Image-to-video (or text-to-video) via any FAL video model (Kling, Seedance, Veo), routed through the GooseWorks proxy, so the call is charged to your GooseWorks credits. The template recipe names the model + params; image_url inputs must be public URLs (the orchestrator hosts local frames with the MCP media_upload). Returns the result video URL and downloads it. Use for the generative base clip of any video-ad format.
Install gooseworks: https://gooseworks.ai/creative-agent/install.md # then, in Claude Code, Cursor, or Codex: /gooseworks use the create-video-fal skill
Image-to-video (or text-to-video) via any FAL video model (Kling, Seedance, Veo), routed through the GooseWorks proxy, so the call is charged to your GooseWorks credits. The template recipe names the model + params; image_url inputs must be public URLs (the orchestrator hosts local frames with the MCP media_upload). Returns the result video URL and downloads it. Use for the generative base clip of any video-ad format.
gen_video.py --model fal-ai/kling-video/v3/pro/image-to-video --payload '{...}' --out clip.mp4 — charged to your GooseWorks credits; host-swaps the FAL queue URLs; downloads the result.
media_proxy.py — never a provider SDK's default host.A provider likeness/policy rejection stops the attempt. Preserve the provider's reason, request id and charged/uncharged/unknown state. Do not resubmit an identical rejected payload. Offer a permitted original character, user-cleared reference, or a supported non-likeness route only when allowed by that provider. A different model is not a policy bypass. Review changed inputs and extra spend through the normal approval flow.
Before generation, write a scene checklist from the brief: each wearable's exact count and body location; which hand holds each object; allowed gestures; object contacts and movement; cast identities and reference ownership. Keep unnecessary hands still, use one simple action per shot, and review the whole generated take against the checklist. A prompt is prevention, not proof: reject extra/missing products, impossible contacts or identity drift.
For multiple characters, compare a shared scene with pinned references, fewer people per shot, and separately generated/composed plates. The first preserves interaction but risks identity drift; separate plates improve control but add composition work and may weaken interaction. Lock an approved reference per person and map who speaks each line. No six-character/two-attempt guarantee is supported. A future paid benchmark must state cast size, attempts, budget, model/settings and pass criteria (identity, speaker, counts, gestures and complete dialogue) and retain every failure.
How the video models behave, measured on shipped projects. Each note lives here once; recipes point here instead of repeating it. Seedance and the talking-creator models keep their notes in their own atoms.
cfg_scale 0.5 or lower, with motion-only
prompts, it adds on-style motion where Seedance and Veo invent photoreal middle states.Research supported advertising promises from a specific buyer's context, current product facts, customer language and observed ads. Turn them into static, video or copy ideas; match video ideas to actual recipes and save a product-scoped angle bank for write-video-ad-script. Product-led discovery can use verified facts without reviews. Reference persistence and reach are observations, not proof of performance.
Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling.
For paid lead-gen and participant-recruitment ads, replaces vanity CPA with true CAC per qualified lead by joining ad-platform data with downstream funnel events, surfaces tracking gaps, and classifies every creative into Scale / Keep / Investigate / Cut.
Phone-screen and motion-graphic video ads can be built from HTML, so they are quick and cheap to make. Here are the formats and what each one needs.
Teach your coding agent to build fast, cheap value prop video ads from a brand's logo and product images, using HTML instead of a video model.
An iMessage video ad shows a text conversation on an iPhone screen. Here is how a single skill teaches Claude to build one, with sound and an end card.