Image
Core functionality module for generating and processing image content
clawhub install imagePerform Optical Character Recognition (OCR) on screenshots to extract text from images.
# Install Skill (downloads SKILL.md to .claude/skills/) clawhub install screenshot-ocr # Then just tell Claude: "use Screenshot Ocr to help me..."
# Same install command — works with all SKILL.md-compatible AI coding tools clawhub install screenshot-ocr
This Skill is compatible with the OpenClaw standard. After installation, a SKILL.md file is auto-generated, usable by any OpenClaw-compatible AI Agent (Claude Code, Cursor, Windsurf, etc.).
python3 scripts/ocr.py clipboard
python3 scripts/ocr.py file screenshot.png
python3 scripts/ocr.py file screenshot.png --save result.txt
python3 scripts/ocr.py file screenshot.png --copy
# 安装 Tesseract(Linux)
sudo apt install tesseract-ocr tesseract-ocr-chi-sim
# macOS
brew install tesseract
# Windows
# 下载安装 https://github.com/UB-Mannheim/tesseract/wiki
# 识别截图
python3 scripts/ocr.py clipboard
# 识别图片并复制
python3 scripts/ocr.py file ~/Desktop/1.png --copy
pip install pytesseract pillow
clawhub run screenshot-ocr --image ./screenshot.png --language auto --format jsonUpload images to img402.dev and get a public URL. Free tier: 1MB max, 7-day retention, no auth. Use when the agent needs a hosted image URL — for sharing in messages, embedding in documents, posting to social platforms, or any context that requires a public link to an image file.
clawhub install image-hosting