基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/iArsalanshah/GhostFetch --skill ghostfetch命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | ghostfetch |
| description | Stealthy web fetching for AI agents. Bypasses blocks on X.com and other sites to return clean Markdown. |
| metadata | {"openclaw-emoji":"👻","openclaw-requires":"python3"} |
GhostFetch is a stealthy headless browser service designed specifically for AI agents. It bypasses anti-bot protections (like those on X/Twitter) and returns clean, LLM-friendly Markdown.
GhostFetch is already in your workspace at the repo root. To use it as a skill, ensure the Python environment is set up from the repo directory:
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
playwright install chromium
You can use GhostFetch in two ways:
Use the scraper module directly to get Markdown from a URL.
python3 -m src.core.scraper "https://x.com/user/status/123"
Start the FastAPI server to handle concurrent jobs and webhooks.
# Start server
python3 main.py
# Fetch via API
curl -X POST "http://localhost:8000/fetch" \
-H "Content-Type: application/json" \
-d '{"url": "https://x.com/user/status/123"}'
Created by Syed Arsalan Shah (@iArsalanshah)