Document Parser
Skill by ankylala
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/ankylala/document-parserWhat This Skill Does
The Document Parser skill is a robust, high-performance solution designed for OpenClaw agents to convert unstructured documents—including PDFs, images (JPG/PNG), and Word files (.docx)—into clean, structured, and machine-readable data. Powered by sophisticated OCR and layout analysis algorithms, it excels at identifying complex document elements such as tables, headers, paragraphs, and even official seals. By standardizing output into formats like Markdown or JSON, it bridges the gap between static files and actionable data, enabling seamless integration with downstream workflows or AI data processing pipelines.
Installation
To integrate this skill into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/ankylala/document-parser
After installation, you must configure your access credentials. You can set them via system environment variables (DOCUMENT_PARSER_API_KEY and DOCUMENT_PARSER_BASE_URL) or by creating a config.json file within the skill directory containing your authentication details. Ensure that your network allows communication with the designated base URL to retrieve parsing results.
Use Cases
This skill is ideal for enterprise document digitization, data extraction, and administrative automation. Use it for:
- Automated Invoice and Receipt processing: Extracting tabular line items for expense reports.
- Contract Digitization: Identifying clauses and validating document authenticity via seal detection.
- Legacy Document Archiving: Converting scanned historical records into editable and searchable Markdown files.
- Workflow Automation: Parsing specific page ranges from lengthy technical manuals to feed into RAG (Retrieval-Augmented Generation) systems.
Example Prompts
- "Document Parser, please parse the report at C:\docs\q3_financial.pdf and convert the tables into markdown for my summary."
- "Extract text and identify any official stamps on the scan located at C:\invoices\contract_v2.jpg. Enable layout analysis for better formatting."
- "Run a parse on pages 5 through 10 of my research document at D:\data\thesis.docx and export the content in JSON format."
Tips & Limitations
To achieve the best results, ensure your input files are of high resolution, especially when using the --seal or --table flags. Complex, multi-column layouts may occasionally require iterative testing with the --layout option enabled to refine structural accuracy. Note that document processing speed is dependent on file size and page count; for extremely large PDFs, it is recommended to process files in batches using the --pages argument to optimize performance and prevent timeout errors.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-ankylala-document-parser": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, external-api, network-access