- Home
- Skills
- Legal & Compliance
- Contract & Terms Risk Spotting Gate
Works with the AI Agents you already use
Contract & Terms Risk Spotting Gate
The Contract & Terms Risk-Spotting Gate is an adversarial reviewer for contracts, agreements, NDAs, leases, and terms-of-service.
$14
Contract & Terms Risk Spotting Gate
Example session with this skill installed
Section 7. Either party may terminate with 30 days notice. Client shall indemnify Provider against all claims arising from the engagement. Provider's total liability shall not exceed fees paid in the prior month. This agreement renews automatically for successive one-year terms unless cancelled 90 days before renewal.
- Read your context and instructions
- Compiled the contract & terms
**VERDICT:** REVIEW **SUMMARY:** Indemnity and liability are one-sided and the renewal window is long; worth raising before signing. **FLAGGED CLAUSES** - Sec. 7 indemnity | Client indemnifies Provider for "all claims" with no reciprocal indemnity. | WHY IT MATTERS: open-ended, one-directional liability exposure. - Sec. 7 liability cap | Provider's liability capped at one month of fees. | WHY IT MATTERS: very low cap relative to your uncapped indemnity. **ONE-SIDED TERMS** - Indemnity runs only from Client to Provider. - Liability cap protects Provider only. **VAGUE / AMBIGUOUS** - "all claims arising from the engagement" is broad and undefined. **MISSING PROTECTIONS** - No mutual indemnity; no governing-law or dispute-resolution clause shown. **QUESTIONS TO RAISE BEFORE SIGNING** - Can the indemnity be made mutual and limited to third-party claims? - Can the renewal cancellation window be shortened from 90 to 30 days? **NOTE:** This is a risk-spotting aid, not legal advice. For high-stakes items, consult a qualified lawyer.
Connects securely to your tools. The creator never sees your data.
About this skill
The Contract & Terms Risk-Spotting Gate is an adversarial reviewer for contracts, agreements, NDAs, leases, and terms-of-service. You hand it a document you are about to sign or accept, and it reads it the way a cautious counterparty would — hunting for clauses that are one-sided, unusually risky, vague, or conspicuously missing.\n\nIt runs five passes — one-sided terms, obligations & liability, vague/ambiguous language, missing protections, and red-flags — and returns a structured LOW RISK / REVIEW / HIGH RISK verdict: flagged clauses in plain language, why each one matters, and specific questions to raise before signing. It gives you a concentrated map of where the risk is so you know what to scrutinize or take to a professional.\n\nIt judges; it does not draft. It never rewrites clauses, negotiates, or tells you whether to sign. Crucially, it is not a lawyer and does not give legal advice — for high-stakes items it points you to qualified counsel.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Legal & Compliance.
It is not a lawyer and does not give legal advice. It cannot guarantee it has caught every risk, does not know your jurisdiction's law or your specific circumstances, and should not be relied on as the sole review for high-stakes agreements. It reviews one document at a time and cannot cross-reference external agreements, side letters, or prior versions it has not been shown. Quality depends on the document text you provide; garbled PDF extraction limits what it can check. For HIGH RISK or high-value contracts, consult a qualified lawyer.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
8 uses
Times used to date
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 months ago
Permissions
File Scopes
Read-only access is the only permission this skill needs. It reads the single contract or terms document you provide and returns flagged risks and questions. It never writes files, connects to a network, or runs commands — nothing leaves your environment and the document is not stored or transmitted.