← Back to Skills Marketplace
13790
Downloads
11
Stars
110
Active Installs
1
Versions
Install in OpenClaw
/install image-ocr
Description
Extract text from images using Tesseract OCR
Usage Guidance
Install Tesseract only from trusted OS repositories, and run OCR only on images whose contents you are comfortable processing in your local agent session.
Capability Analysis
Type: OpenClaw Skill
Name: image-ocr
Version: 1.0.0
The skill bundle is designed to extract text from images using Tesseract OCR. The `SKILL.md` provides standard installation instructions via `dnf` for the `tesseract` package and examples for using the OCR functionality. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, prompt injection attempts against the agent, or obfuscation. All content aligns with the stated purpose of providing OCR capabilities.
Capability Assessment
Purpose & Capability
The stated purpose, metadata, dependency, and examples all align with extracting text from images using Tesseract OCR.
Instruction Scope
Instructions are limited to explicit OCR commands on provided image paths with an optional language flag; there are no hidden, autonomous, destructive, or unrelated behaviors.
Install Mechanism
The skill documents a manual `sudo dnf install tesseract` system package install, which is purpose-aligned but changes the local package set.
Credentials
The artifact requests no credentials, network access, session stores, environment secrets, or broad filesystem indexing; it only needs access to images the user chooses to process.
Persistence & Privilege
Installing Tesseract is a persistent system-level change requiring elevated privileges, but the skill bundle itself contains only `SKILL.md` and shows no background process or privilege escalation.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install image-ocr - After installation, invoke the skill by name or use
/image-ocr - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial publish
Metadata
Frequently Asked Questions
What is Image Ocr?
Extract text from images using Tesseract OCR. It is an AI Agent Skill for Claude Code / OpenClaw, with 13790 downloads so far.
How do I install Image Ocr?
Run "/install image-ocr" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Image Ocr free?
Yes, Image Ocr is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Image Ocr support?
Image Ocr is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Image Ocr?
It is built and maintained by Xejrax (@xejrax); the current version is v1.0.0.
More Skills