XcodeBuildMCP
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
Open-source web scraping API. Turn any website into clean markdown or structured JSON. Anti-detect browser, proxy auto-selection, self-hosted. One command: make up
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/anakin-inc-anakin)在同一工作中把 AI 连到服务的 MCP
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more
同类工作,排序与 Skill 列表相同
| 本项 anakin | MinerU | watermarks-remover | obsidian-skills | anysearch-skill | |
|---|---|---|---|---|---|
| 作者 | Anakin-Inc | opendatalab | guillaumemeyer | kepano | anysearch-ai |
| Skill 数 | 1 | 1 | 1 | 5 | 1 |
| GitHub 星标 | 3,863 | 83,919 | 27,723 | 53,104 | 6,905 |
| 最近代码更新 | 2026年8月19日 | 2026年11月18日 | 2026年11月17日 | 2026年9月15日 | 2026年11月13日 |
| 许可证 | AGPL-3.0 | – | MIT | MIT | Apache-2.0 |
Anakin-Inc 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
开发者未说明 · SKILL.md 形式的 Skill 可用于支持 Agent Skills 的应用,如 Claude Code、Codex 和 Cursor
GitHub account Anakin-Inc (organization), 5 years old
★ 3,863 stars · code last changed 2026年8月19日
No, plain text files the AI reads and follows
No scripts, so it does not go online by itself
No hooks or writes to machine settings found
Checked automatically from the repo files at commit a842fc2 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
This skill uses the AGPL-3.0 license, which is not on the list we redistribute, so we do not hand out a ZIP from our site. Download it from GitHub and arrange the folder yourself, or use "Let the AI install it" above, which is easier
Download from GitHub (whole repo) ↗
Unzip it, then zip only the openclaw-skill folder again. The ZIP must have a anakinscraper folder with SKILL.md at the top level, no loose files
+Create skillUpload a skillpick anakinscraper.zip
SettingsCapabilitiesCode execution and file creation
Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free
Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)
Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)
Checked against official docs 2026年11月12日 · Source: support.claude.com, support.claude.com, code.claude.com
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /openclaw-skill,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/anakin-inc/anakin.git /tmp/popnx-skill-anakin-inc-anakin-a842fc2 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-anakin-inc-anakin-a842fc2/openclaw-skill' ~/.claude/skills/openclaw-skillChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 anakinscraper 文件夹放到 ~/.agents/skills/anakinscraper
~ 是你的主文件夹($HOME)
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/anakin-inc/anakin.git /tmp/popnx-skill-anakin-inc-anakin-a842fc2 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-anakin-inc-anakin-a842fc2/openclaw-skill' ~/.agents/skills/openclaw-skillChecked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/anakin-inc/anakin.git /tmp/popnx-skill-anakin-inc-anakin-a842fc2 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-anakin-inc-anakin-a842fc2/openclaw-skill' ~/.agents/skills/openclaw-skill复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 openclaw-skill
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/anakin-inc/anakin.git /tmp/popnx-skill-anakin-inc-anakin-a842fc2 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-anakin-inc-anakin-a842fc2/openclaw-skill' ~/.cursor/skills/openclaw-skill适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
✓ 命令已检查 2026年11月17日
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
3,433 个字符 · 在 GitHub 打开完整文件
---
name: anakinscraper
description: Scrape any website into clean markdown or structured JSON. Anti-detect browser, smart proxy rotation, AI-powered data extraction.
version: 1.0.0
license: AGPL-3.0
user-invocable: true
metadata: {"openclaw":{"requires":{"bins":["node"]},"emoji":"🕷️","homepage":"https://github.com/Anakin-Inc/anakinscraper-oss"}}
---
# AnakinScraper Skill
Scrape any website and get back clean markdown or structured JSON data. Uses an anti-detect browser (Camoufox) to handle JavaScript-heavy sites and anti-bot protection.
## Setup
1. Start AnakinScraper (if not already running):
```bash
git clone https://github.com/Anakin-Inc/anakinscraper-oss.git
cd anakinscraper-oss && make up
```
2. Copy the skill into your OpenClaw workspace:
```bash
cp -r openclaw-skill ~/.openclaw/workspace/skills/anakinscraper
```
The skill calls the AnakinScraper REST API at `http://localhost:8080` directly. No additional build step required.
## Available Tools
### anakinscraper_scrape
Scrape a single URL synchronously. Returns markdown, cleaned HTML, and optionally structured JSON.
Use this when the user asks to:
- "Scrape this website"
- "Get the content from this URL"
- "Turn this page into markdown"
- "What's on this webpage?"
Parameters:
- `url` (required) — The URL to scrape
- `useBrowser` (optional, default false) — Force browser rendering for JavaScript-heavy sites
- `generateJson` (optional, default false) — Extract structured JSON data using AI
### anakinscraper_extract_json
Scrape a URL and extract structured data as JSON. Best for product pages, articles, listings.
Use this when the user asks to:
- "Extract the product data from this page"
- "Get structured data from this URL"
- "Parse this listing page into JSON"
- "What products are on this page?"
Parameters:
- `url` (required) — The URL to extract data from
### anakinscraper_batch_scrape
Scrape multiple URLs at once (up to 10). Returns results for all URLs.
Use this when the user asks to:
- "Scrape these 5 URLs"
- "Get content from all these pages"
- "Batch scrape this list"
Parameters:
- `urls` (required) — Array of URLs to scrape (max 10)
- `useBrowser` (optional) — Force browser rendering
- `generateJson` (optional) — Extract structured JSON from each page
### anakinscraper_scrape_async
Submit a scrape job asynchronously. Returns a job ID for later polling. Use for pages that take longer than 30 seconds.
Parameters:
- `url` (required) — The URL to scrape
- `useBrowser` (optional) — Force browser rendering
- `generateJson` (optional) — Extract structured JSON
### anakinscraper_get_job
Check the status of an async scrape job. Poll until status is "completed" or "failed".
Parameters:
- `jobId` (required) — The job ID returned by anakinscraper_scrape_async
## Usage Guidelines
1. **Default to `anakinscraper_scrape`** for most requests — it's synchronous and returns results immediately.
2. **Use `anakinscraper_extract_json`** when the user wants structured data (products, articles, listings).
3. **Use `anakinscraper_batch_scrape`** when scraping multiple URLs.
4. **Use `anakinscraper_scrape_async` + `anakinscraper_get_job`** only for pages you know will be slow (complex SPAs, heavy anti-bot sites).
5. **Set `useBrowser: true`** for JavaScript-heavy sites, SPAs, or sites with anti-bot protection.
6. Present the **markdown** field for readable content, **generatedJson.data** for structured data.
提问、分享技巧或报告无法使用。按“有帮助”数量排序。