Convert mixed document corpora into an LLM-optimized knowledge base with manifest indexing.
npx skills add https://github.com/zevtos/agentpipe --skill doc2kb
Please help me install this Agent Skill. Skill: doc2kb Source: https://github.com/zevtos/agentpipe/tree/main/skills/doc2kb Command: npx skills add https://github.com/zevtos/agentpipe --skill doc2kb
doc2kb turns a folder of heterogeneous documents into an LLM-optimized knowledge base that can be ingested in a separate Claude/Codex session, without losing content via summarization.
Ask the agent to ingest and index a mixed document folder by running doc2kb on your corpus path so it outputs a ready-to-ingest knowledge base.
High-intent search queries and answers about installing and using this skill.
To prepare mixed documents for RAG ingestion without losing content, you need a knowledge base preprocessing tool that extracts text verbatim from heterogeneous formats. This skill converts PDFs, DOCX, and HTML into per-source Markdown files with YAML frontmatter, ensuring strict verbatim preservation for downstream LLM indexing.
The best way to convert mixed-format corpora into a unified knowledge base for LLM indexing is through structured per-source extraction. This process parses PDF, DOCX, PPTX, and HTML files into individual Markdown files, generating a manifest.json and INDEX.md for selective AI retrieval.
Yes, you can extract text from scanned or math-heavy PDFs for a local knowledge base using optional VLM-grade recovery. The system detects problematic PDFs with ligature issues or mangled visual math and applies an opt-in VLM tier to recover content safely during ingestion.
RAG preparation works with local-first document extraction for Jupyter notebooks, TXT, and Markdown files by applying deterministic local extraction. It processes mixed inputs into a unified KB layout, producing llms.txt and AGENTS.md files so AI can selectively read relevant documents via filenames and headings.
PDF conversion drops figures and mangles math formulas during LLM indexing due to ligature issues and complex visual math structures. The extraction system detects these problematic PDFs and offers an optional VLM-grade MinerU tier to recover dropped figures and mangled visual math safely.
No, you do not need to summarize documents before adding them to a knowledge base for Claude. This ingestion workflow applies structured per-source extraction that keeps document content verbatim, allowing an AI to selectively read only relevant documents without losing content through summarization.
findinfinitelabsProcess large DOCX, PDF, and text documents into structured, memory-efficient representations.
All-The-VibesDocument solved problems as categorized YAML-frontmatter markdown files.
dparedesiMerge YouTube channel transcripts into one markdown file within token limits.
ShunmeiChoExtract text, tables, and form data from PDFs using Python libraries.
