Skip to content

gooseworks-ai/goose-skills / drafts/marketing/make-video-ads

make-video-ads

Verified

Use 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.

skill.meta.json

View on GitHub
{
  "slug": "make-video-ads",
  "tier": "playbook",
  "version": "0.2.0",
  "pillar": "6 — Paid media / performance marketing (creative production with pillar 15)",
  "intents": [
    "everyone says video converts — I cannot produce it myself",
    "make me a 30-second video ad for paid social",
    "a Reel / TikTok / Shorts ad for the new product",
    "a UGC-style video made with AI",
    "remake this ad I like for my brand",
    "more like my winning video, with new hooks",
    "my video ad got rejected — fix it",
    "cut my own footage into an ad"
  ],
  "reads": [
    "brand brain: kit (voice, value props), products (facts, price, images), learnings incl. do/dont/must rules, organic posts with views — learn-my-brand / server research",
    "claims sign-off marker and 'Claims you may use' facts (via the shared claims-gate atom) — learn-my-brand",
    "voice-of-customer bank: research/audience/voc-bank.md / 'Voice-of-customer bank' document — research-audience",
    "angle bank: research/competitors/angle-bank.md (A-NN) / 'angle bank' document — research-competitors",
    "campaign record: brief, concepts, asset list — plan-campaign (campaign_read)",
    "weekly performance read: reports/performance/<date>.md ('what to make next') — analyze-performance",
    "request lines 'Rotation needed: for make-video-ads' / 'Fix needed: for make-video-ads' in ads/campaigns/<slug>/rotation-requests.md, and the health line of ads/campaigns/<slug>/state.md — run-paid-campaigns",
    "Goose-made creative performance — meta_read performance",
    "saved video outliers (formats carrying the category) — research-market, research-competitors (social_inspiration_library)",
    "competitor video ads (structure only) and the brand's own footage — media library",
    "creator paid-usage rights: creators/roster.csv (proposed rights only) — work-with-creators",
    "kept product photos — make-product-photos (product record / approved photos)"
  ],
  "writes": [
    "video projects named <product>_<A-NN|angle_type>_<hook_family>_<ratio>_<date>, kept/rejected with reasons — read by analyze-performance (attribution) and run-paid-campaigns (launch picks kept videos)",
    "launch notes ads/videos/<project_id>.md (one per video, each kept hook variant included): script, angle, claim trace, cuts, people and disclosures, the chosen script-checked launch copy (primary text, headline, CTA, destination — run-paid-campaigns launches from it verbatim), AI-label and music notes, which hook is which — read by run-paid-campaigns and analyze-performance",
    "lines put to the human through the claims gate's scoped sign-off, recorded through learn-my-brand's contract; declined lines listed with restore-proof in the launch notes",
    "brand learnings and corrections only through the shared save-learning atom, in the human's words — read by every creative playbook",
    "'Rotation ready:' / 'Fix ready:' answers under run-paid-campaigns' request lines — read by run-paid-campaigns on its next run"
  ],
  "needs": {
    "mcp": [
      "gooseworks:get_started",
      "gooseworks:tools_load",
      "gooseworks:account_whoami",
      "gooseworks:brand_read",
      "gooseworks:knowledge_search",
      "gooseworks:brand_update",
      "gooseworks:file_list",
      "gooseworks:file_read",
      "gooseworks:file_write",
      "gooseworks:campaign_read",
      "gooseworks:meta_read",
      "gooseworks:social_inspiration_library",
      "gooseworks:social_inspiration_search",
      "gooseworks:catalog_fetch",
      "gooseworks:media_search",
      "gooseworks:media_list",
      "gooseworks:media_analyze",
      "gooseworks:media_excerpt",
      "gooseworks:media_upload",
      "gooseworks:video_references",
      "gooseworks:video_formats",
      "gooseworks:video_create",
      "gooseworks:video_change",
      "gooseworks:video_approve",
      "gooseworks:video_production",
      "gooseworks:video_read",
      "gooseworks:video_fix",
      "gooseworks:video_review",
      "gooseworks:video_batch",
      "gooseworks:video_share",
      "gooseworks:video_import",
      "gooseworks:card_wait"
    ]
  },
  "atoms": [
    "write-script",
    "script-check",
    "present-gate",
    "review-render"
  ],
  "shared_atoms": [
    "claims-gate",
    "save-learning",
    "spend-gate",
    "ad-policy-check",
    "honest-review"
  ]
}
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: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
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: 115kUpdated Claude CodeCodexVerifiedInstall
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: 115kUpdated Claude CodeCodexVerifiedInstall