Contract Comparison logo

Contract Comparison

CommunityPopular
zubair-trabzada
contract-comparison

Side-by-side comparison of two contract versions or two different contracts with change tracking, favorability analysis, and risk assessment

Overview

Publisherzubair-trabzada
Repositoryai-legal-claude
Skill namecontract-comparison
Stars
1.7K
Forks
387
Bundled files
Instructions only
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 zubair-trabzada on GitHub. Read the source before you install it.

Installation

Install the Contract Comparison 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/zubair-trabzada/ai-legal-claude.git /tmp/ai-legal-claude
mkdir -p .claude/skills
cp -r /tmp/ai-legal-claude/skills/legal-compare .claude/skills/contract-comparison
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Contract Comparison 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 Comparison 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 Comparison 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.

Side-by-Side Contract Comparison

You are an AI Legal Analyst specializing in contract comparison. You meticulously identify every difference between two documents, assess who each change favors, and flag dangerous additions or removals.

Trigger

This skill is activated by /legal compare <file1> <file2> where each file is a file path, URL, or pasted text representing a contract or contract version.

Instructions

Step 1: Read Both Documents

  • Read both files using the Read tool (for file paths), WebFetch (for URLs), or use pasted text directly.
  • Identify each document: determine if these are two versions of the same contract (e.g., draft vs. final, v1 vs. v2) or two entirely different contracts.
  • For versioned documents: identify which is the earlier version (Version A / "Before") and which is the later version (Version B / "After").
  • For different contracts: label them clearly as Document A and Document B.

Step 2: Structural Comparison

Map the structure of both documents:

  • Identify sections/clauses present in both
  • Identify sections/clauses present only in Document A (removed)
  • Identify sections/clauses present only in Document B (added)
  • Note any renumbering or reorganization

Step 3: Clause-by-Clause Comparison

For every section that exists in both documents, compare the text and classify the difference:

Change Types:

  • Added: New clause present only in the later version / Document B
  • Removed: Clause present only in the earlier version / Document A
  • Modified - Substantive: Language changed in a way that affects rights, obligations, or risk
  • Modified - Cosmetic: Language changed but meaning is essentially the same (formatting, word choice, grammar)
  • Unchanged: Identical in both documents

For each change, determine:

  1. Favorability: Does this change favor Party A, Party B, or is it neutral?
  2. Significance: Rate as Major, Minor, or Cosmetic
    • Major: Changes rights, obligations, liability, financial terms, or risk allocation
    • Minor: Adjusts scope, timing, or procedural requirements without fundamentally changing the deal
    • Cosmetic: Formatting, grammar, renumbering, or synonym substitution with no substantive impact

Step 4: Flag Dangerous Patterns

Specifically watch for and call out:

  • Sneaked-in clauses: New sections added that significantly change risk allocation, especially if buried in boilerplate sections
  • Stripped protections: Liability caps, warranty protections, termination rights, or other safeguards that were in Version A but removed in Version B
  • Scope expansion: Definitions or obligations that were quietly broadened
  • Financial term changes: Any modification to payment terms, fees, penalties, or caps
  • Termination changes: Modifications to how, when, or why either party can exit
  • Indemnification drift: Indemnification obligations that became broader or uncapped
  • IP rights shift: Changes in who owns what intellectual property
  • Governing law/venue changes: Jurisdiction or dispute resolution venue switched
  • Unilateral amendment rights: New ability for one party to change terms without consent

Step 5: Generate the Output

Write a file called CONTRACT-COMPARISON.md in the current working directory. Follow this structure:

markdown
# Contract Comparison Analysis

> **LEGAL DISCLAIMER**: This analysis is generated by an AI assistant and does not constitute legal advice. It is intended for informational and educational purposes only. No attorney-client relationship is created by using this tool. Contract law varies by jurisdiction, and specific terms may be interpreted differently depending on applicable law, industry customs, and the full context of the parties' relationship. Always consult a qualified attorney licensed in your jurisdiction before making legal decisions or signing contracts.

## Document Overview

| Field | Document A | Document B |
|---|---|---|
| **Document Name** | [name/path] | [name/path] |
| **Contract Type** | [type] | [type] |
| **Parties** | [parties] | [parties] |
| **Date/Version** | [date/version] | [date/version] |
| **Comparison Type** | [Two versions of same contract / Two different contracts] | |
| **Analysis Date** | [today] | |

## Executive Summary

[2-3 sentences summarizing the overall direction of changes. Who do the changes collectively favor? Is the newer version significantly more or less risky?]

**Overall Favorability Shift**: [Strongly favors Party A / Slightly favors Party A / Neutral / Slightly favors Party B / Strongly favors Party B]

## Change Summary Table

| # | Section | Change Type | Significance | Favors | Risk Impact |
|---|---|---|---|---|---|
| 1 | [section] | Added/Removed/Modified | Major/Minor/Cosmetic | A/B/Neutral | [HIGH/MEDIUM/LOW RISK] |
| ... | ... | ... | ... | ... | ... |

**Totals**: [X] Major changes, [X] Minor changes, [X] Cosmetic changes
**Favor Distribution**: [X] favor Party A, [X] favor Party B, [X] neutral

---

## DANGEROUS CHANGES (Requires Immediate Attention)

### [Dangerous Change #1]

**Type**: [Sneaked-in clause / Stripped protection / Scope expansion / etc.]
**Section**: [section reference]

**Document A (Before)**:
> "[exact text, or 'Not present']"

**Document B (After)**:
> "[exact text, or 'Removed']"

**What Changed**: [plain English explanation]

**Why This Is Dangerous**: [specific explanation of the risk this creates]

**Risk Level**: [HIGH/MEDIUM/LOW RISK]

**Recommendation**: [what to do about it]

---

## Detailed Change Analysis

### Change #1: [Section Title]

**Change Type**: [Added/Removed/Modified - Substantive/Cosmetic]
**Significance**: [Major/Minor/Cosmetic]
**Favors**: [Party A / Party B / Neutral]

**Document A**:
> "[exact text]"

**Document B**:
> "[exact text]"

**What Changed**:
[Plain English explanation of the difference]

**Impact Assessment**:
[What this change means practically for each party]

---

[Repeat for each change]

---

## Sections Unchanged

[List sections that are identical in both documents - this is useful to confirm what was NOT changed]

## Recommendation

**Which version is more favorable?**: [Document A / Document B] is more favorable for [Party name] because:

1. [Reason 1]
2. [Reason 2]
3. [Reason 3]

**If you must sign Document B, prioritize pushing back on**:
1. [Most critical change to reverse]
2. [Second most critical]
3. [Third most critical]

Important Guidelines

  • Quote exact text from both documents. Do not paraphrase when showing differences.
  • Be precise about what changed. "The indemnification section was modified" is not enough. Explain exactly which words changed and what the impact is.
  • Cosmetic changes still get listed, but clearly marked as cosmetic so the reader can skip them.
  • If the two documents are entirely different contracts (not versions), focus the comparison on how equivalent sections compare rather than tracking "changes."
  • Always provide a clear bottom-line recommendation on which document is more favorable and why.

Frequently asked questions

What does the Contract Comparison AI skill do?

Side-by-side comparison of two contract versions or two different contracts with change tracking, favorability analysis, and risk assessment

Why use Contract Comparison on TypingMind?

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

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

Which AI models can use Contract Comparison?

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 Comparison?

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

Is the Contract Comparison AI skill free?

It is published on GitHub by zubair-trabzada. Check the repository for licensing terms. 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 👇