Setup & Installation
openclaw skills install @mattvalenta/pls-url-to-markdown
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install pls-url-to-markdown
What This Skill Does
Fetches web pages and converts HTML content to clean Markdown using Python libraries or CLI tools. Supports article body extraction, code block preservation, and retry logic for failed requests.
Stripping HTML to clean Markdown removes navigation, ads, and boilerplate that inflate token usage and reduce LLM response quality.
When to use it
- Converting blog posts into Markdown for a local knowledge base
- Feeding article content to an LLM without HTML noise
- Archiving documentation pages as plain text files
- Extracting main content from news articles for summarization
- Batch converting web pages to Markdown for offline reading
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: convert https://example.com/article to Markdown
AGENT
- 1Fetch the URL using the requests library
- 2Parse HTML with BeautifulSoup to locate article or main element
- 3Convert extracted HTML fragment to Markdown using markdownify
- 4Preserve code blocks with triple-backtick formatting
- 5Write output to a .md file or return as string
OUTPUT
A clean Markdown file containing only the article body with properly formatted headings, links, and code blocks