Animate an existing product image or static ad into a short branded video using the GooseWorks Animate Images workflow, with source-image continuity and optional end-frame control.
Install gooseworks: https://gooseworks.ai/creative-agent/install.md # then, in Claude Code, Cursor, or Codex: /gooseworks use the animate-image skill
Turn an existing product image or static ad into a short motion creative through GooseWorks. This skill uses the same backend workflow as the Animate Images interface.
This workflow requires the GooseWorks MCP connector (https://mcp.gooseworks.ai/mcp). It uses three tools: ads_creative_animation_quote (free price), ads_creative_animate (paid start) and job_get (poll). Some clients list tools by group and show the ads tools only after they are loaded. If ads_creative_animation_quote or ads_creative_animate is not in the advertised tool list, call tools_load with { "groups": ["ads"] } first (free). If the tools are still missing, or account_whoami reports features.animate_image: false, explain that the connection or feature is not available and stop; do not substitute an unrelated image generator.
| Step | Call | Notes |
|---|---|---|
| Quote | ads_creative_animation_quote | Free and read-only. Fetches nothing and reserves nothing. Returns { dry_run: true, estimate: { frame, duration_seconds, model, estimated_credits } }. |
| Start | ads_creative_animate | Paid. Reserves credits and starts the job. Returns { job_id, kind: "animate", status }. |
| Poll | job_get with { job_id, kind: "animate" } | Read-only. result.output_url holds the video when status is complete; error explains a failure. |
Both ads_creative_animation_quote and ads_creative_animate take the same payload:
{
"brand_id": "<brand id from brand_read>",
"creative_id": "<ad creative id from ads_creative_read or ads_save>",
"animate": {
"source_render_id": "<render id, or null>",
"source_image_url": "<public https URL of the still>",
"frame": "end",
"prompt": "<motion prompt>",
"duration_seconds": 5
}
}creative_id is the ad creative the animation belongs to. Prefer an existing render (source_render_id plus its URL as source_image_url) so provenance is preserved.frame is "start" (the still is the opening frame) or "end" (the still is the closing frame, the default). The two can cost different credits; the quote shows the price for the frame you pass.duration_seconds must be 5 or 10. Other values are rejected.agent_required otherwise.brand_read (leave out brand_id to list the brands). Then find the still:
ads_creative_read (include renders) to get creative_id, source_render_id and the render URL.media_upload under the brand, then save it as an ad creative with ads_save (pass the media_id; free). ads_save returns creative_id, render_id and output_url; use them as creative_id, source_render_id and source_image_url.ads_creative_animation_quote and show the user estimated_credits exactly as the tool returns it. Never convert it to dollars or do your own math. Ask for their yes to that credit number.ads_creative_animate once with the same payload. Save the returned job_id.job_get with kind: "animate" every few seconds until status is complete or failed. Never start the same animation again while it runs; a second start pays again.result.output_url and the source image used. If it fails, report the error in plain words before proposing a retry.ads_creative_animate call is a paid generation.creative_id is the ad creative the animation belongs to. Prefer an existing render (source_render_id plus its URL as source_image_url) so provenance is preserved.frame is "start" (the still is the opening frame) or "end" (the still is the closing frame, the default). The two can cost different credits; the quote shows the price for the frame you pass.duration_seconds must be 5 or 10. Other values are rejected.agent_required otherwise.ads_creative_animate call is a paid generation.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.