Not in the top 1,000 by GitHub stars
evolsb/claude-legal-skill
AI-powered contract review skill with CUAD risk detection, market benchmarks, and lawyer-ready redlines. Works with Claude Code, Codex, Cursor, and 26+ tools.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
bca0d2e9d5ec → bca0d2e9d5ec
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bca0d2e9d5ec
No earlier version was observed for comparison.
497GitHub stars
7stars in 7 days
1skill in this repository
0commits in 30 days
Heat
5.5- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
contract-review
When your agent uses it
Review legal contracts, NDAs, employment agreements, SaaS terms, and M&A documents. Identifies unfavorable terms, suggests redlines, and compares to market standards. Use for contract analysis, due diligence, or negotiation prep.
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
3,478 tokensWhen the skill is activated
Reference documents
5,715 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Activate
- Step 1: Pre-Review Checklist
- Step 2: Identify Document Type & User Position
- Output Format
- Red Flags Quick Scan
- Document Type Checklists
- Risk Categories (CUAD 41 + Extensions)
- Market Standard Benchmarks
- Negotiability Guide
- Jurisdiction Notes
- Guardrails
Files
.gitignoreasset267 bytesCHANGELOG.mddoc1,426 bytesLICENSEasset1,076 bytesREADME.mddoc7,853 bytesexamples/balanced-agreement.mddoc2,922 bytesexamples/demo.pngasset438,559 bytesexamples/ma-agreement-review.mddoc4,511 bytesexamples/nda-review.mddoc3,265 bytesexamples/saas-agreement-review.mddoc3,731 bytesskill.mdcore14,501 bytesskill.mdcore14,501 bytes
Read SKILL.md
# Contract Review Skill
Review legal contracts for risks, extract key terms, and suggest redlines. Built on the CUAD dataset (41 risk categories), ContractEval benchmarks, and LegalBench.
## When to Activate
- User mentions "review contract", "analyze agreement", "check this contract"
- User uploads or references a PDF/DOCX legal document
- User asks about specific clauses, risks, or terms
---
## Step 1: Pre-Review Checklist
Skills included
- contract-review
Repository facts
- License
- MIT
- Created
- Jan 26, 2026
- Last pushed
- Jul 23, 2026
- Forks
- 64
- Open issues
- 7
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1 note
skill.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 30 network referencesin 2 files: README.md:5 CHANGELOG.md:5
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- 1 reference to secretsin 1 file: .gitignore:28
- No requests to vote in Hot
Show all 31 signals by file
.gitignore
- Access to secretsline 28
[Credential-related source omitted]
CHANGELOG.md
- Network accessline 5
### Added - "Why This Exists" backstory section in README - Multi-platform support via [Agent Skills standard](https://agentskills.io) (26+ tools) - Network accessline 6
- "Why This Exists" backstory section in README - Multi-platform support via [Agent Skills standard](https://agentskills.io) (26+ tools) - Full example outputs for NDA, SaaS, M&A, and balanced agreements - Network accessline 7
- Multi-platform support via [Agent Skills standard](https://agentskills.io) (26+ tools)
README.md
- Network accessline 5
[](https://github.com/evolsb/claude-legal-skill/stargazers) - Network accessline 6
[](LICENSE) - Network accessline 7
[](https://agentskills.io) - Network accessline 8
[](https://github.com/TheAtticusProject/cuad) - Network accessline 9
[]() - Network accessline 11
**Works with:** Claude Code · OpenAI Codex · Cursor · GitHub Copilot · Gemini CLI · [26+ tools](https://agentskills.io) - Network accessline 16
# Claude Code git clone https://github.com/evolsb/claude-legal-skill ~/.claude/skills/contract-review - Network accessline 17
git clone https://github.com/evolsb/claude-legal-skill ~/.claude/skills/contract-review - Network accessline 19
# OpenAI Codex git clone https://github.com/evolsb/claude-legal-skill ~/.codex/skills/contract-review - Network accessline 20
git clone https://github.com/evolsb/claude-legal-skill ~/.codex/skills/contract-review - Network accessline 45
Nothing worked as a drop-in skill. So I built one grounded in the [CUAD dataset](https://github.com/TheAtticusProject/cuad) (41 legal risk categories from 510 real contracts), tested it against actual agreements, and iterated until the outp - Network accessline 65
