Read Url

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

agents-store Updated 0 repo stars

File contents

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

Agents-Store/codex-plugins commit 1813048876

Frequently asked questions

npx get-skill add agents-store/read-url