagination until the full text is captured. Validate that the content is readable and appears to be a legal agreement. If fails: if the file cannot be opened or read in any supported format, report the specific error to the user and ask for a valid document before continuing.

  2. [Decide] Assess document quality:

    • If the text is garbled, heavily redacted, or clearly incomplete, stop and inform the user per Rule 12.
    • If the document is readable, proceed to Step 3.
  3. [Think] Identify the contract structure: parties involved, effective date, defined terms section, and overall organization (numbered sections, articles, exhibits). Build a mental map of how sections cross-reference each other. Note the governing law provision if present.

  4. [Agent] Extract all defined terms from the definitions section (or inline definitions throughout). Build a lookup table mapping each term to its definition. Flag any definitions that are unusually broad or that incorporate external references (e.g., "as defined in Provider's Acceptable Use Policy, available at..."). If fails: if no definitions section is found, note that terms are defined inline or absent and proceed, flagging that scope resolution may be incomplete.

  5. [Think] Scan the full document and identify each material clause. For each clause:

    • Classify it using the Common Clause Types taxonomy
    • Record the exact section reference and verbatim text
    • Resolve any defined terms to assess actual scope
    • Check for cross-references that modify or limit the clause
    • Check for "notwithstanding" language that creates priority
  6. [Think] Score each extracted clause against the Risk Levels scale. For each score, document:

    • The specific language that drives the rating
    • How defined terms affect the assessment (if applicable)
    • Whether cross-references or survival clauses amplify or mitigate risk
    • Comparison to market standard for the identified contract type Also identify missing standard protections (e.g., no liability cap, no termination for convenience, no data breach notification requirement) and score those gaps.
  7. [Agent] Generate the clause inventory report using the Clause Inventory Report template. Populate all sections. Sort findings within each risk level by clause type for readability. If fails: report which section could not be populated and stop rather than delivering a partial report without disclosure.

  8. [Ask user] Present a summary of findings: total clauses extracted, count by risk level, and the top 3-5 highest-risk items with their plain-language summaries. Ask if the user wants the full report, wants to drill into specific clauses, or wants to adjust focus areas. If fails: if the user does not respond or the request is unclear, default to offering the full report and ask them to confirm.

  9. [Agent] Based on user response, either deliver the full report (save via file_write and open with open_in_session_tab), provide detailed analysis of requested clauses, or re-run with adjusted focus areas. If fails: if saving or opening the report fails, present the report inline in the session and report the error.

  10. [Agent] Append the closing disclaimer per Rule 1. Confirm that the analysis is complete and recommend next steps (legal review for high-risk items, negotiation points for notable items). If fails: if the disclaimer cannot be appended to the saved file, state the disclaimer directly to the user so it is not omitted.

</Workflow - Contract Clause Extraction>

<Template - Clause Inventory Report>

markdown
# Contract Clause Analysis Report

**DISCLAIMER: This analysis is for informational purposes only and does not constitute legal advice. Consult qualified legal counsel before making decisions based on these findings.**

## Document Summary

| Field | Value |
|-------|-------|
| Document | {{document_name}} |
| Contract Type | {{contract_type}} |
| Parties | {{party_a}} / {{party_b}} |
| Effective Date | {{effective_date}} |
| Governing Law | {{governing_law}} |
| Analysis Date | {{analysis_date}} |
| Focus Areas | {{focus_areas}} |

## Risk Summary

| Risk Level | Count |
|------------|-------|
| Critical | {{critical_count}} |
| High-Risk | {{high_risk_count}} |
| Notable | {{notable_count}} |
| Standard | {{standard_count}} |

## Critical Findings

{{#each critical_findings}}
### {{clause_type}} - Section {{section_ref}}

**Risk Level:** Critical

**Original Text:**
> {{verbatim_text}}

**Plain-Language Summary:** {{plain_language_summary}}

**Risk Reasoning:** {{risk_reasoning}}

**Recommendation:** {{recommendation}}

---
{{/each}}

## High-Risk Findings

{{#each high_risk_findings}}
### {{clause_type}} - Section {{section_ref}}

**Risk Level:** High-Risk

**Original Text:**
> {{verbatim_text}}

**Plain-Language Summary:** {{plain_language_summary}}

**Risk Reasoning:** {{risk_reasoning}}

**Recommendation:** {{recommendation}}

---
{{/each}}

## Notable Findings

{{#each notable_findings}}
### {{clause_type}} - Section {{section_ref}}

**Risk Level:** Notable

**Original Text:**
> {{verbatim_text}}

**Plain-Language Summary:** {{plain_language_summary}}

**Risk Reasoning:** {{risk_reasoning}}

---
{{/each}}

## Standard Clauses

{{#each standard_findings}}
- **{{clause_type}}** (Section {{section_ref}}): {{plain_language_summary}}
{{/each}}

## Missing Protections

{{#each missing_protections}}
- **{{protection_type}}:** {{explanation}} (Risk Level: {{risk_level}})
{{/each}}

## Defined Terms of Note

{{#each notable_definitions}}
- **"{{term}}":** {{definition_summary}}  - {{risk_note}}
{{/each}}

## Next Steps

1. Engage legal counsel to review all Critical and High-Risk findings before signing.
2. Prepare negotiation positions for Notable findings if terms are negotiable.
3. Confirm that missing protections are acceptable or request their inclusion.

**This report does not represent a complete legal review. Additional provisions, implications, or risks may exist that are not captured here.**

</Template - Clause Inventory Report>

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Contract Clause Extractor AI skill do?

Extracts, classifies, and risk-scores key clauses from contracts and legal agreements. Identifies standard vs non-standard terms, flags high-risk provisions (unlimited liability, broad indemnification, auto-renewal), and produces structured clause inventories with plain-language summaries. Use when asked to 'review this contract', 'extract key clauses', 'flag risky terms', 'contract risk assessment', 'what are the key provisions', or 'summarize this agreement'.

Why use Contract Clause Extractor on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/legal/contract-clause-extractor. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Contract Clause Extractor?

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 Clause Extractor?

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

Is the Contract Clause Extractor AI skill free?

Yes. It is published on GitHub by Amazon-Quick under the MIT-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 👇