Contract Redline logo

Contract Redline

Organization
vm0-ai
contract-redline

Review commercial contracts against a playbook, flag risk, and draft redlines or fallback language.

Overview

Publishervm0-ai
Repositoryvm0-skills
Skill namecontract-redline
Stars
76
Forks
18
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 vm0-ai on GitHub. Read the source before you install it.

Installation

Install the Contract Redline 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/vm0-ai/vm0-skills.git /tmp/vm0-skills
mkdir -p .claude/skills
cp -r /tmp/vm0-skills/contract-redline .claude/skills/contract-redline
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Contract Redline 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 Redline 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 Redline 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.

Pre-Review Setup

Organizational Playbook

Before any analysis begins, look for a negotiation playbook configured in the user's local settings. A playbook codifies the organization's preferred positions, tolerable bands, and hard limits for every major provision category.

When no playbook exists:

  • Propose building one collaboratively with the user
  • If the user wants to proceed immediately, anchor the analysis to mainstream commercial norms as your reference point

Contextual Framing

Every review must start by establishing three things:

  1. Agreement category -- Determine whether this is a SaaS subscription, professional services engagement, software license, channel partnership, procurement arrangement, or another structure. The category dictates which provisions carry the most weight.
  2. Client posture -- Establish whether the organization sits on the buying side, selling side, licensing side, or partnership side. Protective language that benefits one party harms the other.
  3. Holistic reading -- Read the entire document end-to-end before marking up any single provision. Provisions operate as an interconnected system. An aggressive indemnity clause may be counterbalanced by a strong liability cap elsewhere.

Provision-by-Provision Analysis

Liability Caps and Damage Exclusions

What to examine:

  • Total cap structure: fixed dollar figure, fee multiple, or absence of any ceiling
  • Symmetry of the cap between the parties
  • Exceptions carved out from the cap and which party they favor
  • Whether indirect, consequential, special, and punitive damages are waived
  • Mutuality of the damages waiver
  • Exceptions to the damages waiver
  • Cap measurement window: per-incident, annual, or lifetime aggregate

Typical problems:

  • Cap pegged to a small fraction of fees (for example, three months of spend on a modest-value deal)
  • One-sided exceptions that hollow out the cap for the drafter's benefit
  • Sweeping exception language like "any breach of this Agreement" that renders the cap meaningless
  • Asymmetric damages waiver leaving one party exposed to consequential loss claims

Indemnification Provisions

What to examine:

  • Reciprocity: does each side indemnify the other, or is it one-directional
  • Triggering events: IP infringement, data incidents, personal injury, warranty breaches
  • Relationship to the liability cap: subject to cap, partially capped, or unlimited
  • Procedural mechanics: timely notice, who controls the defense, settlement authority
  • Duty of the protected party to minimize harm
  • Survival period after the agreement ends

Typical problems:

  • One-directional IP indemnification when both parties contribute intellectual property
  • Catch-all "any breach" triggers that effectively eliminate the liability ceiling
  • No right for the indemnifying party to direct the legal defense
  • Open-ended survival with no time boundary

Intellectual Property Rights

What to examine:

  • Background IP ownership: each party must retain what they brought in
  • Foreground IP: who owns work product created during the engagement
  • Work-for-hire designations and whether their reach is proportionate
  • License grants: breadth, exclusivity, geographic scope, sublicense rights
  • Open source exposure
  • Feedback provisions that grant rights over suggestions or improvements

Typical problems:

  • Overbroad assignment language that could sweep in the customer's pre-existing assets
  • Work-for-hire clauses extending well beyond the specific deliverables
  • Perpetual, irrevocable feedback licenses with no practical limit
  • License scope that exceeds what the business relationship actually requires

Data Protection Provisions

What to examine:

  • Whether a Data Processing Agreement or Addendum is needed and present
  • Controller/processor role allocation
  • Sub-processor engagement rights and change-notification obligations
  • Breach reporting window (must enable the controller to satisfy the 72-hour GDPR deadline)
  • International transfer safeguards: Standard Contractual Clauses, adequacy findings, binding corporate rules
  • Data return or destruction duties upon contract end
  • Security standards and the controller's audit entitlements
  • Processing purpose restrictions

Typical problems:

  • Personal data in scope but no DPA attached
  • Unrestricted sub-processor authorization with no advance notice
  • Breach notification window that exceeds regulatory deadlines
  • No transfer protections for data crossing international borders
  • Vague or missing data deletion commitments

Duration, Renewal, and Exit

What to examine:

  • Length of the initial commitment and any renewal periods
  • Auto-renewal mechanics and the window for opting out
  • Convenience termination: availability, required notice, early exit penalties
  • Cause-based termination: what qualifies as cause, whether a cure window exists
  • Post-termination obligations: data handback, transition support, surviving provisions
  • Wind-down logistics and timeline

Typical problems:

  • Extended initial lock-in with no convenience exit
  • Auto-renewal paired with a narrow opt-out window (such as 30 days before an annual renewal)
  • Termination for cause with no opportunity to remedy the breach
  • Weak or nonexistent transition assistance language
  • Survival provisions that effectively perpetuate core obligations

