Skill Detail

Review contract risk and redlines with Claude Legal Skill

Use Claude Legal Skill to guide an agent through contract risk review, CUAD-style clause checks, market benchmarks, and lawyer-ready redline suggestions.

Security & VerificationMulti-Framework
Security & Verification Multi-Framework Security Reviewed
⭐ 355 GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill review-contract-risk-and-redlines-with-claude-legal-skill Copy
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Tools required
Agent Skills-compatible runtime such as Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, or another compatible tool; access to the contract text or files being reviewed; human legal review for final decisions.
Install & setup
Clone the upstream repository into the agent runtime skill directory, for example ~/.claude/skills/contract-review for Claude Code or ~/.codex/skills/contract-review for Codex, then invoke the documented contract-review skill on a bounded agreement.
Author
C. T. Sheehan
Publisher
Independent
Last updated
Jul 2, 2026
Quick brief

Claude Legal Skill is a bounded contract-review workflow for agent environments. The agent reads an NDA, SaaS agreement, M&A document, merchant agreement, or similar contract; applies CUAD-informed risk categories and document-type checklists; flags risky or missing clauses; compares terms to market benchmarks; and drafts position-aware redline language for human legal review.

How it works

What this skill actually does

Invoke this when a user needs a structured first-pass contract analysis inside an agent workflow instead of uploading the document to a closed legal product or asking a general chatbot for vague legal comments. The scope boundary is contract issue spotting, clause extraction, risk explanation, and proposed redline text. It is not a replacement for counsel, a legal research platform, or a generic checklist. Operators should keep the agreement, party position, jurisdiction assumptions, and final legal judgment explicit and reviewable.

Inputs and prerequisites: Agent Skills-compatible runtime such as Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, or another compatible tool; access to the contract text or files being reviewed; human legal review for final decisions..

Setup notes: Clone the upstream repository into the agent runtime skill directory, for example ~/.claude/skills/contract-review for Claude Code or ~/.codex/skills/contract-review for Codex, then invoke the documented contract-review skill on a bounded agreement.

Source and verification boundary: use https://github.com/evolsb/claude-legal-skill as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.