鸡尾酒顾问 Skill。触发条件：用户描述风味偏好、列出手中原材料、表达饮酒需求。覆盖六大基酒，提供精确配比、调制步骤和个性化推荐理由。
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →鸡尾酒顾问 Skill。触发条件：用户描述风味偏好、列出手中原材料、表达饮酒需求。覆盖六大基酒，提供精确配比、调制步骤和个性化推荐理由。
每天在三个随机时间窗口内，向用户推送**一条**诗词/名句/书籍/电影推荐。不是批量轰炸，是细水长流。
**重要提示**：用户主要使用 Windows 系统，必须优先保证 Windows 上的正常使用！
Polymarket BTC 5分钟 Up/Down 全自动交易机器人。MiniMax AI 驱动，双信号决策，自动止盈止损，真实链上交易，Web控制面板。
Upload files (images, videos, attachments) to Feishu (Lark) Bitable (multi-dimensional table) and return the file_token. Auto-selects direct upload for files up to 20MB or chunked upload (prepare, part, finish) for larger files. Requires App ID and Secret (lark-cli does NOT cover the /drive/v1/medias/ API). Use when the user wants to: upload a file/image/video to Feishu Bitable, get a file_token from Feishu Drive API, upload attachments to 多维表格 (bitable), 上传文件到飞书多维表格, 获取 file_token.
Generate PPT with Baidu AI. Smart template selection based on content.
OpenClaw 全自动安装、配置和修复工具。包括：OpenClaw 安装、Claude API 中转站配置、飞书插件集成、bug 自动修复。当用户需要安装、配置或修复 OpenClaw 时使用此技能。
飞书文档(Docx)API技能。用于创建、读取、更新和删除飞书文档。支持Markdown/HTML内容转换、文档权限管理。
im-social-insurance-backpay
>-
确保已安装：`pip install reportlab pygments`（可选：`pip install pymupdf` 用于检查PDF页数）
基于微信官方插件 @wecom/wecom-openclaw-plugin v1.0.13+，封装的一站式企业微信自动化解决方案 - 你可以方便操作文档、日历、会议、待办、通讯录所有企业微信MCP能力，充分发挥OpenClaw与企业微信的协同能力。
Apple Human Interface Guidelines 实战参考。涵盖 macOS/iOS 设计规范、System Colors、排版层级、控件规格、布局间距、Dark Mode 适配、辅助功能和平台差异。适用于开发 macOS 桌面应用（Electron/SwiftUI/AppKit）和 iOS 应用时的 UI 设计决策。
批量处理与长时任务编排模式。涵盖队列管理、并发调度、中断恢复、熔断器、远程任务轮询、进度报告和反风控策略。适用于批量文件处理、AI API 调用、爬虫和后台任务场景。
Microsoft Fluent Design System 实战参考。涵盖 Windows 11 设计语言、Mica/Acrylic 材质、WinUI 3 控件规格、排版层级、布局模式、Dark Mode、辅助功能和 Electron 适配。适用于开发 Windows 桌面应用或需要 Windows 原生感的跨平台应用。
Google Material Design 3 实战参考。涵盖 Material You 动态色彩、排版系统、组件规格、Shape 系统、Motion 规范、Dark Theme 适配和 Jetpack Compose/Flutter 对照。适用于 Android 应用、Web 应用和跨平台应用的 UI 设计决策。
Zustand 状态管理实战模式。涵盖 Store 设计规范、Slice 工厂复用、persist 持久化、可恢复任务持久化、Electron IPC 联动、Store 测试和常见陷阱。适用于 React + Zustand 项目。
CloudBase is a full-stack development and deployment toolkit for building and launching websites, Web apps, 微信小程序 (WeChat Mini Programs), and mobile apps with backend, database, hosting, cloud functions, storage, AI capabilities, and UI guidance. This skill should be used when users ask to develop, build, create, scaffold, deploy, publish, host, launch, go live, migrate, or optimize websites, Web apps, landing pages, dashboards, admin systems, e-commerce sites, 微信小程序 (WeChat Mini Programs), 小程序, uni-app, or native/mobile apps with CloudBase (腾讯云开发, 云开发), including authentication, login, database, NoSQL, MySQL, cloud functions, CloudRun, storage, AI models, and UI guidance, or when they ask to compare CloudBase with Supabase or migrate from Supabase to CloudBase.
