An automated utility for converting multi-format documents into Markdown files optimized for Obsidian knowledge bases.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install knowledge-importer
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install knowledge-importer using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Knowledge Importer?
The Knowledge Importer is a sophisticated bridge designed to modernize static documents by converting them into dynamic, searchable Markdown files. As a core part of the Openclaw Skills ecosystem, this tool allows users to migrate legacy content from Word, Excel, PowerPoint, and PDF formats directly into a structured Obsidian vault. It solves the common friction of manually re-formatting research materials, reports, and technical manuals, ensuring that all valuable information is accessible within a unified personal knowledge management system.
Beyond simple text extraction, this skill handles complex elements like tables and embedded graphics. It ensures that images are preserved by either uploading them to a dedicated image hosting server or embedding them directly as Base64 strings, providing a versatile solution for maintaining visual context within text-based environments.
Knowledge Importer Use Cases
- Archiving legacy Word-based project reports into a centralized Obsidian knowledge base for better discoverability.
- Converting technical PDF whitepapers into Markdown notes to facilitate tagging, linking, and second-brain processing.
- Transforming Excel data tables into Markdown format for inclusion in software documentation.
- Batch processing entire folders of presentation decks to extract text and images for automated study summaries.
How Knowledge Importer Works
- The user initiates a conversion by providing a file path or directory to the Openclaw Skills execution script.
- The system identifies the file format and selects the appropriate parsing library, such as python-docx or pdfplumber.
- Content is extracted sequentially, identifying headers, paragraphs, and specialized structures like tables.
- Visual assets are extracted from the source file and processed based on the configuration: either uploaded to a remote server like Dufs or converted to a Base64 URI.
- The finalized Markdown content is generated with appropriate links and saved into the user's pre-configured Obsidian directory hierarchy.
Knowledge Importer Setup
To get started with this skill, install the required Python dependencies first:
pip3 install python-docx python-pptx openpyxl pdfplumber
Next, configure your environment variables to point to your image server and Obsidian vault:
# Configure image server URL
export DUFS_SERVER_URL="http://your-server-ip:port"
# Set your local knowledge base path
export KNOWLEDGE_BASE_PATH="/your/Obsidian/path"
Ensure that the Obsidian Command Line Interface (CLI) is enabled within your Obsidian settings under General -> Command line interface.
Knowledge Importer Data Schema & Taxonomy
The skill organizes converted documents into a standardized two-tier directory structure within the local vault. This ensures logical separation of content types as part of the Openclaw Skills workflow.
| Directory Category | Description of Content |
|---|---|
| /Proposals/ | Bids, tender documents, and construction schemes |
| /Solutions/ | Customer-facing solution architectures and documents |
| /Technical/ | Deployment guides, product manuals, and experience notes |
| /Other/ | Default catch-all for custom or unclassified documents |
All images are stored on the remote server using a UUID naming convention (e.g., /Picture/<uuid>.png) to prevent filename collisions.
Knowledge Importer Advanced Features
- Intelligent Image Fallback: Automatically switches to Base64 encoding if the primary image hosting server is offline.
- Batch Processing: Supports the
--batchflag to process entire directories of mixed-format files in a single pass. - Obsidian Integration: Uses the Obsidian CLI to programmatically create and append content, maintaining vault integrity.
- Table Preservation: High-fidelity conversion of Excel and PDF tables into standard Markdown table syntax.
SKILL.md
Loading
Related Openclaw Skills
Feishu Connect Skill
A high-efficiency skill designed to automate the initial registration and credential polling for Feishu robots within the AI agent ecosystem.
Match Board
A specialized dashboard for tracking AILove matching phases, managing pending questions, and receiving automated match updates.
Personal WeChat Connect Skill
A professional integration skill designed to link personal WeChat accounts to AI agents via the OpenClaw gateway.
WeCom Connect
A specialized skill for Openclaw to authorize and connect Enterprise WeChat (WeCom) bots via direct link interaction.
Comic Panel Generator
A specialized tool for generating professional AI comic panels, manga frames, and graphic novel illustrations directly from text descriptions.
a-stock
An AI agent skill designed to fetch real-time Chinese A-share market data and perform automated technical analysis.
Featured*
