A robust document processing tool for extracting plain text and structured table data from multiple file formats for AI analysis.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install mjk39966-document-parser
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 mjk39966-document-parser 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 Document Parser?
Document Parser is a specialized utility designed to bridge the gap between static files and AI-driven analysis. As a key component of the Openclaw Skills ecosystem, it provides a streamlined interface to ingest .docx, .pdf, and .txt files, transforming them into machine-readable JSON or human-readable text.
This skill is particularly effective for developers and researchers who need to automate the extraction of content from complex layouts. By integrating this within the Openclaw Skills framework, users can enable their AI agents to accurately interpret quarterly reports, legal documents, and large manuscripts with high fidelity and metadata awareness.
Document Parser Use Cases
- Extracting financial data from tables within corporate quarterly reports.
- Converting legacy PDF documentation into plain text for LLM fine-tuning or RAG pipelines.
- Automating the reading of Word-based contracts to identify specific clauses.
- Analyzing batch text files to summarize key insights across multiple documents.
How Document Parser Works
- The user provides a document path to the Document Parser script.
- The system identifies the file extension and selects the appropriate parsing engine (python-docx, PyPDF2, or pdfplumber).
- It extracts raw text while maintaining the logical flow of paragraphs and structural integrity of tables.
- The extracted content is packaged into a structured JSON object containing text, nested table arrays, and file metadata.
- The AI agent or user utilizes this structured data to perform final analysis or answer specific queries.
Document Parser Setup
To integrate this into your environment, first install the necessary dependencies for these Openclaw Skills:
Linux/macOS
bash scripts/install_dependencies.sh
Windows
scripts\install_dependencies.bat
Once dependencies are installed, you can parse any document using the following command:
python scripts/parse_document.py /path/to/your/document.pdf
Document Parser Data Schema & Taxonomy
The Document Parser generates a standardized schema to ensure compatibility across different Openclaw Skills workflows:
| Field | Type | Description |
|---|---|---|
text |
String | The full concatenated text content of the document. |
tables |
Array | A list of tables, where each table is represented as a 2D array of rows and cells. |
metadata |
Object | Includes format type (pdf/docx/txt), page count, and total tables found. |
Example JSON structure:
- text: "Full document content..."
- tables: [[["Header1", "Header2"], ["Value1", "Value2"]]]
- metadata: {"format": "pdf", "pages": 5, "tables": 2}
Document Parser Advanced Features
- Multi-format support covering modern Word documents, PDFs, and legacy text files.
- Human-readable output mode using the
--format textflag for quick manual inspections. - Metadata generation for tracking document length and extraction complexity.
- Optimized table extraction for PDFs with clear borders using the pdfplumber engine.
- Seamless integration as a pre-processing step for sophisticated Openclaw Skills analysis agents.
SKILL.md
Loading
Related Openclaw Skills
PDFelement Skill
A local PDF productivity skill that enables AI agents to execute batch operations like OCR, conversion, and security through Wondershare PDFelement.
FTShare A-Share Performance Data
A comprehensive financial data skill for retrieving A-share performance express reports, forecasts, and core financial statements across the Chinese market.
Data Scatter Plot Generator
A high-performance data visualization tool that transforms CSV and Excel datasets into professional scatter plots with automated limit line detection.
PancakeSwap Harvest Rewards
An AI-powered reward tracker that identifies pending CAKE and partner-token rewards across PancakeSwap farms and pools.
Apify Key Rotator
A smart API key management system that rotates Apify keys based on least-recently-used logic and real-time balance checking.
Video Subtitle Translate
A high-performance AI tool for translating subtitles in existing HTTPS videos using the WeryAI API.
Featured*
