review-contract

Review a contract against your organization's negotiation playbook — flag deviations, generate redlines, provide business impact analysis. Use when reviewing vendor or customer agreements, when you need clause-by-clause analysis against standard positions, or when preparing a negotiation strategy with prioritized redlines and fallback positions.

10,671 stars

Best use case

review-contract is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Review a contract against your organization's negotiation playbook — flag deviations, generate redlines, provide business impact analysis. Use when reviewing vendor or customer agreements, when you need clause-by-clause analysis against standard positions, or when preparing a negotiation strategy with prioritized redlines and fallback positions.

Teams using review-contract should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/review-contract/SKILL.md --create-dirs "https://raw.githubusercontent.com/anthropics/knowledge-work-plugins/main/legal/skills/review-contract/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/review-contract/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How review-contract Compares

Feature / Agentreview-contractStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Review a contract against your organization's negotiation playbook — flag deviations, generate redlines, provide business impact analysis. Use when reviewing vendor or customer agreements, when you need clause-by-clause analysis against standard positions, or when preparing a negotiation strategy with prioritized redlines and fallback positions.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# /review-contract -- Contract Review Against Playbook

> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md).

Review a contract against your organization's negotiation playbook. Analyze each clause, flag deviations, generate redline suggestions, and provide business impact analysis.

**Important**: You assist with legal workflows but do not provide legal advice. All analysis should be reviewed by qualified legal professionals before being relied upon.

## Invocation

```
/review-contract <contract file or URL>
```

Review the contract: @$1

## Workflow

### Step 1: Accept the Contract

Accept the contract in any of these formats:
- **File upload**: PDF, DOCX, or other document format
- **URL**: Link to a contract in your CLM, cloud storage (e.g., Box, Egnyte, SharePoint), or other document system
- **Pasted text**: Contract text pasted directly into the conversation

If no contract is provided, prompt the user to supply one.

### Step 2: Gather Context

Ask the user for context before beginning the review:

1. **Which side are you on?** (vendor/supplier, customer/buyer, licensor, licensee, partner -- or other)
2. **Deadline**: When does this need to be finalized? (Affects prioritization of issues)
3. **Focus areas**: Any specific concerns? (e.g., "data protection is critical", "we need flexibility on term", "IP ownership is the key issue")
4. **Deal context**: Any relevant business context? (e.g., deal size, strategic importance, existing relationship)

If the user provides partial context, proceed with what you have and note assumptions.

### Step 3: Load the Playbook

Look for the organization's contract review playbook in local settings (e.g., `legal.local.md` or similar configuration files).

The playbook should define:
- **Standard positions**: The organization's preferred terms for each major clause type
- **Acceptable ranges**: Terms that can be agreed to without escalation
- **Escalation triggers**: Terms that require senior counsel review or outside counsel involvement

**If no playbook is configured:**
- Inform the user that no playbook was found
- Offer two options:
  1. Help the user set up their playbook (walk through defining positions for key clauses)
  2. Proceed with a generic review using widely-accepted commercial standards as the baseline
- If proceeding generically, clearly note that the review is based on general commercial standards, not the organization's specific positions

### Step 4: Clause-by-Clause Analysis

Apply the following review process:

1. **Identify the contract type**: SaaS agreement, professional services, license, partnership, procurement, etc. The contract type affects which clauses are most material.
2. **Determine the user's side**: Vendor, customer, licensor, licensee, partner. This fundamentally changes the analysis (e.g., limitation of liability protections favor different parties).
3. **Read the entire contract** before flagging issues. Clauses interact with each other (e.g., an uncapped indemnity may be partially mitigated by a broad limitation of liability).
4. **Analyze each material clause** against the playbook position.
5. **Consider the contract holistically**: Are the overall risk allocation and commercial terms balanced?

Analyze the contract systematically, covering at minimum:

| Clause Category | Key Review Points |
|----------------|-------------------|
| **Limitation of Liability** | Cap amount, carveouts, mutual vs. unilateral, consequential damages |
| **Indemnification** | Scope, mutual vs. unilateral, cap, IP infringement, data breach |
| **IP Ownership** | Pre-existing IP, developed IP, work-for-hire, license grants, assignment |
| **Data Protection** | DPA requirement, processing terms, sub-processors, breach notification, cross-border transfers |
| **Confidentiality** | Scope, term, carveouts, return/destruction obligations |
| **Representations & Warranties** | Scope, disclaimers, survival period |
| **Term & Termination** | Duration, renewal, termination for convenience, termination for cause, wind-down |
| **Governing Law & Dispute Resolution** | Jurisdiction, venue, arbitration vs. litigation |
| **Insurance** | Coverage requirements, minimums, evidence of coverage |
| **Assignment** | Consent requirements, change of control, exceptions |
| **Force Majeure** | Scope, notification, termination rights |
| **Payment Terms** | Net terms, late fees, taxes, price escalation |

For each clause, assess against the playbook (or generic standards) and note whether it is present, absent, or unusual.

