# object-removal

Sends image URLs to each::sense AI to erase unwanted people, wires, text overlays, and blemishes from photographs.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 415 installs · ★ 44
- Author: eachlabs
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/eachlabs/skills/tree/HEAD/skills/object-removal/SKILL.md
- Updated: 2026-10-07
- HTML: https://affpapa.org/en/nevibecode/skills/object-removal

## What it 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.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill object-removal -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/object-removal/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/object-removal/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill object-removal -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/object-removal/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill object-removal -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/object-removal/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install eachlabs/skills object-removal
```

2. **Manually: put the files in place**
- File: `.github/skills/object-removal/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill object-removal -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/eachlabs/skills --path skills/object-removal
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/object-removal/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill object-removal -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/eachlabs/skills/tree/HEAD/skills/object-removal/SKILL.md

## When to use it
- 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
- Remove the bystander on the left from `https://example.com/beach-photo.jpg` and reconstruct the ocean background
- Clear all overhead cables from `https://example.com/cityscape-wires.jpg` so the sky is unobstructed
- Erase the watermark located in the lower right corner of `https://example.com/watermarked-image.jpg`

## Similar
- [object-separation](https://affpapa.org/en/nevibecode/skills/object-separation.md) — skill · 1100 installs
- [image-inpainting](https://affpapa.org/en/nevibecode/skills/image-inpainting.md) — skill · 377700 installs
- [gpt-image](https://affpapa.org/en/nevibecode/skills/gpt-image.md) — skill · 12300 installs
- [layer-image-editing](https://affpapa.org/en/nevibecode/skills/layer-image-editing.md) — skill · 3400 installs
- [fal-image-edit](https://affpapa.org/en/nevibecode/skills/fal-image-edit.md) — skill · 2700 installs
- [gpt-image-1-5](https://affpapa.org/en/nevibecode/skills/gpt-image-1-5.md) — skill · 615 installs

From the same set: [eachlabs/skills](https://affpapa.org/en/nevibecode/by/eachlabs/skills.md) — 36 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md