Extract and normalize text from URLs, PDFs, documents, and media.
npx skills add https://github.com/lfnovo/content-core --skill content-core
Please help me install this Agent Skill. Skill: content-core Source: https://github.com/lfnovo/content-core/tree/main Command: npx skills add https://github.com/lfnovo/content-core --skill content-core
Content Core removes the hassle of manually copying and cleaning content from websites, documents, and media so you can quickly read, analyze, or summarize what you need.
Ask the agent: "Extract the text from https://example.com and summarize it in bullet points."
High-intent search queries and answers about installing and using this skill.
To extract text from a URL and summarize it, you can use content-core to pull readable text from web pages and pass it to an LLM for concise summarization with optional context. This workflow normalizes web content for deterministic retrieval.
Yes, YouTube transcript extraction is fully supported. The Skill pulls transcripts directly from YouTube videos and normalizes the text so you can immediately feed the content into an LLM-based summarization workflow.
The best way to extract text from PDFs and office documents is using an engine routing system that automatically selects the optimal extraction method. This approach normalizes DOCX, PPTX, XLSX, and EPUB files into clean text.
Yes, audio transcription supports engine fallbacks. If the primary extraction engine fails, the system automatically falls back to alternative configured engines to ensure your audio and video files are successfully transcribed.
Yes, you can expose both content extraction and summarization as MCP tools for Claude Desktop and other MCP clients. This integration allows your AI assistant to directly retrieve and normalize text from various sources.
Web scraping handles content normalization by implementing a unified async extraction workflow. This process cleans and normalizes complex web pages into readable text, ensuring the output is ready for LLM-based summarization without manual copying.
PabloGarciaFuentesBuild Astro islands with client directives, Zod schemas, and SSR adapters.
dawsonblockConvert PDF-like files into normalized Markdown text using Python regex extraction.
SignmanalStore and query vector embeddings with metadata filtering for RAG applications.
buda-aiExtract and enhance audio from video files for MP3/WAV/AAC output.
