Official skill · Legal basics
Marketing claims check
Checks marketing copy for risky claims: superlatives, competitor comparisons, testimonials, free offers, prices, and health or finance claims. Use it when before a landing page, ad, or email campaign goes live.
AI skill
Have your AI flag risky claims in your marketing copy
14 days free · No card needed
Works in Claude, ChatGPT, and coding agents. On Team and Business, the official skill in your pod updates itself when we improve it.
When to use it
- Before a landing page, ad, or email campaign goes live
- Copy says "#1", "fastest", "guaranteed", "free", or names a competitor
What you give it
- The copy as it will appear
- Where it runs
- Proof you already have
What you get
A claims table with risk, proof needed, proof on hand, and safer lines, plus questions for counsel and a publish verdict.
How it works
- List every claim
- Classify each one
- Name the proof each needs
- Rate risk
- Check the fine print
- Suggest a safer line
- Write the table and questions
Example
What you give it
Jonas at Tidewell (expense app), landing page for the US. Proof given: an internal test in May 2026 where 40 users submitted receipts in an average of 11 seconds. > The #1 expense app for startups. Submit receipts in seconds, 5x faster than Expensify. "Tidewell saved us 20 hours a month" — Finance lead. Free forever. Card required.
What you get back (the start of it)
Marketing claims check — Tidewell landing page, US website, 4 November
_Not legal advice. Flags claims and the proof they need, for review by counsel._
| # | Claim (quote) | Type | Risk | Proof needed | Proof we have | Safer line |
|---|---|---|---|---|---|---|
| 1 | "The #1 expense app for startups" | superlative | high | Ranking source, date, and what "#1" measures | check: proof | "Expense app built for startups" |
| 2 | "Submit receipts in seconds" | performance | low | Timing data | May 2026 test, 40 users, 11 seconds average | "Submit a receipt in about 11 seconds" |
| 3 | "5x faster than Expensify" | comparative, named | high | Like-for-like test against Expensify, method, date | check: proof | Remove, or state the test and its method |
| 4 | "saved us 20 hours a month" — Finance lead | testimonial | medium | Real customer, written permission, exact words, any payment disclosed | check: proof | Same quote with name and company, once permission is on file |
| 5 | "Free forever. Card required." | free | high | What is free, limits, what triggers a charge | check: proof | "Free plan for up to [n] users. Card required to start." |
Fine print gaps
- "Free forever" sits next to "Card required" with no word on when the card is charged.
Questions for counsel
- [ask counsel: what do we need on file before naming Expensify in a comparison in the US?]
- [ask counsel: does "free" with a card required need extra disclosure in the US?]
The rest of this output, the full steps and the checks the AI runs before it answers are in your pod once you add the skill.
Use this skill in your AIShare it with your team
Add it to an AI Skill Pod and everyone on the team, contractors included, uses the same version from their own AI. Read the best ways to share AI skills with a team
Changelog
- v1.0.0 · · First release.
Sources
- FTC Policy Statement Regarding Advertising Substantiation (read 2026-11-04)
- FTC's Endorsement Guides: What People Are Asking (read 2026-11-04)
- 16 CFR § 251.1 - The guide (use of the word Free) (read 2026-11-04)