obsidian-dataweave

Name: obsidian-dataweave
Availability: InStock
Author: howdeploy

Import and process .docx documents into Obsidian Zettelkasten notes with tags and wikilinks.

43|4|Updated Feb 26, 2026

Search Tags:#document processing #obsidian #notebooklm #deep research #zettelkasten #llm wiki

Ready to run

npx skills add https://github.com/howdeploy/ObsidianDataWeave --skill obsidian-dataweave

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: obsidian-dataweave
Source: https://github.com/howdeploy/ObsidianDataWeave/tree/main
Command: npx skills add https://github.com/howdeploy/ObsidianDataWeave --skill obsidian-dataweave

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python-docx, PyYAML, notebooklm-py, rclone, python-docx, PyYAML, notebooklm-py, rclone, Claude Code, Codex, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the management of your Obsidian vault by automating deep research, document processing, and the creation of an LLM Wiki.

Core Features & Use Cases

Deep Research: Conduct research directly into NotebookLM notebooks with deduplication and error-state cleanup.
Document Processing: Import and process .docx documents into Zettelkasten notes with MOC, tags, and wikilinks.
LLM Wiki: Create an isolated LLM Wiki layer for compiling knowledge and searching across your entire vault.
Use Case: With this Skill, you can easily import a research document into your Obsidian, process it into structured notes, and then build a comprehensive knowledge base using the LLM Wiki feature.

Quick Start

Tell Claude Code or Codex to 'Process the document "MyResearchDocument.docx"' to automatically import and process your research document into your Obsidian vault.

Frequently Asked Questions about obsidian-dataweave

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I import .docx documents into an Obsidian vault as structured notes?▼

To import .docx documents into an Obsidian vault, this Skill uses Python and Claude Code APIs to atomize files into Zettelkasten notes, automatically generating MOCs, tags, and wikilinks for structured knowledge management.

What is the best way to build an LLM Wiki for deep research inside Obsidian?▼

Building an LLM Wiki inside Obsidian involves creating an isolated compilation layer that searches across your entire vault, using NotebookLM integration and Claude Code APIs to process and deduplicate deep research materials.

Do I need rclone and Python dependencies to process documents in Obsidian?▼

Yes, you need rclone, Python libraries like python-docx and PyYAML, and notebooklm-py to automate document import, processing, and search indexing within your Obsidian vault environment.

Can I use NotebookLM to conduct deep research directly into my Obsidian notes?▼

Yes, you can conduct deep research directly into NotebookLM notebooks, which this Skill integrates with your Obsidian vault while providing deduplication and error-state cleanup for your notes.

How does document atomization work when processing research files for Zettelkasten?▼

Document atomization works by breaking down imported .docx research files into discrete Zettelkasten notes, automatically tagging them and establishing wikilinks to maintain connectivity within your Obsidian vault.

What are the limitations of using Claude Code APIs for Obsidian document processing?▼

Limitations include requiring specific environments like Claude Code or Codex APIs, alongside dependencies such as rclone and Python libraries, meaning document processing cannot run independently without these external tools.