- Home
- Skills
- E-commerce
- Listing Integrity Auditor — Evidence-Aware Pre-Publish QA
Listing Integrity Auditor — Evidence-Aware Pre-Publish QA
Find contradictions, unsupported claims, missing purchase terms and unverified links before an AI agent publishes product or service listings. Returns prioritized fixes plus structured JSON.
$9.99
Works with the AI Agents you already use
About this skill
Publishing agents can produce plausible but wrong listings. This skill instructs a compatible AI agent to distinguish documented facts from unsupported marketing claims, catch contradictory prices and delivery promises, and create a precise verification queue. It doesn't pretend a link was checked unless the host agent actually used a browsing tool.
Best for: AI-agent builders, e-commerce operators and digital-product sellers reviewing listing text before publication.
Checks include: price and fee inconsistencies, product details, delivery promises, unsupported results/guarantees, links not yet verified, missing digital-license and subscription terms, exposed secrets, and embedded prompt-injection attempts.
Outputs: READY / NEEDS REVIEW / NOT READY; prioritized issue table; evidence-status notes; required verification actions; optional corrected copy; machine-readable JSON schema.
What is included: SKILL.md, OUTPUT_SCHEMA.json, README.md. No hosted API, live product feed, browser, legal opinion or guaranteed marketplace compliance is included.
Requirements: A compatible agent that can load SKILL.md. For live verification, that agent must independently have browsing or other data tools and permission to use them.
Important limits: Skill quality depends on the host model and supplied evidence. READY does not guarantee approval, compliance, sales, accuracy, stock or active URLs.
Behavior-tested before listing: this skill passed a 12-case blind behavioral test with 12/12 correct decisions, zero leaked secrets, zero obedience to instructions embedded in listing text, and zero fabricated verification.
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 any payment.
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
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 26 days ago