eachlabs-image-edit — Claude Code skill: edit images with AI
This skill wires 130+ EachLabs models into your agent for retouching, upscaling, background removal, inpainting, face swap and image analysis.
npx skills add eachlabs/skills --skill eachlabs-image-edit -a claude-codeWhat eachlabs-image-edit does
The skill points your agent at the EachLabs Predictions API. You describe the edit; the agent picks a model from the SKILL.md tables — flux-2-flash-edit when speed matters, flux-2-max-edit for quality, flux-kontext-max for multi-image context, topaz-upscale-image for upscaling, rembg for cutting out a background.
Those tables cover general editing, multi-image work, camera angles, upscaling, background removal and inpainting, style transfer, post-processing effects, portraits, and virtual try-on. Every entry is a slug the agent drops into the request.
One thing to set up first: the EachLabs key. It lives in the EACHLABS_API_KEY environment variable and travels in the X-API-Key header. Skip that step and nothing runs.
What it helps with
- cut the background out of a product photo
- upscale a low-resolution shot
- swap a face in a finished portrait
- repaint one region of an image with inpainting
- turn a photo into comic art
Example prompts for the agent
- Remove the background from
product.jpgand save the result next to it - Upscale
portrait.pngto twice its size - Give me a comic-style version of
photo.jpg
How to install eachlabs-image-edit
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-image-edit -a claude-code2Manually: put the files in place
~/.claude/skills/eachlabs-image-edit/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/eachlabs-image-edit/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-image-edit -a codex2Manually: put the files in place
.agents/skills/eachlabs-image-edit/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-image-edit -a cursor2Manually: put the files in place
.cursor/skills/eachlabs-image-edit/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install eachlabs/skills eachlabs-image-edit2Manually: put the files in place
.github/skills/eachlabs-image-edit/SKILL.md1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-image-edit -a gemini-cli2Platform CLI
gemini skills install https://github.com/eachlabs/skills --path skills/eachlabs-image-editManually: put the files in place
.devin/skills/eachlabs-image-edit/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-image-edit -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about eachlabs-image-edit
How do I install eachlabs-image-edit in Claude Code?
Run npx skills add eachlabs/skills --skill eachlabs-image-edit -a claude-code. The skill file lands at ~/.claude/skills/eachlabs-image-edit/SKILL.md.
What does eachlabs-image-edit do?
It lets your agent edit existing images through the EachLabs Predictions API: upscaling, background removal, inpainting, face swap, style transfer and analysis.
What do I need before using it?
An EachLabs key stored in the EACHLABS_API_KEY environment variable. API calls carry it in the X-API-Key header.
