Fetch web page content and convert HTML to clean Markdown.
npx skills add https://github.com/zephyrwang6/myskill --skill web-scraper-zephyrwang6
Please help me install this Agent Skill. Skill: web-scraper Source: https://github.com/zephyrwang6/myskill/tree/main/web-scraper Command: npx skills add https://github.com/zephyrwang6/myskill --skill web-scraper-zephyrwang6
This Skill helps users quickly access and convert web page content into readable Markdown, eliminating manual copy-paste and tedious formatting when researching online articles.
Run the fetch script to retrieve a URL and convert it to Markdown: python3 scripts/fetch_url.py "https://example.com/article"
Options: --timeout <seconds> (default: 30) --max-length <chars> (default: 100000) --raw Output raw HTML instead of Markdown
High-intent search queries and answers about installing and using this skill.
Use the fetch script to convert HTML pages to clean markdown: run `python3 scripts/fetch_url.py "https://example.com/article"`. The Skill fetches the page, strips navigation and ads, and outputs readable markdown while preserving structure for offline access or AI workflows.
Yes. This Skill automates HTML-to-markdown conversion, eliminating manual formatting. It fetches web page content via requests library, parses HTML, and returns clean text extraction—ideal for research, summarization, or feeding extracted content into downstream processes.
This Skill provides an alternative fetch mechanism using Python's requests library with fallback to urllib. It handles page retrieval when standard tools are unavailable, then converts the HTML to markdown for reliable content extraction.
Pass `--timeout <seconds>` (default: 30) and `--max-length <chars>` (default: 100000) flags to the fetch script. These options control request duration and limit markdown output size, accommodating different network conditions and content volume needs.
Yes. Use the `--raw` flag with the fetch script to retrieve unprocessed HTML. This option supports workflows requiring raw HTML parsing or custom post-processing before markdown conversion.
otrebuFetch multiple URLs with curl and aggregate content into a timestamped Markdown file.
zhangyanbo2007Extract text and metadata from PDFs with OCR and multiple output formats.
abdullah1854Crawl websites and extract content into Markdown, JSON, or text.
platonaiExtract titles, text, and structured fields from web pages using browser automation.
