docx
01Skill Claude CodeCodex
Extract text from Microsoft Word documents.
Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.
Synthadoc is an open-source knowledge compilation engine that uses an LLM to turn source documents into a structured, cross-referenced wiki made from local Markdown files. It is for researchers, teams, and organizations that need a maintainable domain knowledge base, with interfaces including a CLI, Obsidian, a web UI, and MCP; the catalogue entries provide agent skills for operating its workflows.
Skill Claude CodeCodex
Extract text from Microsoft Word documents.
Skill Claude CodeCodex
Extract text from images using a vision LLM.
Skill Claude CodeCodex
Ingest Markdown and plain text files.
Skill Claude CodeCodex
Extract text from PDF documents.
Skill Claude CodeCodex
Extract text from Microsoft PowerPoint presentations.
Skill Claude CodeCodex
Extract conversation turns from AI session history files (.jsonl).
Skill Claude CodeCodex
Fetch and extract text from web URLs.
Skill Claude CodeCodex
Search the web and ingest results as wiki pages.
Skill Claude CodeCodex
Extract data from Excel and CSV files.
Skill Claude CodeCodex
Extract transcripts from YouTube videos via the YouTube caption system.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: