agentleFS
OneWave-AIOneWave-AI/claude-skills/contract-analyzer/SKILL.md

contract-analyzer

Skill378 starsChanged 52 days agoMITView on GitHub

Review contracts for concerning clauses, extract key terms, compare to standard terms, and flag unusual provisions. Use when user needs contract review, legal document analysis, or agreement evaluation.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Contract Analyzer

Review contracts to surface risks, key terms, and unusual provisions, then recommend negotiation actions.

Contents

  • references/key-terms.md -- full checklist of terms to extract by category
  • references/risk-flags.md -- red/yellow flags, standards comparison, commonly missing clauses
  • references/output-template.md -- the full analysis report format
  • references/examples.md -- worked examples and best practices

Workflow

  1. Include this disclaimer in every output: "Legal Disclaimer: This is informational analysis only, not legal advice. Always consult with a qualified attorney for legal matters. Contract interpretation can be complex and jurisdiction-specific."
  2. Identify the contract type (employment, independent contractor/freelance, NDA, service, partnership, software license, real estate, purchase).
  3. Extract key terms across financial, duration/termination, intellectual property, liability/indemnification, and other critical categories. See references/key-terms.md.
  4. Flag concerning clauses as red flags (high risk) or yellow flags (review carefully). See references/risk-flags.md.
  5. Compare terms to industry standards: note deviations, one-sided provisions, and missing standard protections. See references/risk-flags.md.
  6. Assess balance: determine whether obligations, penalties, and protections are reciprocal or favor one party.
  7. Provide actionable recommendations: specific clauses to negotiate, alternative language, questions to ask, terms to add, and deal-breakers.
  8. Format the report per references/output-template.md. For worked examples and best practices, see references/examples.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.