A high-performance OCR skill that utilizes the GITEE AI API to extract, recognize, and summarize text from image files.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install moark-ocr
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 moark-ocr 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 Moark OCR?
Moark OCR is a specialized tool within the ecosystem of Openclaw Skills designed to provide developers and AI agents with visual perception capabilities. By connecting to the GITEE AI API, this skill allows users to transform static images, screenshots, and scanned documents into actionable text data.
Unlike traditional OCR tools that simply output raw text, Moark OCR leverages prompt-based logic to summarize the recognized content according to specific user requirements. This makes it an essential component for developers building automated workflows that need to interpret visual information accurately and contextually.
Moark OCR Use Cases
- Extracting snippets of code or error messages from screenshots during debugging sessions.
- Digitizing data from physical receipts, invoices, or business cards for automated bookkeeping.
- Summarizing core insights from complex infographics or slide deck images.
- Converting non-selectable text in PDF screenshots into editable Markdown format.
How Moark OCR Works
- The user initiates a request by providing an image path and a descriptive prompt for the extraction.
- The system invokes the internal Python script, passing the GITEE AI credentials and image parameters.
- The script processes the image via the external API and generates a structured response containing the recognized text.
- The agent parses the standard output to identify the specific OCR_RESULT tag.
- The final output is rendered in Markdown, featuring an emoji-enhanced header and a contextual summary that strictly follows the user's initial instructions.
Moark OCR Setup
To get started with this component of your Openclaw Skills library, install the required dependencies and configure your API access:
pip install openai
You must also set your GITEE AI API key as an environment variable or pass it directly through the CLI:
export GITEEAI_API_KEY="your_api_key_here"
python scripts/perform_ocr.py --image ./path/to/document.png --prompt "Summarize the main headings" --api-key $GITEEAI_API_KEY
Moark OCR Data Schema & Taxonomy
The skill manages data through a CLI-based input-output pipeline. The following table describes the data structure utilized:
| Attribute | Description | Requirement |
|---|---|---|
--image |
Path to the source image file (JPG, PNG, etc.) | Required |
--prompt |
Natural language instructions for text processing | Required |
GITEEAI_API_KEY |
Authentication token for the AI backend | Required |
OCR_RESULT: |
The prefix used to identify valid extracted text in the logs | System Generated |
Moark OCR Advanced Features
- Prompt-driven summarization: Beyond simple extraction, the skill filters and summarizes text based on your specific needs.
- Error handling for missing credentials: Automatically prompts the user if the primary API environment variable is not detected.
- Markdown-ready output: Results are formatted with specific icons for immediate use in documentation or chat interfaces.
- No-hallucination policy: The skill is configured to repeat user requirements honestly without adding imaginary details to the OCR results.
SKILL.md
Loading
Related Openclaw Skills
WeryAI Video Watermark Removal
A specialized technical skill for removing watermark overlays from existing HTTPS videos using the WeryAI API.
Milvus Vector Database
A high-performance skill for operating Milvus vector databases to handle high-dimensional data, similarity searches, and RAG workflows via the pymilvus SDK.
Echo Developer Guide
A comprehensive integration guide for developers to build applications on AINative and earn revenue through customizable API markups.
Architecture Inventory & Risk Assessment
A professional tool for managing Tencent Cloud architecture blueprints, evaluating Well-Architected scores, and identifying governance risks.
Apache ORC Storage Specialist
A comprehensive reference for the Apache ORC columnar storage format, covering file architecture, compression codecs, and cross-engine integration.
cuihua-i18n-helper
An AI-powered internationalization assistant that automates string extraction, multi-language translation, and quality assurance for modern web applications.
Featured*
