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/review-render/ATOM.md
View on GitHub---
name: review-render
description: Internal step of make-video-ads. Reviews a finished video against the approved script, following the shared honest-review principles — transcript, sampled scenes, on-screen text, key frames and the engine's check — reports findings for the human to confirm, and proposes priced, targeted fixes only for confirmed defects.
---
# review-render
How to review and report — what was perceived, findings to confirm, unseen items, remakes, records — is `../../../../../skills/marketing/honest-review/SKILL.md`. This atom adds the video specifics.
**Reads:** `gooseworks:video_read` `include: ["renders","recipe","scenes"]`; `gooseworks:media_analyze` `action: "read"` on the final render's `asset_id` with the `project_id`; the approved script and claim trace; `references/review-rubric.md`.
**Writes:** the review note; fix proposals; fixes via `gooseworks:video_fix` after a yes.
1. **Wait for the analysis** if it is queued or processing (free; read again later); failed → `action: "retry"` (free).
2. **Transcript vs approved lines:** list differences; a mismatch may be the speech-to-text — flag it for listening, not as proven.
3. **Scene walk:** each sampled shot shows what its line is about (the right product for the right line); on-screen text spelled right; no picture implying a result; a generated person speaking about using the product carries a label that rendered (speaker test); end card and grid text match what was approved. Supers absent from the read are "not seen in sampled frames".
4. **Frames:** look at key frames when the host can show them (a shell host can download the render); say when you could not.
5. **Engine check:** translate its result into plain words; "passed" covers files, not taste or claims.
6. **Note to the human:** each finding as "the automatic read shows X at <time> — please confirm", then what only they can judge (motion, voice, pacing, music, overall feel) and "please watch the first three seconds and every product shot".
7. **Fixes:** only for defects the human confirms, with the new words shown and the price as the engine gives it, made on a yes; two rounds. `video_fix` changes scenes (`line` / `on_screen` / `picture`), remakes a bad take, or changes voice or music; end-card or grid text from the plan's `answers` cannot be changed on a finished video — that needs a new draft (`video_create` `like` or `video_batch` `more_like`) and `video_change` `answers`, priced.
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 |