More screenshots
Works with the AI Agents you already use
video ad claim checker
Video ad production moves fast, and AI-generated scripts often hallucinate product capabilities or pricing that don't exist.
$7.99
video ad claim checker
Example session with this skill installed
Audit this script.
Fact: Battery lasts 8 hours.
Brief: No guarantees.
Script: 'Our new device guarantees 24 hours of power.'
Mode: Script Pre-Audit.
- Read your context and instructions
- Compiled the video ad claim
I have completed the pre-audit for the provided script against the established evidence baseline.
Executive Audit Summary
- Overall Audit Verdict:
PASS_WITH_REVISIONS - Materials Inspected: Product Fact (Battery Life), Campaign Brief, Script Line.
- Key Findings: The script contains a material overstatement of battery performance and a prohibited guarantee.
- Audit Boundaries: Visual treatments, supers, and final render context were not reviewed.
Findings Ledger
| ID | Element | Claim or Visual | Evidence & Discrepancy | Severity | Status |
|---|---|---|---|---|---|
| F-01 | Script Line | "guarantees 24 hours of power" | Contradicts 8-hour fact; violates "No guarantees" rule. | High | CONFIRMED_MISMATCH |
Remediation Matrix
- Finding ID: F-01
- Original Asset Element: "Our new device guarantees 24 hours of power."
- Core Issue & Risk: Claim exceeds documented performance by 3x and uses a prohibited outcome guarantee.
- Actionable Correction: "Our new device provides up to 8 hours of power."
- Substantiation Basis: Supplied Product Fact (8 hours).
- Outstanding Action Item: Review final on-screen text (supers) for qualifying laboratory conditions.
Integrity Checklist
- Core Product Performance Claims:
ISSUE_FOUND - Visual Demonstration Fidelity:
NEEDS_REVIEW - Offer & Commercial Pricing:
NOT_APPLICABLE - Asset Perimeter & Uninspected Footage:
NEEDS_REVIEW
Final Production Gate
- Cleared Components: Core device mention.
- Mandatory Revisions: Correct battery life claim and remove "guarantee" phrasing.
- Verification Blockers: None for this specific text line.
- Pipeline Decision:
REVISE AND RE-SUBMIT
Next steps
- Apply the corrected battery life copy to the voiceover script.
- Provide the visual storyboard to check for implied performance hallucinations.
- Confirm if laboratory test conditions need to be added as a qualifying super.
Connects securely to your tools. The creator never sees your data.
About this skill
Video ad production moves fast, and AI-generated scripts often hallucinate product capabilities or pricing that don't exist. This skill provides a rigorous audit of ad scripts, transcripts, and storyboards against your actual product facts and campaign briefs to catch high-risk discrepancies before they reach production.
What it does
- Claim Verification cross-references performance claims, benefit statements, and guarantees against provided evidence.
- Offer Reconciliation audits pricing, discount percentages, and eligibility thresholds against approved offer terms.
- Visual-Audio Matching identifies potential risks where visual demonstrations or storyboards imply outcomes not supported by the voiceover or evidence.
- Risk Categorization assigns severity ratings (High, Medium, Low) and status labels (Confirmed Mismatch, Potential Risk) to every finding.
- Copy Remediation generates actionable, evidence-backed replacement copy for unsupported or misleading statements.
How it works
- Evidence Mapping starts by establishing a baseline of product documentation, briefs, and offers.
- Claim Extraction categorizes every performance, visual, and commercial claim found in the script or transcript.
- Cross-Examination flags contradictions between different asset elements, such as a voiceover claiming a discount that the on-screen text contradicts.
- Audit Reporting generates a findings ledger and remediation matrix with specific production gate recommendations.
Frameworks & tools
This skill is designed for use within LLM environments like Claude or GPT-4. It processes text-based scripts, JSON/Markdown briefs, and image descriptions or frame transcripts.
Why this beats prompting it yourself
Generic prompts often fail to maintain strict evidentiary boundaries, leading the AI to "hallucinate" corrections that are also unsubstantiated. This skill enforces a professional audit pipeline that uses specific provenance labels and prohibits the fabrication of facts, ensuring every correction is rooted in your actual data.
Use cases
- Auditing AI-generated video scripts for factual accuracy before rendering.
- Verifying promotional offers and price terms in high-volume social media ad variations.
- Flagging missing disclosures or qualifications in regulated product categories.
- Reconciling discrepancies between a creative brief and the final post-production transcript.
Known limitations
This skill provides risk analysis, not legal advice or guarantees of platform approval. It cannot independently verify sources not provided in the prompt and requires text-based descriptions of visual frames.
Does not provide legal advice or platform guarantees. Requires text descriptions for visual elements. Cannot verify external facts not provided in the session context.
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 20 days ago
Permissions
No special permissions declared or detected