This skill outputs structured JSON redlines. To produce the tracked-changes Word docs and redline PDFs that lawyers actually send, pair with [**legal-redline-tools**](https://github.com/evolsb/legal-redline-tools): - Network accessline 68
pip install git+https://github.com/evolsb/legal-redline-tools.git - Network accessline 134
This skill follows the open [Agent Skills standard](https://agentskills.io) and works with any compatible tool. - Network accessline 137
# Claude Code git clone https://github.com/evolsb/claude-legal-skill ~/.claude/skills/contract-review - Network accessline 138
git clone https://github.com/evolsb/claude-legal-skill ~/.claude/skills/contract-review - Network accessline 140
# OpenAI Codex git clone https://github.com/evolsb/claude-legal-skill ~/.codex/skills/contract-review - Network accessline 141
git clone https://github.com/evolsb/claude-legal-skill ~/.codex/skills/contract-review - Network accessline 149
git clone https://github.com/evolsb/claude-legal-skill ~/Developer/claude-legal-skill - Network accessline 187
- [CUAD Dataset](https://github.com/TheAtticusProject/cuad) — Atticus Project (NeurIPS 2021) - Network accessline 188
- [LegalBench](https://hazyresearch.stanford.edu/legalbench/) — Stanford HAI - Network accessline 189
- [ContractEval](https://arxiv.org/abs/2303.07389) — Contract understanding benchmarks - Network accessline 193
- **Need deliverables?** Use [legal-redline-tools](https://github.com/evolsb/legal-redline-tools) to generate tracked-changes `.docx`, redline PDFs, and negotiation memos from the skill's output - Network accessline 195
- **Found an issue?** [Open a GitHub issue](https://github.com/evolsb/claude-legal-skill/issues) - Network accessline 199
Questions or feedback? [Open an issue](https://github.com/evolsb/claude-legal-skill/issues) or email chris@ctsheehan.com. - Network accessline 205
--- Built by [Chris Sheehan](https://ctsheehan.com). - Network accessline 206
Built by [Chris Sheehan](https://ctsheehan.com).
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 30 facts
- Network access in prose of documentationCHANGELOG.md:5Low confidence
- Network access in prose of documentationCHANGELOG.md:6Low confidence
- Network access in prose of documentationCHANGELOG.md:7Low confidence
- Network access in prose of documentationREADME.md:5Low confidence
- Network access in prose of documentationREADME.md:6Low confidence
- Network access in prose of documentationREADME.md:7Low confidence
- Network access in prose of documentationREADME.md:8Low confidence
- Network access in prose of documentationREADME.md:9Low confidence
- Network access in prose of documentationREADME.md:11Low confidence
- Network access in code of documentationREADME.md:16Low confidence
- Network access in code of documentationREADME.md:17Low confidence
- Network access in code of documentationREADME.md:19Low confidence
- Network access in code of documentationREADME.md:20Low confidence
- Network access in prose of documentationREADME.md:45Low confidence
- Network access in prose of documentationREADME.md:65Low confidence
- Network access in code of documentationREADME.md:68Low confidence
- Network access in prose of documentationREADME.md:134Low confidence
- Network access in code of documentationREADME.md:137Low confidence
- Network access in code of documentationREADME.md:138Low confidence
- Network access in code of documentationREADME.md:140Low confidence
- Network access in code of documentationREADME.md:141Low confidence
- Network access in code of documentationREADME.md:149Low confidence
- Network access in prose of documentationREADME.md:187Low confidence
- Network access in prose of documentationREADME.md:188Low confidence
- Network access in prose of documentationREADME.md:189Low confidence
- Network access in prose of documentationREADME.md:193Low confidence
- Network access in prose of documentationREADME.md:195Low confidence
- Network access in prose of documentationREADME.md:199Low confidence
- Network access in prose of documentationREADME.md:205Low confidence
- Network access in prose of documentationREADME.md:206Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skill.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skill.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skill.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skill.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skill.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skill.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
