Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Extracts clean markdown content from any URL using the Jina Reader API. Handles HTML complexity, JavaScript rendering, and many paywalls, returning structured text with metadata including title, URL, and published time. Output works directly with AI analysis or other command-line tools.
Bypasses JavaScript rendering and many paywalls that simple HTTP fetchers miss, returning clean structured markdown without requiring custom HTML parsing.
When to use it
- Summarizing news articles without parsing HTML
- Extracting text from search result URLs during research
- Batch converting a list of URLs to markdown files
- Piping article content into grep or word count tools
- Feeding webpage text into downstream AI processing
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Get the content of https://example.com/article with its metadata
- 1Run jina-reader.py with the URL and --format json flag
- 2Receive JSON response containing title, URL, published date, and content fields
- 3Extract the content field for the full markdown text
- 4Return structured metadata and content to the user
JSON object with article title, canonical URL, published date, and full markdown body text