A powerful OCR tool that converts screenshots, photos, and scanned documents into clean Markdown text using the MinerU Open API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install image-to-markdown
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 image-to-markdown 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 Image to Markdown?
The Image to Markdown skill is a high-performance OCR utility designed for developers and AI agents who need to bridge the gap between visual media and structured text. By leveraging the MinerU Open API, this tool allows for seamless extraction from various formats including PNG, JPG, and WebP without the friction of API keys or complex sign-up processes.
Integrating this into your workflow via Openclaw Skills ensures that visual data—whether from a whiteboard session or a system screenshot—is immediately available as editable, searchable Markdown. It is built to handle both local files and direct URLs, making it an essential component for automated data entry and documentation pipelines.
Image to Markdown Use Cases
- Extracting technical text or code snippets from shared screenshots in development channels.
- Converting photos of physical documents, whiteboards, or receipts into digital Markdown notes.
- Automating content ingestion by processing image URLs directly without manual downloads.
- Facilitating AI agent understanding of visual context by providing a text-based representation of images.
How Image to Markdown Works
- The user provides a local image path or a web URL to the CLI tool.
- The skill triggers the mineru-open-api flash-extract command to initiate the process.
- The image is uploaded to the MinerU cloud API for real-time OCR analysis.
- Text is recognized based on the specified language hint (defaulting to Chinese or English).
- The tool streams the extracted content back to the terminal or saves it as a .md file in the designated output directory.
Image to Markdown Setup
You can install the necessary components for this Openclaw Skills extension using your preferred package manager:
# Install via npm
npm install -g mineru-open-api
# Or install via uv
uv tool install mineru-open-api
# Or install via Go (macOS/Linux)
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api
Image to Markdown Data Schema & Taxonomy
The skill manages data primarily through the CLI interface and the MinerU cloud processing layer.
| Feature | Specification |
|---|---|
| Supported Formats | PNG, JPG, JPEG, WebP, BMP, TIFF |
| File Size Limit | Maximum 10MB per image |
| Output Type | Raw Markdown text or .md file |
| Privacy | Real-time processing; no persistent storage of uploaded images |
Image to Markdown Advanced Features
- Direct URL Support: Process remote images instantly without saving them to your local disk first.
- Language Hinting: Improve OCR accuracy for specific regions using the
--languageflag (e.g.,enfor English). - Zero-Config Auth: Use the
flash-extractfeature for immediate results with no API key required. - Custom Output Directories: Use the
-oflag to organize large batches of extracted text into specific folders.
SKILL.md
Loading
Related Openclaw Skills
Article Collect
A lightweight tool for AI agents to bookmark, organize, and manage article URLs and summaries.
FTShare Fund Data
A comprehensive financial data connector providing detailed mutual fund metrics, net asset values, and performance history via a unified routing interface.
Daily Report Generator
An automated documentation tool that converts raw work descriptions into structured, professional daily and weekly reports.
Dajiala WeChat Article Fetcher
A specialized automation tool for fetching WeChat Official Account article links and metadata via the Dajiala API and exporting them to Excel.
Baidu Document Parser
An advanced document processing engine that converts complex PDFs, images, and Office files into structured data for RAG and LLM applications.
UX Writing (Deep Workflow)
A comprehensive deep-dive workflow for designing interface text that reduces cognitive load, prevents errors, and builds user trust.
METADATA
Featured*
