Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Generates photorealistic digital twins and avatar clones from reference photos using the each::sense AI API. Produces still images, multi-expression sets, full-body representations, and animated videos. Supports iterative refinement across sessions and consistent output across different aspect ratios and platforms.
Session-based refinement lets you iterate on the same twin across multiple requests without re-uploading reference photos each time.
When to use it
- Replace a CEO's live camera feed with a polished digital twin for investor calls
- Produce lip-synced dubbed video content in multiple languages from a single presenter
- Generate consistent branded spokesperson images across LinkedIn, YouTube, and website
- Create a customer service chat avatar with a warm, neutral expression
- Build a full-body virtual presenter for a digital conference or trade show
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Create a corporate spokesperson twin from three executive headshots, then generate LinkedIn and YouTube thumbnail versions
- 1Upload reference photos and send initial request with session_id set to a unique project identifier
- 2Receive base digital twin image in professional studio lighting
- 3Send follow-up request in the same session asking for a 1:1 square LinkedIn format
- 4Send another request in the same session asking for a 16:9 landscape version positioned for YouTube thumbnails
- 5Return all three format variations to the user
Three format-specific images of the same digital twin ready for LinkedIn profile, YouTube thumbnail, and corporate communications
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.