$ loading_
Clean raw HTML into LAG-ready text and reduce wasted model tokens.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "Refinery MCP" MCP server from askskill: Run: claude mcp add 'io-github-cameronlares-refinery-mcp' -- npx -y @larelabs/refinery-mcp
Clean the following raw HTML into LLM-ready plain text. Remove scripts, styles, navigation, and ads, while preserving headings, body content, and list structure: {{html}}Structured plain text that can be directly passed to an LLM for summarization or Q&A.
Extract the main article content from this HTML, remove template noise, and output it in paragraphs for downstream vector indexing: {{html}}Cleaned main-body text suitable for chunking, embedding, and retrieval-augmented generation.
Preprocess scraped webpage HTML into concise text, keeping link text and heading hierarchy while removing irrelevant tags and duplicate content: {{html}}A cleaner, shorter text output ready for downstream analysis, classification, or information extraction.
Automatically repairs and polishes prompts to create clearer, more effective AI inputs.
Convert any URL into clean, LAG-ready Markdown, text, or HTML.
Clean AI-generated Markdown and export shareable HTML, PDF, DOCX, or PNG documents.
Rewrite rough prompts into optimized structured prompts for better LLM outputs.
Convert URLs into lean LLM-ready text with token and cost savings receipts.
Convert webpages into clean Markdown for archiving, extraction, and AI workflows.