#### Detailed Clause Guidance

##### Limitation of Liability

**Key elements to review:**
- Cap amount (fixed dollar amount, multiple of fees, or uncapped)
- Whether the cap is mutual or applies differently to each party
- Carveouts from the cap (what liabilities are uncapped)
- Whether consequential, indirect, special, or punitive damages are excluded
- Whether the exclusion is mutual
- Carveouts from the consequential damages exclusion
- Whether the cap applies per-claim, per-year, or aggregate

**Common issues:**
- Cap set at a fraction of fees paid (e.g., "fees paid in the prior 3 months" on a low-value contract)
- Asymmetric carveouts favoring the drafter
- Broad carveouts that effectively eliminate the cap (e.g., "any breach of Section X" where Section X covers most obligations)
- No consequential damages exclusion for one party's breaches

##### Indemnification

**Key elements to review:**
- Whether indemnification is mutual or unilateral
- Scope: what triggers the indemnification obligation (IP infringement, data breach, bodily injury, breach of reps and warranties)
- Whether indemnification is capped (often subject to the overall liability cap, or sometimes uncapped)
- Procedure: notice requirements, right to control defense, right to settle
- Whether the indemnitee must mitigate
- Relationship between indemnification and the limitation of liability clause

**Common issues:**
- Unilateral indemnification for IP infringement when both parties contribute IP
- Indemnification for "any breach" (too broad; essentially converts the liability cap to uncapped liability)
- No right to control defense of claims
- Indemnification obligations that survive termination indefinitely

##### Intellectual Property

**Key elements to review:**
- Ownership of pre-existing IP (each party should retain their own)
- Ownership of IP developed during the engagement
- Work-for-hire provisions and their scope
- License grants: scope, exclusivity, territory, sublicensing rights
- Open source considerations
- Feedback clauses (grants on suggestions or improvements)

**Common issues:**
- Broad IP assignment that could capture the customer's pre-existing IP
- Work-for-hire provisions extending beyond the deliverables
- Unrestricted feedback clauses granting perpetual, irrevocable licenses
- License scope broader than needed for the business relationship

##### Data Protection

**Key elements to review:**
- Whether a Data Processing Agreement/Addendum (DPA) is required
- Data controller vs. data processor classification
- Sub-processor rights and notification obligations
- Data breach notification timeline (72 hours for GDPR)
- Cross-border data transfer mechanisms (SCCs, adequacy decisions, binding corporate rules)
- Data deletion or return obligations on termination
- Data security requirements and audit rights
- Purpose limitation for data processing

**Common issues:**
- No DPA when personal data is being processed
- Blanket authorization for sub-processors without notification
- Breach notification timeline longer than regulatory requirements
- No cross-border transfer protections when data moves internationally
- Inadequate data deletion provisions

##### Term and Termination

**Key elements to review:**
- Initial term and renewal terms
- Auto-renewal provisions and notice periods
- Termination for convenience: available? notice period? early termination fees?
- Termination for cause: cure period? what constitutes cause?
- Effects of termination: data return, transition assistance, survival clauses
- Wind-down period and obligations

**Common issues:**
- Long initial terms with no termination for convenience
- Auto-renewal with short notice windows (e.g., 30-day notice for annual renewal)
- No cure period for termination for cause
- Inadequate transition assistance provisions
- Survival clauses that effectively extend the agreement indefinitely

##### Governing Law and Dispute Resolution

**Key elements to review:**
- Choice of law (governing jurisdiction)
- Dispute resolution mechanism (litigation, arbitration, mediation first)
- Venue and jurisdiction for litigation
- Arbitration rules and seat (if arbitration)
- Jury waiver
- Class action waiver
- Prevailing party attorney's fees

**Common issues:**
- Unfavorable jurisdiction (unusual or remote venue)
- Mandatory arbitration with rules favorable to the drafter
- Waiver of jury trial without corresponding protections
- No escalation process before formal dispute resolution

### Step 5: Flag Deviations

Classify each deviation from the playbook using a three-tier system:

#### GREEN -- Acceptable

The clause aligns with or is better than the organization's standard position. Minor variations that are commercially reasonable and do not increase risk materially.

