Convert URLs into Markdown with traceable source metadata.
npx skills add https://github.com/blessonism/openclaw-skills --skill content-extract
Please help me install this Agent Skill. Skill: content-extract Source: https://github.com/blessonism/openclaw-skills/tree/main/content-extract Command: npx skills add https://github.com/blessonism/openclaw-skills --skill content-extract
This skill centralizes the transformation of a URL into a readable, Markdown-formatted document with a traceable source contract, enabling downstream OpenClaw workflows to rely on consistent inputs.
Convert the given URL into clean, Markdown-formatted output with traceable source links.
High-intent search queries and answers about installing and using this skill.
To convert a URL to Markdown, the skill first probes the page via web_fetch. If the site blocks the probe or renders dynamically, it falls back to MinerU, returning a clean Markdown document with traceable source links for analysis.
Yes, you can extract README and metadata from a GitHub repository URL using a dedicated fast path. This bypasses unreliable client-side rendering to directly fetch repository metadata and return clean, Markdown-formatted content.
The best way to extract content from anti-bot or dynamic web pages is using MinerU as a fallback. The extraction process initially attempts a cheap web_fetch probe, then automatically switches to MinerU for sites that block the initial probe.
Yes, web content extraction supports a domain whitelist feature. You can configure specific domains to skip the initial web_fetch probing step, streamlining the extraction process for trusted sources and returning Markdown output faster.
URL content extraction returns a unified Result Contract with source traceability to ensure downstream workflows receive consistent inputs. It includes fields like source_url, engine, markdown, artifacts, and sources, guaranteeing reliable data lineage.
The limitation of using web_fetch for URL to Markdown conversion is its inability to bypass anti-bot mechanisms or render dynamic content. When web_fetch fails on such sites, the extraction automatically falls back to MinerU.
shariqazeemConfigure Starknet RPC endpoints with authenticated tokens and CORS whitelists via slot CLI.
reflecttPoll the public feed and convert findings into Markdown artifacts.
LawMotion-AIConvert legal texts from TXT, DOCX, and PDF into structured Markdown.
dennislee928Scrapes and crawls websites into LLM-ready markdown or JSON.
