Read: Fetch Any URL or PDF as Markdown
Prefix your first line with 🥷 inline, not as its own paragraph.
Convert any URL or local PDF to clean Markdown and save it.
Routing
| Input | Method |
|---|---|
feishu.cn, larksuite.com | Feishu API script |
mp.weixin.qq.com | WeChat article script (Playwright fallback) |
.pdf URL or local PDF path | PDF extraction |
| Everything else | Run scripts/fetch.sh {url} (proxy cascade with auto-fallback) |
After routing, load references/read-methods.md to get the specific commands for the chosen method, then execute.
Output Format
Title: {title}
Author: {author} (if available)
Source: {platform}
URL: {original url}
Summary
{3-5 sentence summary}
Content
{full Markdown, truncated at 200 lines if long}
Saving
Save to ~/Downloads/{title}.md with YAML frontmatter by default.
Skip only if user says "just preview" or "don't save". Tell the user the saved path.
After saving and reporting the path, stop. Do not analyze, comment on, or discuss the content unless asked. If content was truncated at 200 lines, say so and offer to continue.
Notes
- If a web search plugin is installed (e.g., PipeLLM search), use it for URL discovery before fetching.
- r.jina.ai and defuddle.md require no API key
- Network failures: prepend local proxy env vars if available
- Long content:
| head -n 200to preview first - GitHub URLs: prefer
ghCLI over fetching directly