菜单
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。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
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。
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.
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.
| name | ocr-extract |
| description | 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。 |
| version | 1.0.0 |
| author | DunCrew |
| tags | ["ocr","text-extraction","image-processing"] |
| keywords | ["OCR","文字识别","图片文字","表格识别","text recognition","截图识别"] |
| dangerLevel | safe |
| inputs | [{"name":"imagePath","type":"string","required":true,"description":"图片文件路径"},{"name":"language","type":"string","required":false,"description":"Tesseract 语言代码，默认 eng+chi_sim"},{"name":"outputFormat","type":"string","required":false,"description":"输出格式: text / markdown"},{"name":"preprocess","type":"boolean","required":false,"description":"是否图像预处理，默认 true"}] |
| metadata | {"openclaw":{"emoji":"🔍","primaryEnv":"python","requires":{"bins":["python3","tesseract"]}}} |
智能 OCR 文字提取工具，比 parseFile 的 OCR 功能更强大。
使用 ocrExtract 工具从图片中提取文字。支持预处理优化和表格还原。
| 特性 | parseFile | ocrExtract |
|---|---|---|
| 图像预处理 | 无 | 灰度+二值化 |
| 表格识别 | 不支持 | Markdown 表格 |
| 语言选择 | 固定 | 可配置 |
| 预处理开关 | 无 | 可控 |
基本文字提取:
{"imagePath": "C:/screenshots/test.png"}
日文识别:
{"imagePath": "C:/screenshots/jp.png", "language": "jpn"}
表格识别:
{"imagePath": "C:/screenshots/table.png", "outputFormat": "markdown"}
不做预处理（已经是高清图片时）:
{"imagePath": "C:/screenshots/hd.png", "preprocess": false}