← Back to Skills Marketplace
342
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install ocr-skill-test
Description
Extract text from images using Tesseract.js OCR. Supports Chinese (simplified/traditional) and English.
Usage Guidance
This skill appears to do only local OCR and needs only Node plus the tesseract.js npm package. Before installing: (1) be aware first run will download Tesseract language data (~20MB per language) from upstream/CDN — ensure network access and trust the source; (2) images are processed locally, but do not feed it sensitive images unless you trust the host machine; (3) you can inspect package.json and scripts/ocr.js (included) to confirm no unexpected network endpoints or secret usage; (4) if you require air-gapped operation, block network access or pre-provision the traineddata files.
Capability Analysis
Type: OpenClaw Skill
Name: ocr-skill-test
Version: 1.0.0
The skill provides legitimate OCR functionality using the well-known 'tesseract.js' library. The implementation in 'scripts/ocr.js' is straightforward, handling file paths and arguments safely without any use of dangerous functions like eval() or shell execution. No evidence of data exfiltration, persistence mechanisms, or malicious prompt injection was found across the documentation or code.
Capability Assessment
Purpose & Capability
Name/description match the provided files: a Node script that calls tesseract.js to OCR local images. Required binary (node) and the dependency (tesseract.js) are appropriate and proportionate.
Instruction Scope
SKILL.md and scripts/ocr.js restrict activity to reading a user-supplied image file and running Tesseract locally. The README/SKILL.md correctly note first-run language-data downloads (~20MB/lang). There is no code that reads unrelated files or accesses environment variables. Note: traineddata will be fetched from upstream/CDN by tesseract.js on first run (download-only); this is expected but does involve network access.
Install Mechanism
No custom install script is bundled; package.json depends on tesseract.js from npm which is a normal, auditable source. No arbitrary URL downloads or archive extraction in the skill itself.
Credentials
The skill requests no environment variables or credentials. The lack of secrets is proportionate to the stated purpose.
Persistence & Privilege
always is false; the skill does not modify other skills or require persistent elevated privileges. It will cache downloaded language data locally (expected behavior).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install ocr-skill-test - After installation, invoke the skill by name or use
/ocr-skill-test - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release
Metadata
Frequently Asked Questions
What is OCR Test?
Extract text from images using Tesseract.js OCR. Supports Chinese (simplified/traditional) and English. It is an AI Agent Skill for Claude Code / OpenClaw, with 342 downloads so far.
How do I install OCR Test?
Run "/install ocr-skill-test" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is OCR Test free?
Yes, OCR Test is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does OCR Test support?
OCR Test is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created OCR Test?
It is built and maintained by shaw555 (@shaw555); the current version is v1.0.0.
More Skills