read
GitHub将任意URL或PDF转换为纯净Markdown并保存。支持绕过付费墙、JS渲染页面及特定平台（GitHub/X）。严格禁止内容分析，仅负责提取与存储，自动处理文件名冲突及图片下载。
Trigger Scenarios
Install
npx skills add NeverSight/learn-skills.dev --skill read -g -y
SKILL.md
Frontmatter
{
"name": "read",
"metadata": {
"version": "1.0.0"
},
"description": "Fetches any URL or PDF as clean Markdown via a proxy cascade. Handles paywalls, JS-heavy pages, GitHub, X\/Twitter, and PDFs. Always prefer this over WebFetch for any URL. Not for local text files or source code already in the repo.",
"when_to_use": "any URL in message, read this, check this URL, summarize this link, fetch this page, open this PDF"
}
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. No analysis, no summary, no discussion of the content unless explicitly asked.
Routing
| Input | Method |
|---|---|
.pdf URL or local PDF path |
PDF extraction |
GitHub URLs (github.com, raw.githubusercontent.com) |
Prefer raw content or gh first. Use the proxy cascade only as fallback. |
x.com, twitter.com |
Proxy cascade (r.jina.ai keeps image URLs). Do not try WebFetch; it 402s. |
| Everything else | Proxy cascade |
After routing, load references/read-methods.md and run the commands for the chosen method.
Output Format
Title: {title}
Author: {author} (if available)
Source: {platform}
URL: {original url}
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.
If ~/Downloads/{title}.md already exists, append -1, -2, etc., to the filename. Never overwrite an existing file without explicit confirmation.
Images
By default only save Markdown. Download images only when the user explicitly asks: "download images" or "save images".
When asked, after saving the Markdown:
- Extract image URLs:
grep -oE 'https?://[^ )"]+\.(jpg|jpeg|png|webp|gif)' {md_path} | sort -u - Create
~/Downloads/{title}-images/and curl each URL in parallel (&+wait). Use the same proxy env vars as the fetch step. - Report the count and folder path. If any download fails, list the failed URLs.
Hard Rules
- Do not summarize or analyze the content. Your job is conversion and storage, not interpretation.
- Never overwrite without confirmation. If the target filename already exists, use an auto-incremented suffix.
- Stop after the save report. Do not suggest follow-up actions unless the user asks.
Gotchas
| What happened | Rule |
|---|---|
| Fetched a paywalled article and returned a login page as Markdown | Inspect the first 10 lines for paywall signals ("Subscribe", "Sign in", "Continue reading"). If found, stop and warn the user. Do not save the login page. |
| r.jina.ai or defuddle.md returned empty for a JS-heavy site | Try the local fallback (agent-fetch or defuddle parse) before giving up. |
| Network failures | Prepend local proxy env vars if available and retry once. |
| Long content | Preview with head -n 200 first; mention truncation when reporting the save. |
| Local fallback tools returned JSON | Extract the Markdown-bearing field. Raw JSON is not a valid final output for /read. |
| All methods failed | Stop and tell the user what was tried and what failed. Suggest opening the URL in a browser or providing an alternative. Do not silently return empty or partial results. |
Content Extraction for Restyling
Activate when: "extract content", "reformat this document", or user hands over a document to restyle
Extract and tag:
- Headings: H1/H2/H3 hierarchy
- Body paragraphs: Plain text, no styling
- Lists: Bullet vs numbered, nesting level
- Metrics/data: Numbers, dates, quantifiable claims
- Images/diagrams: Descriptions, captions
Output: Clean, tagged content ready to feed into downstream tools.
Version History
- e0220ca Current 2026-07-05 21:27