Use this skill when developing Node.js backend services or CloudBase cloud functions (Express/Koa/NestJS, serverless, backend APIs) that need AI capabilities. Features text generation (generateText), streaming (streamText), AND image generation (generateImage) via @cloudbase/node-sdk ≥3.16.0. Built-in models include Hunyuan (hunyuan-2.0-instruct-20251111 recommended), DeepSeek (deepseek-v3.2 recommended), and hunyuan-image for images. This is the ONLY SDK that supports image generation. NOT for browser/Web apps (use ai-model-web) or WeChat Mini Program (use ai-model-wechat).
Complete guide for CloudBase Auth using the CloudBase Node SDK – caller identity, user lookup, custom login tickets, and server-side best practices.
CloudBase platform knowledge and best practices. Use this skill for general CloudBase platform understanding, including storage, hosting, authentication, cloud functions, database permissions, and data models.
WeChat Mini Program development rules. Use this skill when developing WeChat mini programs, integrating CloudBase capabilities, and deploying mini program projects.
CloudBase (腾讯云开发) 适用场景：全栈 Web、微信小程序、静态托管、云函数、云托管、文档/MySQL 数据库、身份认证、云存储等。用于在 OpenClaw/Moltbot 下配置 CloudBase（mcporter + 提示词约束，无脚本、设备码登录）。
A simple skill send files to feishu.
批量图片处理工具，支持压缩、裁剪、水印、格式转换等操作。
Analyze Chinese stock prices (A-shares, HK stocks) and provide investment recommendations. Use when the user asks about stock analysis for Chinese companies, including buying/selling recommendations and market trends.
🔥 **Claude Code 源码分析工具**
邮件营销自动化工具，支持批量发送、模板管理、效果追踪。
批量处理 Excel 文件的自动化工具，支持合并、拆分、格式转换、数据清洗等操作。
市场分析服务 | Market Analysis Service. 企业市场趋势分析 | Enterprise market trend analysis. 竞品分析 | Competitor analysis. 用户行为洞察 | User behavior insights. 触发词：市场分析、竞品分析、market analysis、趋势.
PDF 文件批量处理工具，支持合并、拆分、转图片、提取文字等操作。
knowledge-precipitation
> **版本：** 0.2.4（进度 checkpoint + 可靠超时补救）
> **版本：** 0.3.0（主题关联图 · 快速定位知识节点）
Use Chanjing Avatar API for lip-syncing video generation
蝉镜内容创作技能包（顶层路由）
>-
Use Chanjing AI creation APIs to submit image or video generation tasks across multiple models, inspect task status, poll async results, and explicitly download generated assets when requested.
Use Chanjing Avatar API for lip-syncing and video synthesis (including cartoon avatar)
Run this skill as a lightweight pre-check for chanjing actions. When the user asks to generate or configure chanjing credentials/keys (APP_ID/SECRET_KEY), run this skill to guide them—check if already configured; if yes, ask whether to re-apply; then open login page and let the user either run the config command or paste APP_ID/SECRET_KEY for the agent to apply.
Use Chanjing TTS API to synthesize speech from text, using user-provided voice
Use Chanjing TTS API to convert text to speech
Use Chanjing video synthesis APIs to create digital human videos from text or audio, with optional background upload, task polling, and explicit download when the user asks to save the result locally.
Use Chanjing customised person APIs to create, inspect, list, poll, and delete custom digital humans from uploaded source videos.
>-
Use Chanjing text-to-digital-person APIs to create AI portrait images, turn them into talking videos, optionally run LoRA training, poll async tasks, and explicitly download generated assets when requested.
当用户提到"图生图"、"AI 画图"、"生成图片"、"画一个"等时激活。
luoyonghao-perspective
Cost-effective skill selector for maximizing ROI on AI operations (增收降本版 v1.0.0). Use when the user needs to accomplish a task and wants the optimal skill chosen automatically to minimize costs while maximizing quality. Evaluates skills based on quality (35%), token cost (30%), security/reliability (20%), and speed (15%). Searches both local skills and clawhub.com, presents top recommendations for user confirmation before execution.
AI科研团队智能协作助手。用于：(1) 管理团队知识库和项目进度追踪 (2) 协助会议纪要整理、文献综述、实验记录 (3) 代码辅助和数据分析 (4) 按团队协议执行日/周工作循环。当团队成员在Issue、PR或即时通讯中@AI，或需要知识管理、项目进度监控、文档协作时触发。