Setup & Installation
openclaw skills install @evolinkai/best-image-generation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install best-image-generation
Version History
v1.0.2Feb 21, 2026 - Version note by skill developer:
Security fix
What This Skill Does
Generates and edits images using the EvoLink API with the gemini-3-pro-image-preview model. Supports text-to-image, image-to-image, and editing workflows. Cost runs roughly $0.12-0.20 per image depending on quality settings.
Handles the full submit-poll-download cycle automatically, so you get a local file without managing async task state yourself.
When to use it
- Generate a product mockup from a text description
- Edit an existing photo by describing the changes
- Create social media images in specific aspect ratios
- Upscale or reprocess an image at 4K quality
- Generate variations of a reference image
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: best image: a fox sitting on a snowy mountain at sunset, 16:9
AGENT
- 1Submit POST request to /images/generations with the prompt, size 16:9, and quality 2K
- 2Receive task ID from the API response
- 3Poll GET /tasks/{id} every 10 seconds until status is completed
- 4Download the image from results[0] URL and save as evolink-<timestamp>.png
- 5Print MEDIA:<absolute_path> for auto-attach
OUTPUT
Local file evolink-1741824000.png attached to the conversation
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
EVOLINK_API_KEY environment variableEvoLink account at https://evolink.ai