Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
End-to-end pipeline for producing UGC-style promotional videos from a single product image. Runs six sequential steps: hero image generation, image variations, best-shot selection, script writing, lip-sync video generation per scene, and final editing with subtitles, transitions, and logo. Output is a finished MP4 ready for delivery.
Replaces a disconnected multi-tool workflow by chaining image generation, video synthesis, and editing into one orchestrated pipeline with a consistent output folder structure.
When to use it
- Producing a 4-scene product launch video from a packaged food photo
- Building influencer-style skincare ads without hiring a creator
- Generating fashion campaign videos from product shots
- Creating multiple UGC video variations for social media A/B testing
- Turning a gadget photo into a finished promotional clip with voiceover and branding
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: create a UGC campaign for this product image, target young adults, casual tone
- 1Generates a hero image by combining the product photo with a selected model using morpheus-fashion-design
- 2Produces 10 image variations from the hero image using multishot-ugc
- 3Analyzes all 11 images and selects 4 that are distinct, lip-sync ready, and artifact-free
- 4Writes a 4-line pure-dialogue script matched to the brand tone and target audience
- 5Runs veed-ugc four times to generate a lip-sync video per scene
- 6Assembles all clips in Remotion, adds animated subtitles, transitions, and a logo ending, and renders the final MP4
~/clawd/outputs/{project}/final/video.mp4 — a complete UGC promotional video with subtitles and logo
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.