agentleFS
Sign inStart free
eigent-aieigent-ai/agent-skills/skills/pdf-and-documents/contract-review-risk-scoring/SKILL.md

contract-review-risk-scoring

Skill27 starsChanged 8 months agoApache-2.0View on GitHub

Review contracts with clause-by-clause risk scoring, market benchmarks, negotiability ratings, and redline suggestions. Use when the user pastes an NDA, SaaS/MSA, M&A LOI, or payment agreement and wants a Contract Safety Score, CUAD-based risk breakdown, or /review as [position] analysis.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not skip boilerplate — buried risk often lives in definitions and general provisions.

    line 58
  2. Distinctive:

    When contract text is incomplete, state what cannot be assessed.

    line 59
  3. Distinctive:

    Prefer specific redline language over vague "negotiate this" notes.

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Contract Review & Risk Scoring

Focused contract review built on CUAD (41 risk categories), ContractEval benchmarks, and LegalBench.

Source Repository

Covers NDAs, SaaS/MSA, M&A, payment agreements, and finder/broker agreements.

/review [contract] as [your position]

Core skill. Reads the full contract, maps clauses against CUAD's 41 risk categories, assigns severity (low / medium / high / critical), benchmarks key terms against market norms, and outputs a prioritised fix list with concrete redline language. Finishes with an overall Contract Safety Score.

Workflow:

  1. Confirm document type and user's position (customer, vendor, receiving party, acquirer, etc.).
  2. Parse and enumerate all material clauses.
  3. Score each clause against CUAD risk categories.
  4. Benchmark flagged terms vs market norms.
  5. Assign negotiability rating per issue (easy / moderate / hard).
  6. Draft specific redline language for top issues.
  7. Output Contract Safety Score (0–100) with summary.

Output structure:

## Contract Safety Score: [score]/100

## Critical Issues (fix before signing)
## High / Medium / Low Issues
## Market Benchmark Comparison
## Recommended Redlines (prioritised)
## Negotiation Strategy Notes

Example Prompts

  • Review this NDA [paste] — I'm the receiving party. Flag unusual confidentiality scope, one-sided carve-outs, non-compete buried in obligations. Contract Safety Score + top 3 redlines.
  • Review this SaaS subscription agreement [paste] — I'm the customer. Check liability caps, data ownership, unilateral change clauses, auto-renewal. Compare to market norms.
  • Review this LOI [paste] — I'm the acquirer. Flag provisions locking us in early, limiting diligence rights, or unusual exclusivity. Score overall risk; critical issues first.

Guardrails

  • This is decision support, not legal advice. Include a disclaimer when delivering output.
  • Do not skip boilerplate — buried risk often lives in definitions and general provisions.
  • When contract text is incomplete, state what cannot be assessed.
  • Prefer specific redline language over vague "negotiate this" notes.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.

Check your setup, free