An Intelligent Document Parsing (IDP) skill that converts complex documents like PDFs and spreadsheets into clean Markdown or structured JSON.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install miaoda-doc-parse
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 miaoda-doc-parse 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 miaoda-doc-parse?
The miaoda-doc-parse skill is a sophisticated Intelligent Document Parsing (IDP) utility designed to bridge the gap between unstructured documents and AI-ready data formats. It allows developers and AI agents to programmatically ingest content from a wide array of formats including PDF, Microsoft Office files, and structured data tables. As a versatile component within the Openclaw Skills ecosystem, it ensures that high-fidelity content extraction is accessible via a simple CLI interface.
By transforming documents into Markdown, this skill preserves structural integrity—such as headers and tables—while making the text fully searchable and digestible for LLMs. Whether you are dealing with local files or remote URLs, miaoda-doc-parse streamlines the data preparation phase of any automated workflow.
miaoda-doc-parse Use Cases
- Automating the extraction of text and tables from dense PDF reports and academic papers.
- Converting legacy Word documents and project proposals into Markdown for documentation sites.
- Parsing financial data from Excel or CSV files to be used in data analysis pipelines.
- Ingesting PowerPoint presentation content into knowledge management systems.
- Extracting clean text from HTML files without the overhead of a full web crawler.
How miaoda-doc-parse Works
- The skill receives a command with a specified file path or a direct download URL.
- The Intelligent Document Parsing engine identifies the file type and structure.
- Content is extracted, including the conversion of complex elements like tables into Markdown-compatible formats.
- The user can specify an output format, choosing between standard text (Markdown) or structured JSON.
- The resulting data is returned to the console or integrated into an automated AI agent workflow.
miaoda-doc-parse Setup
To use this skill, ensure your environment is configured for miaoda-studio-cli. You can execute parsing commands directly from your terminal:
# Parse a local document to Markdown
miaoda-studio-cli doc-parse --file "path/to/document.pdf"
# Parse a remote file and output as JSON for programmatic use
miaoda-studio-cli doc-parse --file "https://example.com/spreadsheet.xlsx" --output json
miaoda-doc-parse Data Schema & Taxonomy
The skill categorizes data based on the file extension and maps it to a unified output structure. Below is the mapping of supported formats:
| Category | Extensions | Typical Use Case |
|---|---|---|
| Portable Docs | Reports, Papers, Contracts | |
| Word Processing | .doc, .docx | Documentation, Proposals |
| Spreadsheets | .xlsx, .csv | Structured Data, Financials |
| Presentations | .pptx | Slides, Pitches |
| Web/Text | .html, .txt, .md | Raw Content, Web Snippets |
When using the --output json flag, the schema provides detailed metadata alongside the content body for advanced processing within Openclaw Skills.
miaoda-doc-parse Advanced Features
- Intelligent Table Extraction: Automatically converts complex Excel and PDF tables into clean Markdown or JSON arrays.
- Remote File Support: Supports direct parsing of documents hosted on external URLs without needing manual downloads.
- Multi-format Output: Switch between human-readable Markdown for documentation and machine-readable JSON for API integrations.
- High-Precision IDP: Utilizes Intelligent Document Parsing to maintain context and structure that standard OCR might lose.
- Seamless Integration: Designed to work in tandem with other Openclaw Skills for comprehensive research and data retrieval tasks.
SKILL.md
Loading
Related Openclaw Skills
Usage Stats
An automated diagnostic and reporting tool that analyzes session logs to provide comprehensive token usage and cost analytics.
Silicon Soul
Silicon Soul is a self-evolution methodology for AI Agents that fuses Eastern cultivation philosophy with modern algorithm engineering to drive continuous autonomous improvement.
Supa Guru Dojo API Skill
A lightweight skill for automated single-question challenge cycles via the Supa Guru Dojo API with built-in moral reflection and karma tracking.
Assistant Reliability Watchtower
A deterministic reliability monitoring tool for OpenClaw assistant workflows that automates smoke probes, scorecard validation, and daily health digests.
Luzia Crypto Data
A high-performance cryptocurrency market data integration for fetching real-time prices and historical OHLCV data.
Architecture Characteristics Identifier
A systematic framework for AI agents to identify, categorize, and prioritize the technical -ilities that drive software architecture decisions.
Featured*
