gooseworks-ai/goose-skills / drafts/marketing/make-video-ads
make-video-ads
VerifiedUse when the marketer says: make me a video ad, a 30-second ad for paid social, a Reel / TikTok / Shorts ad, a UGC-style video made with AI (no real creator), a product demo video, remake this ad I like for my brand, cut our best organic video into an ad, more like my winning video with new hooks, my video ad got rejected — fix it. Delivers a produced, ready-to-post video ad grounded in a researched angle: one message, a hook for the first two seconds, every claim traced to the brand's signed-off claims, no generated person posing as a customer, the exact words and the price approved before anything renders (one video, or one plus two hook variants), an honest review of the result, priced fixes only on a yes, and launch copy and notes for the ads team. Works in chat apps. Never publishes or spends ad budget. Not for real creators filming for you — work-with-creators (unsure? ask: AI-made or a real person); not for a phone-shot organic post — run-organic-social; not for static ads — make-static-ads.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 16.9 KB |
| atoms/present-gate/ATOM.md | markdown | 3.0 KB |
| atoms/review-render/ATOM.md | markdown | 2.4 KB |
| atoms/script-check/ATOM.md | markdown | 2.8 KB |
| atoms/write-script/ATOM.md | markdown | 2.8 KB |
| references/angles-formats-and-company-types.md | markdown | 6.8 KB |
| references/claims-policy-and-people.md | markdown | 7.8 KB |
| references/excellent-script-example.md | markdown | 5.1 KB |
| references/paths-and-gates.md | markdown | 5.7 KB |
| references/reading-the-brain.md | markdown | 6.5 KB |
| references/review-rubric.md | markdown | 5.6 KB |
| references/script-craft.md | markdown | 5.2 KB |
| skill.meta.json | config | 4.3 KB |
| tests/test-by-hand.md | markdown | 8.4 KB |
atoms/script-check/ATOM.md
View on GitHub---
name: script-check
description: Internal step of make-video-ads. Extracts every claim-bearing span from a video plan — spoken lines, on-screen text, pictures, end-card and grid text, launch copy, and text inside images or clips — hands them to the shared claims gate and ad-policy check, and applies the video-only speaker test and idea trace, before the plan is saved.
---
# script-check
Claims verdicts (keep, rewrite, cut, the scoped sign-off when nothing is signed): `../../../../../skills/marketing/claims-gate/SKILL.md`. Platform and category rules: `../../../../../skills/marketing/ad-policy-check/SKILL.md`. This atom is the video extract step plus the checks only video needs.
**Reads:** the candidates (write-script) and the plan's `answers`; the engine's `warnings`, `claims_note`, `product_facts`, `buyer_brief`; `gooseworks:media_analyze` / `media_search` visible text for every `image_asset_id`, clip and cast image; `references/claims-policy-and-people.md`.
**Writes:** fixes to the candidates; the claim trace, source trace, cut list, people and disclosure notes for the gate.
1. **Extract** every claim-bearing span from each scene's `line`, `on_screen`, `picture` and `extra` fields, the plan's `answers` (tagline, offer, offer line, product-line name, strapline), the end card's brand fields (CTA, tagline, website), the launch copy, and the text printed inside any image or clip used.
2. **Claims gate** on the spans. Candidates that are not claims (`approvedClaims`, proof points, `may_claim`, product-page efficacy wording) are cut with their restore-proof unless the gate's sign-off covers them; only verbatim or a listed variant, never your own rewording.
3. **Idea trace** (`claims-policy-and-people.md` §1): angle bank, voice-of-customer row, or a labelled brand source; engine-drafted angles labelled "untested".
4. **Speaker test** (§3) on every line a person says and every first-person on-screen or caption line over a generated person; check from the template that the style renders a label before relying on one.
5. **Ad-policy check** on the plan: personal-attribute hooks (including the engine's own suggestions), before/after of bodies or faces, category and market rules, music rights, child appeal, disclosures; TikTok as a placement → its stricter rules.
6. **Footage and images:** this brand's product, no "not for publishing" flag, rights acceptable, consent for real people; printed claims inside images either signed or the image swapped for a clean packshot.
7. **Engine warnings:** resolve each — rewrite, cut, or `keep_claims` only for an exact restatement of a signed claim or a plain product fact. Never `keep_claims` a new health or efficacy claim.
Output for the gate: claim trace, source trace, cut list (`line → why → proof that would restore it`), people and disclosures, policy flags per placement, "not checked" items.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |