← Back to Skills Marketplace
16817
Downloads
19
Stars
119
Active Installs
1
Versions
Install in OpenClaw
/install ocr-local
Description
Extract text from images using Tesseract.js OCR (100% local, no API key required). Supports Chinese (simplified/traditional) and English.
Usage Guidance
Install only if you are comfortable with npm dependencies and a first-run download of Tesseract language data. For restricted or offline environments, preload or vendor the language data through a controlled process before use, and avoid OCRing sensitive images unless you are comfortable with the extracted text appearing in the agent session.
Capability Assessment
Purpose & Capability
The skill’s purpose is local OCR using Tesseract.js, and the script reads a user-specified image path, runs OCR, and prints text or JSON output without requesting credentials or unrelated access.
Instruction Scope
The wording “100% local” is somewhat imprecise because the docs also disclose first-run Tesseract language-data downloads and later local caching; this is a transparency caveat, not evidence of hidden behavior.
Install Mechanism
Installation uses Node/npm with the tesseract.js dependency and runtime language-data downloads. This is coherent for Tesseract OCR, though not ideal for strictly offline or pinned-supply-chain environments.
Credentials
Access is proportionate to OCR: it operates on image files the user passes in and does not show image upload, OCR-output exfiltration, environment-variable access, shell execution, or credential handling.
Persistence & Privilege
The only persistence indicated is local caching of downloaded language data. There is no evidence of background workers, privilege escalation, modification of other skills, or durable agent behavior.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install ocr-local - After installation, invoke the skill by name or use
/ocr-local - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Local OCR skill using Tesseract.js, no API key required
Metadata
Frequently Asked Questions
What is OCR - Local (No API Key)?
Extract text from images using Tesseract.js OCR (100% local, no API key required). Supports Chinese (simplified/traditional) and English. It is an AI Agent Skill for Claude Code / OpenClaw, with 16817 downloads so far.
How do I install OCR - Local (No API Key)?
Run "/install ocr-local" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is OCR - Local (No API Key) free?
Yes, OCR - Local (No API Key) is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does OCR - Local (No API Key) support?
OCR - Local (No API Key) is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created OCR - Local (No API Key)?
It is built and maintained by shaw555 (@shaw555); the current version is v1.0.0.
More Skills