A high-performance conversion tool that turns PDFs, Office documents, images, and audio into LLM-ready Markdown.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install markdown-anything
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 markdown-anything 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 Markdown Anything?
Markdown Anything is a powerful utility designed for Openclaw Skills users who need to bridge the gap between static documents and AI-ready text. By leveraging the Markdown Anything API, this skill allows developers to convert over 25 file formats—including complex PDFs, DOCX files, spreadsheets, and even audio—into clean, structured Markdown text.
This skill ensures that context-heavy documents can be easily digested by LLMs for better reasoning and prompt engineering. It provides a streamlined interface for local conversion scripts, allowing agents to automate the extraction of data from unstructured sources without manual copy-pasting. Whether you are dealing with scanned images or multi-page reports, this integration maintains the semantic structure of your content for optimal performance in any Openclaw Skills environment.
Markdown Anything Use Cases
- Extracting structured text from complex PDF reports for LLM analysis.
- Converting DOCX or PPTX documentation into Markdown for technical wikis.
- Transforming spreadsheets (XLSX) into Markdown tables for easier data manipulation.
- Utilizing OCR through Enhanced AI to process scanned documents and images.
- Converting audio files into text-based formats for summarization tasks within Openclaw Skills.
How Markdown Anything Works
- The user provides a file path to the mda-convert tool via the CLI or an agent command.
- The script checks for the required MDA_API_TOKEN and any optional configuration flags.
- The file is securely transmitted to the Markdown Anything API endpoint for processing.
- The API parses the document structure, applies OCR if necessary, and generates clean Markdown.
- The resulting Markdown is piped to stdout, ready for the AI agent to use in its context window or save to a file.
Markdown Anything Setup
To get started with this skill, you must obtain an API token from your Markdown Anything workspace. Set the token as an environment variable in your terminal:
export MDA_API_TOKEN=mda_your_token_here
Ensure the scripts in the directory are executable. You can then run conversions directly using the provided shell script:
scripts/convert.sh /path/to/your/document.pdf
You can also check your remaining credit balance at any time:
scripts/credits.sh
Markdown Anything Data Schema & Taxonomy
The skill operates on a request-response model via the API. The output is structured to be compatible with Openclaw Skills workflows.
| Feature | Description |
|---|---|
| Input Formats | PDF, DOCX, XLSX, PPTX, JPG, PNG, MP3, and 25+ others. |
| Output Format | Clean, LLM-optimized Markdown string. |
| Metadata | Optional JSON-like metadata block included if MDA_INCLUDE_METADATA is enabled. |
| Token Efficiency | Minimized whitespace and optimized structure for LLM context windows. |
Markdown Anything Advanced Features
- Enhanced AI mode for high-accuracy OCR on low-quality scans and images.
- Token optimization to reduce the footprint of the output for LLM context windows.
- Metadata extraction to capture document properties alongside the text content.
- Credit management via the mda-credits tool to monitor API usage in real-time.
- Cross-format support covering over 25 distinct file types within a single Openclaw Skills environment.
SKILL.md
Loading
Related Openclaw Skills
Maps
A location-intelligence skill providing geocoding and routing capabilities without requiring external API keys.
Jina AI Reader & Search
A comprehensive toolset for converting web pages to LLM-friendly markdown and performing multi-step deep research.
MacPilot Skills
A suite of automation skills that allow AI agents to control macOS via Accessibility APIs, handling everything from window management to OCR-based interactions.
Halocard Virtual Cards
Generate single-use virtual credit cards on the fly to complete secure online payments during automated agent tasks.
Swiggy Skill for Openclaw
Connect your AI agent to Swiggy to automate food delivery, Instamart grocery shopping, and Dineout restaurant bookings in India.
Self-Improvement Skill
A specialized framework for AI agents to capture, analyze, and promote technical learnings and errors into permanent project memory.
Featured*
