Menü
多模态 AI 图片理解工具。将图片发送给支持 vision 的 LLM 模型，获取图片的语义理解和详细描述。可分析截图、设计稿、图表、报错信息等。
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | image-understand |
| description | 多模态 AI 图片理解工具。将图片发送给支持 vision 的 LLM 模型，获取图片的语义理解和详细描述。可分析截图、设计稿、图表、报错信息等。 |
| version | 1.0.0 |
| author | DunCrew |
| tags | ["vision","image-understanding","multimodal"] |
| keywords | ["图片理解","视觉分析","截图分析","图片描述","image understanding","vision","看图","分析图片"] |
| dangerLevel | safe |
| inputs | [{"name":"imagePath","type":"string","required":true,"description":"图片文件路径（本地绝对路径）"},{"name":"prompt","type":"string","required":false,"description":"分析指令/问题"},{"name":"detail","type":"string","required":false,"description":"视觉精度: low / high / auto"}] |
| metadata | {"openclaw":{"emoji":"👁️","primaryEnv":"shell"}} |
多模态 AI 图片理解工具，使用 LLM 的 vision 能力分析图片内容。
使用 imageUnderstand 工具让 AI 理解图片内容。与 OCR 不同，此工具不仅能提取文字，还能理解 UI 布局、图表含义、设计意图等语义信息。
screenCapture 截取目标内容imageUnderstand 进行语义理解ocrExtract 提取分析截图内容:
{"imagePath": "C:/temp/screenshots/error.png", "prompt": "这个错误窗口在说什么？如何解决？"}
解读图表:
{"imagePath": "C:/charts/sales.png", "prompt": "请分析这个销售数据图表的趋势"}
使用低精度模式（节省 token）:
{"imagePath": "C:/screenshots/overview.png", "prompt": "简要描述这个页面的布局", "detail": "low"}
Display interactive HTML content, visualizations, dashboards, or games on connected OpenClaw nodes (Mac, iOS, Android). Supports live reloading, remote navigation, JS execution, and canvas snapshots for development, testing, and presentation scenarios.
Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.
Execute shell commands and scripts on the user's local machine.
Unified memory search and management system for retrieving, storing, and organizing information across daily logs, persistent memory, SOPs, and execution traces. Use this skill to recall past events, manage knowledge bases, update important notes, or filter historical data by tags and time ranges.
智能 OCR 文字提取工具。从图片中识别文字，支持中英文混排、图像预处理（灰度化+二值化提升识别率）、表格结构还原为 Markdown 格式。
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery. Ideal for rapid prototyping, generating placeholder assets, testing AI art variations across models (GPT-Image, DALL-E 3/2), and building local thumbnail galleries with customizable resolution, quality, and output formats.