本文へ移動
cccskills
無料GitHub で公開

animate-image

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.

インストール方法を見る

含まれるファイル(2)

  • SKILL.md4.1 KB
  • skill.meta.json317 B

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Animate Image

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.

Prerequisite

This workflow requires the GooseWorks MCP connector (https://mcp.gooseworks.ai/mcp). Animate Images has no tools of its own: it is the animate action of ads_creative_edit, and the job is polled with job_get. If ads_creative_edit and job_get are not in the advertised tool list, 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.

Older versions of this skill called estimate_animate_image, submit_animate_image and get_animate_image. Those names are no longer advertised. Use the calls below.

Tool calls

StepCallNotes
Estimateads_creative_edit with action: "animate", dry_run: trueFree. Reserves nothing. Returns { dry_run: true, estimate: { frame, duration_seconds, model, estimated_credits, estimated_cost_usd } }.
Submitads_creative_edit with action: "animate" (no dry_run)Paid. Reserves credits and starts the job. Returns { job_id, kind: "animate", status }.
Polljob_get with { job_id, kind: "animate" }Read-only. result.output_url holds the video when status is complete; result.error explains a failure.

Both ads_creative_edit calls take the same payload:

{
  "brand_id": "<brand id from brand_list>",
  "creative_id": "<ad project id from ads_creative_read>",
  "action": "animate",
  "animate": {
    "source_render_id": "<render id, or null when animating a plain image URL>",
    "source_image_url": "<public https URL of the still>",
    "frame": "end",
    "prompt": "<motion prompt>",
    "duration_seconds": 5
  }
}
  • creative_id is the ad project 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). End-frame mode costs slightly more.
  • duration_seconds must be 5 or 10. Other values are rejected.
  • Submitting needs an agent-scoped token or a default agent on the account; the tool returns agent_required otherwise.

Workflow

  1. Resolve the brand with brand_list and the project or creative with ads_creative_read (include renders to get source_render_id and the render URL). A plain image that is not yet in GooseWorks can be registered with media_upload first to get a public URL.
  2. Clarify the motion goal, duration (5 or 10 seconds), and whether the user wants the source image as the start frame or the end frame.
  3. Write a motion prompt describing camera movement, subject movement, environment movement, pacing, and what must remain unchanged. Do not redesign the product or add unsupported claims.
  4. Call ads_creative_edit with dry_run: true and confirm the quoted credits with the user before generating.
  5. Call ads_creative_edit once without dry_run. Save the returned job_id.
  6. Poll job_get with kind: "animate" every few seconds until status is complete or failed. Never re-submit a running job; it double-bills.
  7. Return result.output_url and the source image used. If it fails, report result.error before proposing a retry.

Rules

  • Ask before spending credits. The estimate call is the only free call; every non-dry-run submit is a paid generation.
  • Never submit without an explicit user approval of the quoted credits.
  • Preserve product shape, logo, packaging, and on-image copy unless the user explicitly requests a change.
  • Prefer subtle, physically plausible motion for product shots and graphic ads.
  • A new prompt for an already-running job is a new paid generation; do not silently create it.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

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.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

The intake stage of a Meta ad harness. Researches the brand first, states what it assumes, and asks only what it cannot infer and what would change money, claims or legal exposure if guessed wrong — at most four questions a turn, in plain business language. Writes the brand's stable facts (ads/brand.md), the campaign brief, and a log of what was asked vs assumed. Use it when someone wants to run Meta ads and the brand's ad facts are not yet recorded.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

Analyze the message match between your ads and landing pages. Checks if the promise in the ad copy carries through to the landing page headline, body, and CTA. Flags disconnects that kill conversion rates. Works with Google, Meta, and LinkedIn ads.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

Turn a brand's facts, a campaign brief and the product into a one-minute Meta ad strategy with its reasoning — goal, audience, objective and placements, budget split, how many ads and how different they must be (generate 3x so the user can choose), the test frame, the success metric, and safety rules for the user to accept. Decides what launch-meta-ad-campaign then executes, and re-reads the strategy after a deep check to show which assumption changed. Use it after intake and before any creative is generated or any campaign is built.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

gooseworks-ai のスキルをすべて見る

このスキルの問題を報告する