contract-risk-analyzer
Skill0 starsChanged 3 months agoMITView on GitHub
Performs deep, clause-level risk analysis on commercial contracts (MSAs, NDAs, SOWs, vendor/reseller agreements, license agreements, employment agreements, leases) retrieved through Lumina's RAG pipeline. Segments the agreement into a standard clause taxonomy, benchmarks each clause against a configurable negotiation playbook or general market-standard heuristics, scores risk severity, flags clauses that are missing/silent, and returns a structured risk report with redline suggestions and inline citations to the source clause text and page/section location. Use this skill whenever a user uploads or references a contract and asks to "review," "redline," "assess risk in," "summarize the risk in," or "compare against our playbook" a legal agreement — or asks about specific clause types (indemnity, liability cap, termination, IP assignment, auto-renewal, governing law, confidentiality, non-compete, SLA, data protection/DPA, force majeure, assignment/change of control) inside a contractual document. Trigger even if the user does not say the word "contract" explicitly, as long as they reference a specific agreement, exhibit, or SOW and want risk, exposure, or negotiation-position feedback on it.
In this repository11 other files it gives its agents.
- frontend/AGENTS.mdAGENTS.md
- .agents/skills/ui-ux-pro-max/CLAUDE.mdCLAUDE.md
- frontend/CLAUDE.mdCLAUDE.md
- deep-causal-reasoningSkill
- fable-reasoningSkill
- frontend-designSkill
- in-editor-testingSkill
- opus-reasoningSkill
- rufloSkill
- sonnet-reasoningSkill
- ui-ux-pro-maxSkill
The file
Files
Contract Risk Analyzer
1. Purpose & Trigger Conditions
Evaluates commercial agreements across 17 standard clause categories, benchmarks against market heuristics or playbooks, and scores exposure severity relative to the requesting party's role.
2. Severity Rubric
- Critical: Unbounded liability, unmitigated IP loss, or perpetual auto-renewal without exit.
- High: Material deviation from market standard with plausible financial/operational loss.
- Medium: Moderate deviation from standard positions, bounded or mitigable.
- Low / Informational: Minor deviations or standard boilerplate.
3. Mandatory Disclaimer
This report is an automated risk-flagging aid generated by Lumina and does not constitute legal advice. It may not capture every risk, may misclassify ambiguous language, and does not account for facts outside the reviewed document(s). Consult qualified legal counsel before making decisions based on this report.
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
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.