Dispute Resolution and Governing Law

What to examine:

  • Applicable law and jurisdiction selection
  • Resolution pathway: courts, arbitration, mandatory mediation step
  • Litigation venue and personal jurisdiction
  • Arbitral institution, procedural rules, and seat (if arbitration applies)
  • Jury trial waiver
  • Class action waiver
  • Fee-shifting for the prevailing party

Typical problems:

  • Inconvenient or obscure venue selection
  • Compulsory arbitration under rules that advantage the drafter
  • Jury waiver without compensating procedural safeguards
  • No graduated escalation mechanism before formal proceedings

Deviation Rating System

GREEN -- Within Bounds

The provision matches or improves upon the organization's baseline position. Any variation is commercially sensible and does not meaningfully shift risk.

Illustrations:

  • Liability cap set at 18 months of fees when the baseline calls for 12 months (favorable to the buyer)
  • Mutual confidentiality term of 2 years against a 3-year baseline (shorter but reasonable)
  • Governing law in a reputable commercial jurisdiction near the preferred one

Response: Note for transparency. No negotiation warranted.

YELLOW -- Push Back

The provision sits outside the baseline but within a zone where negotiation is realistic. The position is seen in the market but is not the organization's preference. Warrants attention and discussion, though not immediate escalation.

Illustrations:

  • Liability cap at 6 months of fees against a 12-month baseline (below standard yet negotiable)
  • One-directional IP indemnification when the baseline is mutual (common but not preferred)
  • Auto-renewal opt-out of 60 days when the baseline is 90 days
  • Acceptable but non-preferred governing law jurisdiction

Response: Draft specific replacement language. Supply a fallback if the primary ask is refused. Estimate the business consequence of accepting the term as-is versus negotiating.

RED -- Escalate Immediately

The provision breaches the acceptable range, trips a defined escalation trigger, or introduces material exposure. Requires review by senior counsel, outside legal advisors, or a business decision-maker with sign-off authority.

Illustrations:

  • No liability cap at all, or no limitation of liability provision
  • Unilateral, uncapped, broadly-scoped indemnification
  • Assignment of the organization's background intellectual property
  • Personal data processing with no DPA offered
  • Unreasonable restrictive covenants or exclusivity demands
  • Hostile jurisdiction combined with mandatory arbitration

Response: Articulate the precise exposure. Offer market-standard replacement language. Quantify potential downside. Recommend the appropriate escalation path.

Crafting Effective Redlines

Principles for producing markup that advances the negotiation:

  1. Supply exact text -- Deliver language that can be inserted verbatim, not abstract guidance.
  2. Stay commercially reasonable -- Aggressive overreach slows deals. Be firm on critical protections and pragmatic elsewhere.
  3. Include professional rationale -- Attach a concise justification suitable for sharing with opposing counsel.
  4. Offer a Plan B -- For every YELLOW item, provide a secondary position in case the first request is declined.
  5. Rank by importance -- Signal which markups are essential and which are strategic asks.
  6. Match the relationship context -- Calibrate tone depending on whether the counterparty is a new vendor, a long-standing partner, or a commodity supplier.

Markup Format

Present each proposed change as follows:

**Provision**: [Section number and title]
**Existing text**: "[verbatim excerpt from the agreement]"
**Proposed replacement**: "[specific new language]"
**Justification**: [One to two sentences explaining the rationale, appropriate for external sharing]
**Importance**: [Essential / Strongly Preferred / Optional]
**Fallback**: [Alternative position if the primary request is declined]

Negotiation Prioritization

Organize all proposed markups into three tiers to guide negotiation strategy:

Tier 1 -- Non-Negotiable (Walk-Away Items)

Provisions where the organization cannot execute the agreement without resolution:

  • Absent or grossly inadequate liability protections
  • Missing data protection requirements for regulated information
  • IP terms that jeopardize core business assets
  • Clauses that conflict with the organization's regulatory obligations

Tier 2 -- High Priority (Strong Preferences)

Provisions that materially affect the risk profile but allow room for negotiation:

  • Liability cap adjustments within the acceptable band
  • Indemnification scope and reciprocity improvements
  • Flexibility around termination and exit rights
  • Audit, inspection, and compliance verification rights

Tier 3 -- Strategic Concessions (Trading Material)

Provisions that strengthen the position but can be yielded to secure more important wins:

  • Preferred governing law when the alternative is still acceptable
  • Notice period fine-tuning
  • Minor definitional refinements
  • Insurance documentation requirements

Negotiation approach: Open with Tier 1 demands. Offer Tier 3 concessions as currency to lock in Tier 2 outcomes. Never yield on Tier 1 without escalating to authorized decision-makers.

Frequently asked questions

What does the Contract Redline AI skill do?

Review commercial contracts against a playbook, flag risk, and draft redlines or fallback language.

Why use Contract Redline on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vm0-ai/vm0-skills/tree/main/contract-redline. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Contract Redline?

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 Redline?

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

Is the Contract Redline AI skill free?

It is published on GitHub by vm0-ai. 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 👇