# xingtu-tool

xingtu-tool — a skill for shaping Xiaohongshu images: retouch portraits and products, build covers, and place readable text over photos.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 211 installs · ★ 564 repo stars
- Author: vivy-yi
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/vivy-yi/xiaohongshu-skills/tree/HEAD/skills/06-工具生态/xingtu-tool/SKILL.md
- Updated: 2026-01-23
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/xingtu-tool

## What it does

xingtu-tool lays out a Xingtu-based workflow for Xiaohongshu image content. It helps an agent guide edits from the first import through basic corrections, retouching, cover design, and export.

The instructions cover brightness, contrast, saturation, sharpness, skin cleanup, product polishing, text blocks, stickers, and templates. They also separate portrait work from product work: skin should retain some texture, while product colors should stay close to reality instead of being changed by heavy filters.

Xingtu must be available before the workflow starts, since the first step is importing a photo into the app. The skill is not aimed at complex graphic design or professional RAW processing; the source points to Canva and Lightroom for those jobs.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add vivy-yi/xiaohongshu-skills --skill xingtu-tool -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add vivy-yi/xiaohongshu-skills --skill xingtu-tool -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add vivy-yi/xiaohongshu-skills --skill xingtu-tool -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install vivy-yi/xiaohongshu-skills skills/06-工具生态/xingtu-tool
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add vivy-yi/xiaohongshu-skills --skill xingtu-tool -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/vivy-yi/xiaohongshu-skills --path skills/06-工具生态/xingtu-tool
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add vivy-yi/xiaohongshu-skills --skill xingtu-tool -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/vivy-yi/xiaohongshu-skills/tree/HEAD/skills/06-工具生态/xingtu-tool/SKILL.md

## When to use it
- prepare a photo for a Xiaohongshu post
- build a cover with a clear title and supporting details
- retouch a portrait without plastic-looking skin
- polish a product image while keeping its color accurate
- place text, stickers, or a template on an image

## Example prompts
- Edit this photo for a Xiaohongshu post: improve the lighting, keep the skin natural, and add a readable title.
- Turn this image into a cover with the main message in the upper third, without covering the subject.
- Retouch this product photo, preserve its real color, and add a clean caption.

## Similar
- [portrait-enhancement](https://affpapa.org/en/nevibecode/skills/portrait-enhancement.md) — skill · 497 installs
- [unsplash-image](https://affpapa.org/en/nevibecode/skills/unsplash-image.md) — skill · 388 installs
- [baoyu-cover-image](https://affpapa.org/en/nevibecode/skills/baoyu-cover-image.md) — skill · 32900 installs
- [moviepy](https://affpapa.org/en/nevibecode/skills/moviepy.md) — skill · 1700 installs
- [scenario-text-overlay](https://affpapa.org/en/nevibecode/skills/scenario-text-overlay.md) — skill · 906 installs
- [bria-ai](https://affpapa.org/en/nevibecode/skills/bria-ai.md) — skill · ★ 76 repo stars

From the same set: [vivy-yi/xiaohongshu-skills](https://affpapa.org/en/nevibecode/by/vivy-yi/xiaohongshu-skills.md) — 100 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
