Skip to content

gooseworks-ai/goose-skills / skills/marketing/ad-policy-check

ad-policy-check

Verified

Checks paid ads against the ad platform's rules (Meta, TikTok, Google, LinkedIn and others) and the brand's category rules: the copy, on-image or on-screen text, pictures and people. Rewrites what can be fixed honestly, adds the disclosures that are needed, and flags anything that needs a human or legal review, with one pass, fixed or flag line per ad and platform. Use alone when you already have the ad text or images and know where they will run; otherwise run the playbook for the job (e.g. make-static-ads, make-content, email-lifecycle).

FileKindSize
SKILL.mdskill md6.9 KB
disclosure.mdmarkdown3.0 KB
skill.meta.jsonconfig538 B

disclosure.md

View on GitHub
# Disclosure — organic posts, email and creator content

Shared reference in the `ad-policy-check` skill, next to its SKILL.md (owner make-static-ads). Load it for content that is not a paid ad: organic social posts, newsletters and other email, creator briefs and creator posts, replies. Paid ads use `SKILL.md` in this folder. Craft knowledge, not legal advice; rules differ by market, so when one decides whether something ships, tell the human to confirm it.

## 1. Material connections (creators, affiliates, employees, gifted product)

- Anyone paid, gifted product, given a commission or discount code, or employed by the brand who talks about it must disclose the connection **clearly, in the post itself, before "more"**: "#ad", "Ad", "Paid partnership with <brand>", "Gifted by <brand>". Platform branded-content tools ("Paid partnership" label) are switched on as well, not instead.
- On video: said out loud and shown on screen near the start; on a story: on every frame that endorses.
- "#sp", "#collab", "#thanks", disclosure only in a bio or at the end of a long caption, or behind "more" — not enough (US FTC Endorsement Guides; UK CAP / ASA; EU UCPD; India ASCI).
- Creator briefs say what to disclose and how, and never script claims the brand could not make itself — a creator saying it is the brand saying it.
- Reviews and testimonials: real, verbatim, not edited to change meaning, typical results; no paid or incentivised review without saying so; never a review from someone who does not exist (US FTC rule on fake reviews and testimonials, 2024).

## 2. AI-generated or altered content

- Realistic generated people, voices or scenes that could pass as real: label them where the platform asks (Meta "AI info", TikTok AIGC, YouTube altered/synthetic content) and on the asset when a viewer could be misled.
- A generated person never presents as a real customer or employee.
- Synthetic-content transparency rules (e.g. the EU AI Act's) are evolving: one line to the human — "check disclosure needs for your market".

## 3. Organic posts

- Contests and giveaways: official rules linked, eligibility, no purchase necessary where required, the platform's own rules (no tagging in photos to enter on Meta, etc.).
- Claims in organic posts are claims — the same claims check applies.
- Health, finance, alcohol and other regulated categories keep their category rules in organic posts too.
- Reposting someone's content (UGC) needs their permission, and credit.

## 4. Email and SMS

- Commercial email: an honest subject line and sender, the brand's physical address, a working unsubscribe honoured promptly (US CAN-SPAM); in the EU/UK, consent before marketing email and SMS (GDPR / PECR), and a clear identity.
- SMS: explicit consent, opt-out words ("Reply STOP"), quiet hours where the market requires them (US TCPA and state rules).
- Offers in email follow the same rules as ads: real terms, a real end date, no fake scarcity.

## 5. Report

Per item: `pass` · `fixed (what, why)` · `flag (risk, rule, decision needed)`; "not checked: <rule>, <why>" when you could not check it.
receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationStars: 323kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 323kUpdated Claude CodeCodexVerifiedInstall
using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 323kUpdated Claude CodeCodexVerifiedInstall
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 323kUpdated Claude CodeCodexVerifiedInstall