**Examples:**
- Liability cap at 18 months of fees when standard is 12 months (better for the customer)
- Mutual NDA term of 2 years when standard is 3 years (shorter but reasonable)
- Governing law in a well-established commercial jurisdiction close to the preferred one

**Action**: Note for awareness. No negotiation needed.

#### YELLOW -- Negotiate

The clause falls outside the standard position but within a negotiable range. The term is common in the market but not the organization's preference. Requires attention and likely negotiation, but not escalation.

**Examples:**
- Liability cap at 6 months of fees when standard is 12 months (below standard but negotiable)
- Unilateral indemnification for IP infringement when standard is mutual (common market position but not preferred)
- Auto-renewal with 60-day notice when standard is 90 days
- Governing law in an acceptable but not preferred jurisdiction

**Action**: Generate specific redline language. Provide fallback position. Estimate business impact of accepting vs. negotiating.
- **Include**: Specific redline language to bring the term back to standard position
- **Include**: Fallback position if the counterparty pushes back
- **Include**: Business impact of accepting as-is vs. negotiating

#### RED -- Escalate

The clause falls outside acceptable range, triggers a defined escalation criterion, or poses material risk. Requires senior counsel review, outside counsel involvement, or business decision-maker sign-off.

**Examples:**
- Uncapped liability or no limitation of liability clause
- Unilateral broad indemnification with no cap
- IP assignment of pre-existing IP
- No DPA offered when personal data is processed
- Unreasonable non-compete or exclusivity provisions
- Governing law in a problematic jurisdiction with mandatory arbitration

**Action**: Explain the specific risk. Provide market-standard alternative language. Estimate exposure. Recommend escalation path.
- **Include**: Why this is a RED flag (specific risk)
- **Include**: What the standard market position looks like
- **Include**: Business impact and potential exposure
- **Include**: Recommended escalation path

### Step 6: Generate Redline Suggestions

For each YELLOW and RED deviation, provide:
- **Current language**: Quote the relevant contract text
- **Suggested redline**: Specific alternative language
- **Rationale**: Brief explanation suitable for sharing with the counterparty
- **Priority**: Whether this is a must-have or nice-to-have in negotiation

#### Redline Generation Best Practices

When generating redline suggestions:

1. **Be specific**: Provide exact language, not vague guidance. The redline should be ready to insert.
2. **Be balanced**: Propose language that is firm on critical points but commercially reasonable. Overly aggressive redlines slow negotiations.
3. **Explain the rationale**: Include a brief, professional rationale suitable for sharing with the counterparty's counsel.
4. **Provide fallback positions**: For YELLOW items, include a fallback position if the primary ask is rejected.
5. **Prioritize**: Not all redlines are equal. Indicate which are must-haves and which are nice-to-haves.
6. **Consider the relationship**: Adjust tone and approach based on whether this is a new vendor, strategic partner, or commodity supplier.

#### Redline Format

For each redline:
```
**Clause**: [Section reference and clause name]
**Current language**: "[exact quote from the contract]"
**Proposed redline**: "[specific alternative language with additions in bold and deletions struck through conceptually]"
**Rationale**: [1-2 sentences explaining why, suitable for external sharing]
**Priority**: [Must-have / Should-have / Nice-to-have]
**Fallback**: [Alternative position if primary redline is rejected]
```

### Step 7: Business Impact Summary

Provide a summary section covering:
- **Overall risk assessment**: High-level view of the contract's risk profile
- **Top 3 issues**: The most important items to address
- **Negotiation strategy**: Recommended approach (which issues to lead with, what to concede)
- **Timeline considerations**: Any urgency factors affecting the negotiation approach

#### Negotiation Priority Framework

When presenting redlines, organize by negotiation priority:

**Tier 1 -- Must-Haves (Deal Breakers)**
Issues where the organization cannot proceed without resolution:
- Uncapped or materially insufficient liability protections
- Missing data protection requirements for regulated data
- IP provisions that could jeopardize core assets
- Terms that conflict with regulatory obligations

**Tier 2 -- Should-Haves (Strong Preferences)**
Issues that materially affect risk but have negotiation room:
- Liability cap adjustments within range
- Indemnification scope and mutuality
- Termination flexibility
- Audit and compliance rights

**Tier 3 -- Nice-to-Haves (Concession Candidates)**
Issues that improve the position but can be conceded strategically:
- Preferred governing law (if alternative is acceptable)
- Notice period preferences
- Minor definitional improvements
- Insurance certificate requirements

**Negotiation strategy**: Lead with Tier 1 items. Trade Tier 3 concessions to secure Tier 2 wins. Never concede on Tier 1 without escalation.

### Step 8: CLM Routing (If Connected)

If a Contract Lifecycle Management system is connected via MCP:
- Recommend the appropriate approval workflow based on contract type and risk level
- Suggest the correct routing path (e.g., standard approval, senior counsel, outside counsel)
- Note any required approvals based on contract value or risk flags

If no CLM is connected, skip this step.

