# photo-restoration

Repairs damaged archival images and colorizes monochrome photographs via each::sense AI. It fixes scratches, water marks, tears, and reconstructs degraded faces.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 390 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/photo-restoration/SKILL.md
- Updated: 2026-10-07
- HTML: https://affpapa.org/en/nevibecode/skills/photo-restoration

## What it does

The skill sends restoration requests to each::sense AI. It fixes physical defects like scratches, tears, and water spots. The models can also colorize monochrome film, eliminate grain, and sharpen blurry faces from old portraits.

Under the hood, calls go to `https://eachsense-agent.core.eachlabs.run/v1/chat/completions` targeting `eachsense/beta`. Images must be supplied as web addresses inside `image_urls`. Responses stream back via Server-Sent Events with mode set to `max`.

Requests fail without an `EACHLABS_API_KEY` token set in your environment. You cannot upload local binary files directly through the prompt. Every picture needs an accessible public URL first.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install eachlabs/skills photo-restoration
```

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

### Gemini CLI

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

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

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill photo-restoration -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/photo-restoration/SKILL.md

## When to use it
- remove tears, creases, and scratch marks from scanned prints
- colorize vintage black and white portraits
- reconstruct blurred facial details in historical portraits
- fix fading and water damage on aged photographs
- reduce film grain on archival scans

## Example prompts
- Repair the physical damage on `https://example.com/old-family-photo.jpg`, clear the scratches, and restore blurry facial details.
- Apply realistic colors to `https://example.com/bw-family-portrait.jpg` so the clothing and skin tones look natural.
- Recover contrast and fix water marks on `https://example.com/faded-vintage-photo.jpg` without making it look over-processed.

## Similar
- [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill · 414180 installs
- [writing-for-agents](https://affpapa.org/en/nevibecode/skills/writing-for-agents.md) — skill · 466719 installs
- [media-use](https://affpapa.org/en/nevibecode/skills/media-use.md) — skill · 1100000 installs
- [mcp-builder](https://affpapa.org/en/nevibecode/skills/mcp-builder.md) — skill · 130949 installs
- [subagent-driven-development](https://affpapa.org/en/nevibecode/skills/subagent-driven-development.md) — skill · 237746 installs
- [orchestration](https://affpapa.org/en/nevibecode/skills/orchestration.md) — skill · 350300 installs

From the same set: [eachlabs/skills](https://affpapa.org/en/nevibecode/by/eachlabs/skills.md) — 44 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