Image
Core functionality module for generating and processing image content
clawhub install image图像 OCR 识别技能,可从图像中提取和识别文本内容。
# Install Skill (downloads SKILL.md to .claude/skills/) clawhub install siliconflow-image-ocr # Then just tell Claude: "use Image Ocr to help me..."
# Same install command — works with all SKILL.md-compatible AI coding tools clawhub install siliconflow-image-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.).
python scripts/paddleocr_vl.py \
--prompt "请提取图片中的全部文字" \
--image-path /path/to/image.png
SILICONFLOW_API_KEY
- 本机凭据文件 ~/.openclaw/secrets/siliconflow_api_key(推荐,权限 600)
https://api.siliconflow.cn/v1SILICONFLOW_API_KEY
- 或本机凭据文件:~/.openclaw/secrets/siliconflow_api_key(权限建议 600)python scripts/paddleocr_vl.py --prompt "请回复:ok"
若返回标准 JSON(非鉴权错误),说明配置成功。python scripts/paddleocr_vl.py \
--prompt "请提取图片中的全部文字" \
--image-path /path/to/image.png
python scripts/paddleocr_vl.py --prompt "请回复:ok"
chat/completions。--image-path 或 --image-url,会按多模态消息发送。clawhub run siliconflow-image-ocr --image="./invoice.jpg" --language="zh" --format="markdown"Upload 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