joeseesun-qiaomu-anyth…
多源内容智能处理器:任何内容 → 播客 / PPT / 思维导图 / Quiz
给 Agent 一个链接,它会先选对读取通道,再把完整原文交给后续的总结、写作、翻译或分析任务。 微信、飞书、X/Twitter、PDF、arXiv 和普通网页走不同的专用路线。遇到公众号验证码页会自动回退到浏览器提取,不会把“环境异常”误当正文。
$ npx -y skills add joeseesun/qiaomu-markdown-proxy --agent claude-code
给 Agent 一个链接,它会先选对读取通道,再把完整原文交给后续的总结、写作、翻译或分析任务。
微信、飞书、X/Twitter、PDF、arXiv 和普通网页走不同的专用路线。遇到公众号验证码页会自动回退到浏览器提取,不会把“环境异常”误当正文。
English | 中文
向阳乔木(乔向阳 / Joe)是一位实践型 AI 产品与内容创作者,长期把前沿 AI 变化转译成可复用的工作流、产品判断、AI 编程实践、AI 搜索实践和 GEO/AI 营销方法。
| 打赏支持 | 微信公众号 |
|---|---|
| 感谢支持乔木持续分享 AI 实践 | 扫码关注「向阳乔木推荐看」 |
Send any URL to Claude, and it automatically fetches the full content as Markdown. Six content types have dedicated extraction:
| URL Type | Method | Why |
|---|---|---|
WeChat Articles (mp.weixin.qq.com) | Proxy-first wrapper with Playwright fallback | Rejects verification walls before returning content |
Feishu/Lark Docs (feishu.cn, larksuite.com) | Built-in Feishu API script | Requires API authentication, auto-converts to Markdown |
| YouTube | Dedicated YouTube skill | Video content has its own toolchain |
| arXiv / Hugging Face Papers | Built-in LaTeX source extractor | Preserves sections, equations, figures, and tables |
| PDF (remote or local) | Built-in PDF extraction (extract_pdf.sh) | Three-method cascade: marker-pdf → pdftotext → pypdf |
| All other URLs | Proxy cascade via fetch.sh: r.jina.ai → defuddle.md → agent-fetch | Free, no API key, content validation built-in |
python3 -m pip install playwright beautifulsoup4 lxml
python3 -m playwright install chromium
pip install marker-pdfbrew install popplerpip install pypdfnpx agent-fetch --help # No pre-install needed, npx auto-downloads
FEISHU_APP_ID and FEISHU_APP_SECRET
echo $FEISHU_APP_ID # Verify configured
npx skills add joeseesun/qiaomu-markdown-proxy
Verify:
ls ~/.agents/skills/qiaomu-markdown-proxy/SKILL.md
Just send Claude a URL:
Built-in fetch_feishu.py script fetches documents via Feishu Open API and auto-converts to Markdown:
FEISHU_APP_ID and FEISHU_APP_SECRET environment variablesdocx:document:readonly permission| Issue | Solution |
|---|---|
| WeChat scraping fails | Run playwright install chromium to install browser |
WeChat returns 环境异常 | Use scripts/fetch_weixin.sh; it rejects verification pages and falls back to Playwright |
| Python packages are missing | Install uv, or run python3 -m pip install playwright beautifulsoup4 lxml |
| Feishu returns permission error | Check FEISHU_APP_ID and FEISHU_APP_SECRET env vars, confirm app has document read permission |
| Feishu wiki page fails | Confirm app has wiki:wiki:readonly permission |
| r.jina.ai returns empty | Auto-falls back to defuddle.md (no action needed) |
| All proxies fail | URL may have strict auth restrictions, try npx agent-fetch |
给 Claude 发一个 URL,自动抓取完整内容并转为 Markdown。支持六种内容类型的专用抓取:
如果最终目标是“读取后写稿、总结、翻译或分析”,本 Skill 负责先拿到可信原文,再把内容交给下游任务,同一轮继续完成,不会停在抓取结果。
| URL 类型 | 抓取方式 | 原因 |
|---|---|---|
微信公众号 (mp.weixin.qq.com) | 代理优先、Playwright 回退的专用入口 | 验证码页不会被误判为正文 |
飞书文档 (feishu.cn/docx/, /wiki/, /docs/) | 内置飞书 API 脚本 | 需要 API 认证,自动转 Markdown |
| YouTube | 专用 YouTube skill | 视频内容有专用工具链 |
| arXiv / Hugging Face 论文 | 内置 LaTeX 源码提取 | 保留章节、公式、图片和表格 |
| PDF(远程 URL 或本地文件) | 内置 PDF 提取(extract_pdf.sh) | 三级 fallback:marker-pdf → pdftotext → pypdf |
| 其他所有 URL | 代理级联 fetch.sh:r.jina.ai → defuddle.md → agent-fetch | 免费、无需 API key、内置内容验证 |
python3 -m pip install playwright beautifulsoup4 lxml
python3 -m playwright install chromium
pip install marker-pdfbrew install popplerpip install pypdfnpx agent-fetch --help # 无需预装,npx 自动下载
FEISHU_APP_ID 和 FEISHU_APP_SECRET
echo $FEISHU_APP_ID # 验证已配置
npx skills add joeseesun/qiaomu-markdown-proxy
验证:
ls ~/.agents/skills/qiaomu-markdown-proxy/SKILL.md
直接给 Claude 发 URL:
维护者验证:
python3 ~/.agents/skills/qiaomu-meta-skill/scripts/validate_skill.py ~/.agents/skills/qiaomu-markdown-proxy
python3 -m unittest discover -s ~/.agents/skills/qiaomu-markdown-proxy/tests -p 'test_*.py'
内置 fetch_feishu.py 脚本,通过飞书开放 API 抓取文档内容并自动转为 Markdown:
FEISHU_APP_ID 和 FEISHU_APP_SECRET 环境变量docx:document:readonly 权限| 问题 | 解决方法 |
|---|---|
| 公众号返回“环境异常” | 使用 scripts/fetch_weixin.sh,它会识别验证页并回退 Playwright |
| 公众号浏览器抓取失败 | 运行 python3 -m playwright install chromium 安装浏览器 |
| 缺少 Python 依赖 | 安装 uv,或运行 python3 -m pip install playwright beautifulsoup4 lxml |
| 飞书文档返回权限错误 | 检查 FEISHU_APP_ID 和 FEISHU_APP_SECRET 环境变量,确认应用有文档读取权限 |
| 飞书知识库页面抓取失败 | 确认应用有 wiki:wiki:readonly 权限 |
| PDF 提取失败 | 安装任一工具:pip install marker-pdf、brew install poppler、pip install pypdf |
| r.jina.ai 返回空内容 | 自动降级到 defuddle.md(无需手动操作) |
| 所有代理都失败 | URL 可能有严格认证限制,尝试 npx agent-fetch |
MIT. Copyright (c) 向阳乔木.
多源内容智能处理器:任何内容 → 播客 / PPT / 思维导图 / Quiz
多源内容智能处理器:任何内容 → 播客 / PPT / 思维导图 / Quiz
让 AI 做出“不像默认 AI 模板”的设计:先看四个真实方向,再把选定界面实现并验收到可交付。 An opinionated Agent Skill for visual direction, implementation, and browser-based UI verification.
qiaomu-markdown-proxy is a Claude Code plugin with 1 hand-picked skill, indexed on Flowy in the Content category. Install it with the command on its page. It includes qiaomu-markdown-proxy. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it