# lanhu-mcp-collaboration

lanhu-mcp-collaboration connects your assistant to Lanhu to extract UI specifications, inspect Axure prototypes, and download slices.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 256 installs · ★ 9 repo stars
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/mcp-skills/tree/HEAD/skills/lanhu-mcp-collaboration/SKILL.md
- Updated: 2026-10-09
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/lanhu-mcp-collaboration

## What it does

This skill connects your coding assistant to a local Lanhu MCP service. It pulls spacing values, color palettes, typography metrics, and generated HTML/CSS snippets straight from design links. When examining Axure prototypes, it runs targeted checks across development, testing, or exploratory workflows to identify edge cases and business rules.

Asset extraction is handled automatically. The underlying tool detects designated export layers and saves PNG or SVG files into your local folders using semantic names. Team notes can also be saved to a shared message board across client sessions.

The skill fails immediately if the backing server is offline or lacks a valid `LANHU_COOKIE` token. The host machine must also have Python 3.10 or newer and Chromium binaries installed via Playwright.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill lanhu-mcp-collaboration -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill lanhu-mcp-collaboration -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill lanhu-mcp-collaboration -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/mcp-skills skills/lanhu-mcp-collaboration
```

2. **Manually: put the files in place**
- File: `.github/skills/lanhu-mcp-collaboration/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill lanhu-mcp-collaboration -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/mcp-skills --path skills/lanhu-mcp-collaboration
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill lanhu-mcp-collaboration -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/reason-machines/mcp-skills/tree/HEAD/skills/lanhu-mcp-collaboration/SKILL.md

## When to use it
- extract layout tokens, colors, and CSS rules from design frames
- parse functional requirements and logic from Axure prototypes
- download image slices and icons with descriptive file names

## Example prompts
- Analyze the requirements from this Lanhu document in development mode
- Extract design tokens and CSS snippets for the provided Lanhu board link
- Export all asset slices from the target Lanhu stage into ./assets

## Similar
- [lanhu-design-mcp](https://affpapa.org/en/nevibecode/mcp/lanhu-design-mcp.md) — MCP server · ★ 5 repo stars
- [return_rp](https://affpapa.org/en/nevibecode/mcp/return-rp.md) — MCP server · ★ 9 repo stars
- [one-shot-ui](https://affpapa.org/en/nevibecode/mcp/one-shot-ui.md) — MCP server · ★ 6 repo stars
- [extract-design-system](https://affpapa.org/en/nevibecode/skills/extract-design-system.md) — skill · 131800 installs
- [explain-interface](https://affpapa.org/en/nevibecode/skills/explain-interface.md) — skill · 21700 installs
- [design-system](https://affpapa.org/en/nevibecode/skills/jezweb-design-system.md) — skill · 1200 installs

From the same set: [reason-machines/mcp-skills](https://affpapa.org/en/nevibecode/by/reason-machines/mcp-skills.md) — 98 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