## Output Format

Structure the output as:

```
## Contract Review Summary

**Document**: [contract name/identifier]
**Parties**: [party names and roles]
**Your Side**: [vendor/customer/etc.]
**Deadline**: [if provided]
**Review Basis**: [Playbook / Generic Standards]

## Key Findings

[Top 3-5 issues with severity flags]

## Clause-by-Clause Analysis

### [Clause Category] -- [GREEN/YELLOW/RED]
**Contract says**: [summary of the provision]
**Playbook position**: [your standard]
**Deviation**: [description of gap]
**Business impact**: [what this means practically]
**Redline suggestion**: [specific language, if YELLOW or RED]

[Repeat for each major clause]

## Negotiation Strategy

[Recommended approach, priorities, concession candidates]

## Next Steps

[Specific actions to take]
```

## Notes

- If the contract is in a language other than English, note this and ask if the user wants a translation or review in the original language
- For very long contracts (50+ pages), offer to focus on the most material sections first and then do a complete review
- Always remind the user that this analysis should be reviewed by qualified legal counsel before being relied upon for legal decisions

Related Skills

pipeline-review

10671
from anthropics/knowledge-work-plugins

Analyze pipeline health — prioritize deals, flag risks, get a weekly action plan. Use when running a weekly pipeline review, deciding which deals to focus on this week, spotting stale or stuck opportunities, auditing for hygiene issues like bad close dates, or identifying single-threaded deals.

metrics-review

10671
from anthropics/knowledge-work-plugins

Review and analyze product metrics with trend analysis and actionable insights. Use when running a weekly, monthly, or quarterly metrics review, investigating a sudden spike or drop, comparing performance against targets, or turning raw numbers into a scorecard with recommended actions.

vendor-review

10671
from anthropics/knowledge-work-plugins

Evaluate a vendor — cost analysis, risk assessment, and recommendation. Use when reviewing a new vendor proposal, deciding whether to renew or replace a contract, comparing two vendors side-by-side, or building a TCO breakdown and negotiation points before procurement sign-off.

brand-review

10671
from anthropics/knowledge-work-plugins

Review content against your brand voice, style guide, and messaging pillars, flagging deviations by severity with specific before/after fixes. Use when checking a draft before it ships, when auditing copy for voice consistency and terminology, or when screening for unsubstantiated claims, missing disclaimers, and other legal flags.

performance-review

10671
from anthropics/knowledge-work-plugins

Structure a performance review with self-assessment, manager template, and calibration prep. Use when review season kicks off and you need a self-assessment template, writing a manager review for a direct report, prepping rating distributions and promotion cases for calibration, or turning vague feedback into specific behavioral examples.

code-review

10671
from anthropics/knowledge-work-plugins

Review code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a change for N+1 queries, injection risks, missing edge cases, or error handling gaps.

accessibility-review

10671
from anthropics/knowledge-work-plugins

Run a WCAG 2.1 AA accessibility audit on a design or page. Trigger with "audit accessibility", "check a11y", "is this accessible?", or when reviewing a design for color contrast, keyboard navigation, touch target size, or screen reader behavior before handoff.

forecast

10671
from anthropics/knowledge-work-plugins

Generate a weighted sales forecast with best/likely/worst scenarios, commit vs. upside breakdown, and gap analysis. Use when preparing a quarterly forecast call, assessing gap-to-quota from a pipeline CSV, deciding which deals to commit vs. call upside, or checking pipeline coverage against your number.

draft-outreach

10671
from anthropics/knowledge-work-plugins

Research a prospect then draft personalized outreach. Uses web research by default, supercharged with enrichment and CRM. Trigger with "draft outreach to [person/company]", "write cold email to [prospect]", "reach out to [name]".

daily-briefing

10671
from anthropics/knowledge-work-plugins

Start your day with a prioritized sales briefing. Works standalone when you tell me your meetings and priorities, supercharged when you connect your calendar, CRM, and email. Trigger with "morning briefing", "daily brief", "what's on my plate today", "prep my day", or "start my day".

create-an-asset

10671
from anthropics/knowledge-work-plugins

Generate tailored sales assets (landing pages, decks, one-pagers, workflow demos) from your deal context. Describe your prospect, audience, and goal — get a polished, branded asset ready to share with customers.

competitive-intelligence

10671
from anthropics/knowledge-work-plugins

Research your competitors and build an interactive battlecard. Outputs an HTML artifact with clickable competitor cards and a comparison matrix. Trigger with "competitive intel", "research competitors", "how do we compare to [competitor]", "battlecard for [competitor]", or "what's new with [competitor]".