object-removal — Claude Code skill: what it does, how to install
Sends image URLs to each::sense AI to erase unwanted people, wires, text overlays, and blemishes from photographs.
npx skills add eachlabs/skills --skill object-removal -a claude-codeWhat object-removal does
The skill integrates AI inpainting into your agent workflow via each::sense. It builds a streaming POST request to https://eachsense-agent.core.eachlabs.run/v1/chat/completions using the eachsense/beta model, passing natural language instructions alongside an image_urls array.
It handles photo cleanup tasks like clearing power lines from sky shots or erasing tourists around monuments. Every call depends on a valid EACHLABS_API_KEY environment variable, failing immediately if the token is missing. The API accepts hosted image links, so local files must be uploaded before editing.
What it helps with
- remove tourists and bystanders from outdoor photography
- erase watermarks, branding, and text overlays from graphics
- retouch skin blemishes while preserving natural texture
- strip distracting cables and overhead wires from city views
Example prompts for the agent
- Remove the bystander on the left from
https://example.com/beach-photo.jpgand reconstruct the ocean background - Clear all overhead cables from
https://example.com/cityscape-wires.jpgso the sky is unobstructed - Erase the watermark located in the lower right corner of
https://example.com/watermarked-image.jpg
How to install object-removal
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill object-removal -a claude-code2Manually: put the files in place
~/.claude/skills/object-removal/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/object-removal/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill object-removal -a codex2Manually: put the files in place
.agents/skills/object-removal/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill object-removal -a cursor2Manually: put the files in place
.cursor/skills/object-removal/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install eachlabs/skills object-removal2Manually: put the files in place
.github/skills/object-removal/SKILL.md1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill object-removal -a gemini-cli2Platform CLI
gemini skills install https://github.com/eachlabs/skills --path skills/object-removalManually: put the files in place
.devin/skills/object-removal/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add eachlabs/skills --skill object-removal -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 object-removal
How to install object-removal in Claude Code?
Run npx skills add eachlabs/skills --skill object-removal -a claude-code. This registers the skill definition in your local environment.
What does object-removal do?
It submits image URLs and descriptive prompts to the eachsense/beta model, which cuts out target elements and reconstructs the background.
What credentials does object-removal require?
You must provide an EACHLABS_API_KEY environment variable, and your pictures must be accessible via public HTTP or HTTPS addresses.
