图片理解与数据提取 skill。当图片文件（.png/.jpg/.jpeg/.gif/.webp/.bmp）是主要输入且用户需要理解、提取数据或分析图片内容时使用。提供预配置的 caption 脚本（scripts/caption.py），通过 vision 模型将图片转为文本描述，无需额外配置 API Key。覆盖：(1) 通过 scripts/caption.py 对图表/表格/截图/流程图进行 caption，(2) 将 caption 文本解析为结构化 DataFrame，(3) 基于提取数据重新生成可视化图表，(4) 导出为 Excel/CSV。
Install
npx skills add OpenSenseNova/SenseNova-Skills --skill sn-da-image-captionnpx skills add OpenSenseNova/SenseNova-Skills --skill sn-da-image-caption -a claude-code -gnpx skills add OpenSenseNova/SenseNova-Skills --skill sn-da-image-caption -a codex -ggemini skills install https://github.com/OpenSenseNova/SenseNova-Skills.git --path skills/sn-da-image-captiongh skill install OpenSenseNova/SenseNova-Skills sn-da-image-captiongit clone --depth 1 https://github.com/OpenSenseNova/SenseNova-Skills /tmp/OpenSenseNova__SenseNova-Skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/OpenSenseNova__SenseNova-Skills/skills/sn-da-image-caption ~/.claude/skills/sn-da-image-caption # Claude Code
cp -R /tmp/OpenSenseNova__SenseNova-Skills/skills/sn-da-image-caption ~/.agents/skills/sn-da-image-caption # Codex, Cursor, Gemini CLI, Copilot, OpenCode