Screenshot
clawhub2 platformsScreen Capture Very Easy
3.7
Capture, inspect, and compare screenshots of screens, windows, regions, web pages, simulators, and CI runs with the right tool, wait strategy, viewport, and...
1.2K
clawhub install screenshotA tool for capturing screen content and saving it as images or videos.
# Install Skill (downloads SKILL.md to .claude/skills/) clawhub install screenshot-tool # Then just tell Claude: "use Screenshot Tool to help me..."
# Same install command — works with all SKILL.md-compatible AI coding tools clawhub install screenshot-tool
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.).
npm install -g agent-browser && agent-browser install |
| LibreOffice | 文档转 PDF | sudo apt-get install -y libreoffice-impress libreoffice-writer libreoffice-calc |
| poppler-utils | PDF 处理 | sudo apt-get install -y poppler-utils |
| Python 库 | PDF 转图片 | pip3 install pdf2image pillow |# 1. 安装 agent-browser(网页截图必需)
npm install -g agent-browser
agent-browser install
agent-browser install --with-deps # 如需要系统依赖
# 2. 安装 LibreOffice(文档转换必需)
sudo apt-get install -y libreoffice-impress libreoffice-writer libreoffice-calc
# 3. 安装 poppler-utils(PDF 处理必需)
sudo apt-get install -y poppler-utils
# 4. 安装 Python 依赖
pip3 install pdf2image pillow
# 5. 安装中文字体(可选,用于中文文档)
sudo apt-get install -y fonts-wqy-zenhei fonts-wqy-microhei fonts-noto-cjk
# 验证 agent-browser
agent-browser --version
# 验证 LibreOffice
libreoffice --version
# 验证 poppler
which pdftoppm pdfinfo
# 截图单个网页
python3 skills/screenshot-tool/scripts/web_screenshot.py --url "https://example.com" --output page.png
# 截图并滚动(长页面)
python3 skills/screenshot-tool/scripts/web_screenshot.py --url "https://example.com" --full-page --output page.png
# PPT/Word/Excel/PDF 转图片
python3 skills/screenshot-tool/scripts/doc_screenshot.py --input file.pptx --output-dir ./images
# 指定 DPI(默认 300)
python3 skills/screenshot-tool/scripts/doc_screenshot.py --input file.pdf --dpi 200 --output-dir ./images
# 打开网页
agent-browser open "https://example.com" --timeout 60000
# 截图
agent-browser screenshot output.png --full
# 关闭浏览器
agent-browser close
# 截图京东首页
python3 skills/screenshot-tool/scripts/web_screenshot.py \
--url "https://www.jd.com" \
--output jd_homepage.png \
--wait 5
# 转换整个 PPT
python3 skills/screenshot-tool/scripts/doc_screenshot.py \
--input presentation.pptx \
--output-dir ./slides \
--dpi 300
# 转换 PDF 前5页
python3 skills/screenshot-tool/scripts/doc_screenshot.py \
--input document.pdf \
--output-dir ./pages \
--first-page 1 \
--last-page 5
PPT/Word/Excel → LibreOffice → PDF → pdf2image → PNG (300 DPI)
↑
依赖: poppler-utils
URL → agent-browser (headless Chrome) → Screenshot → PNG
↑
依赖: agent-browser CLI
# 检查 LibreOffice 安装
libreoffice --version
# 手动转换测试
libreoffice --headless --convert-to pdf file.pptx
# 检查 poppler 安装
which pdftoppm pdfinfo
# 重新安装
sudo apt-get install -y poppler-utils
# 安装中文字体
sudo apt-get install -y fonts-wqy-zenhei fonts-wqy-microhei fonts-noto-cjk
skills/screenshot-tool/
├── SKILL.md # 本文件
├── scripts/
│ ├── web_screenshot.py # 网页截图脚本
│ └── doc_screenshot.py # 文档转图片脚本
└── README.md # 详细说明
screenshot-tool capture --mode full --output ./snap.png && screenshot-tool record --duration 60 --fps 30 --output ./video.mp4Capture, inspect, and compare screenshots of screens, windows, regions, web pages, simulators, and CI runs with the right tool, wait strategy, viewport, and...
clawhub install screenshot