发现优质的 AI Agent 技能

OCR that never fails silently. Process PDFs and extract structured data with AI-powered confidence scoring that tells you exactly which fields need human review.

DeepRead is an AI-native OCR platform that turns documents into high-accuracy data in minutes. Using multi-model consensus, DeepRead achieves 95%+ accuracy and flags only uncertain fields for review—reducing manual work from 100% to 5-10%. Zero prompt engineering required.

1. 采用RESTFul风格API。 2. 遵循全栈模型同构UMI设计理念。[UMI参考文章](https://mp.weixin.qq.com/s/ja0jfsfkyIK2hdW6bDg2Ow) 3. 采用jwt进行接口权限验证。需要权限调用的接口需先通过登录 /api/uctoo/auth/login 接口获取动态token，再以Bearer 动态token拼接成的字符串作为header的Authorization进行需要权限的接口调用。动态token过期时间默认为172800秒，如需定制修改可编辑根目录.env文件中ACCESS_TOKEN_VALIDITY_SEC字段。 4. 单表对应的CURD操作默认API应以id字段作为数据一致性传输的主标识，如有特殊API不存在id字段的，则以动态token作为主标识。 5. API不应输出的模型字段，可以使用hideSelectedObjectKeys()方法过滤掉不应输出的字段。需注意接口数据的信息安全。

来自 openclaw/skills 技能

来自 openclaw/skills 技能

来自 openclaw/skills 技能

**文档版本**: 2.0 **创建日期**: 2026-02-27 **状态**: 设计中

本项目实现了Agent Skills，将自然语言请求转换为uctoo-backend服务器API调用。技能遵循agentskills标准规范，允许AI助手使用自然语言与uctoo-backend服务进行交互。

You have access to UCM, a marketplace where you can instantly discover and use API services by spending credits. Registration is free and gives you $1.00 in credits (~100 API calls).

curl -s "https://www.klawdin.com/api/profiles" \ -H "X-API-Key: $KLAWDIN_API_KEY" curl -s "https://www.klawdin.com/api/profiles?stage=startup&seeking=investors" \ -H "X-API-Key: $KLAWDIN_API_KEY"

Use `x-read` whenever you need to capture the text, media links, and basic metadata from a public X/Twitter permalink without using the API, creating an account, or burning Brave search credits. It works best for thread permalink URLs (`https://x.com/<user>/status/<id>`) and articles posted on X that surface their content on the same page.

来自 openclaw/skills 技能