# Read Url

> Read and extract content from a URL with fallback Arguments: <url> [--format <markdown|json|screenshot>].

- Skill: `agents-store/read-url` (Agent Skill)
- Install (CLI): `npx get-skill add agents-store/read-url`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agents-store/read-url/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Docs & Writing
- Author: agents-store (https://skillmd.com/u/agents-store)
- Updated: 2026-11-16
- Page: https://skillmd.com/skills/agents-store/read-url

---


# Read URL

Read and extract content from a web page or PDF. Follow `${CLAUDE_PLUGIN_ROOT}/skills/content-extraction/SKILL.md` for the provider fallback chain and the extraction modes. See CONNECTORS.md for provider mapping.

## Process

1. **Detect content type** from URL:
   - `.pdf` → use PDF extraction
   - Regular URL → use ~~scrape with fallback

2. **Read content** with fallback (~~scrape):
   ```
   Try each provider: Jina → Firecrawl → Exa fetch (maxCharacters: 20000)
   On error → next provider automatically
   Long page and a specific question? pass it as `question` to get only the relevant passages
   ```

3. **Optional extras:**
   - `--format screenshot` → capture page screenshot
   - `--format json` → structured JSON extraction (~~extract, one URL per call)
   - Check publish date → detect page date

4. **Display** extracted content with source URL and date.

## Example Usage
```
/read-url https://example.com/article
/read-url https://arxiv.org/pdf/2301.00001
/read-url https://spa-app.com/page --format screenshot
```
