← Back to Skills Marketplace
110
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install img-ocr
Description
图片文字识别工具，基于Tesseract OCR。当用户提到：图片识别、OCR、文字提取、图片转文字、识别图片里的文字时使用。
README (SKILL.md)
img-ocr
Image text recognition tool based on Tesseract OCR.
Dependencies
- Python3
- pytesseract:
pip3 install pytesseract - Pillow:
pip3 install Pillow - Tesseract OCR:
sudo apt install tesseract-ocr - Chinese lang pack:
sudo apt install tesseract-ocr-chi-sim
Quick Usage
python3 skills/img-ocr/scripts/ocr.py /path/to/image.jpg
Typical Scenarios
# Recognize Chinese + English
python3 skills/img-ocr/scripts/ocr.py screenshot.png
# Extract text from screenshot
python3 skills/img-ocr/scripts/ocr.py /path/to/screenshot.jpg
Usage Guidance
This skill appears to do exactly what it says: run a local Tesseract OCR on an image file and print the text. Before installing or running it: 1) be prepared to install system packages (tesseract and language packs) with sudo on Debian/Ubuntu; 2) note the SKILL.md path mismatch (the docs reference skills/img-ocr/scripts/ocr.py but the repo contains ocr.py at the root) — verify the correct path when invoking; 3) the script reads any filesystem path you pass it, so avoid giving paths to sensitive files you don't want processed or exposed; 4) this skill does not transmit results over the network, but if you integrate it into automated workflows, confirm downstream handling of extracted text (where it might be sent or stored).
Capability Analysis
Type: OpenClaw Skill
Name: img-ocr
Version: 1.0.1
The skill is a straightforward implementation of an OCR tool using the Tesseract engine. The Python script (ocr.py) uses standard libraries (pytesseract and Pillow) to process local image files and print the extracted text, with no evidence of network activity, data exfiltration, or malicious instructions in the documentation (SKILL.md).
Capability Assessment
Purpose & Capability
Name/description (image OCR) align with the included code and instructions: the Python script uses pytesseract and Pillow to read an image path and print recognized text.
Instruction Scope
Instructions are narrowly scoped to installing Tesseract/pytesseract and running the OCR script, but SKILL.md references a different script path (skills/img-ocr/scripts/ocr.py) than the provided file (ocr.py). Installation steps use apt (sudo) which requires privilege to install system packages—expected for Tesseract but should be noted.
Install Mechanism
No install spec in the registry; dependency instructions are manual (pip and apt). No downloads from third-party URLs or archive extraction are present in the package.
Credentials
No environment variables, credentials, or config paths are requested. The script only reads the image file path provided as an argument.
Persistence & Privilege
Skill is not always-enabled and does not attempt to modify agent/system configs. It does not request persistent privileges or autonomous elevated presence.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install img-ocr - After installation, invoke the skill by name or use
/img-ocr - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
英文描述更新
v1.0.0
图片文字识别工具，基于Tesseract OCR，支持中文和英文
Metadata
Frequently Asked Questions
What is Img Ocr?
图片文字识别工具，基于Tesseract OCR。当用户提到：图片识别、OCR、文字提取、图片转文字、识别图片里的文字时使用。 It is an AI Agent Skill for Claude Code / OpenClaw, with 110 downloads so far.
How do I install Img Ocr?
Run "/install img-ocr" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Img Ocr free?
Yes, Img Ocr is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Img Ocr support?
Img Ocr is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Img Ocr?
It is built and maintained by Frank_Jin (@ginntech); the current version is v1.0.1.
More Skills