- server:Go 网关(WS 流式识别中继/计费配额/微信登录支付 mock/反馈/埋点),gummy provider 已真实联调 - desktop:Tauri 2(全局快捷键 push-to-talk/浮层/托盘/设置/登录购买/反馈/首启引导) - android:Compose 主 App + IME(键盘内录音直传) - ios:App + 键盘扩展(1A spike 实证键盘内不可录音,走 deep link 听写) - design/design-pipeline:设计系统 + token 导出 iOS/Android 主题 - doc:前后端设计文档(HTML);web:官网宣传页;todo:任务看板 Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
1.5 KiB
name, description, user-invocable
| name | description | user-invocable |
|---|---|---|
| dudu-design | Use this skill to generate well-branded interfaces and assets for dudu (嘟嘟语音输入法), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping. | true |
Read the README.md file within this skill, and explore the other available files.
Key facts: dudu is a paid voice input method (语音输入法) for Mac/Windows/iOS/Android — push-to-talk dictation with streaming recognition. Minimal aesthetic, light/dark themes via data-theme="dark", single accent blue, Lucide line icons, circle-mouth line logo. Link styles.css for all tokens; reusable React components live in components/ (Button, Switch, MicBar, RecognitionOverlay, …); full-screen interactive recreations in ui_kits/desktop and ui_kits/mobile.
If creating visual artifacts (slides, mocks, throwaway prototypes, etc), copy assets out and create static HTML files for the user to view. If working on production code, you can copy assets and read the rules here to become an expert in designing with this brand.
If the user invokes this skill without any other guidance, ask them what they want to build or design, ask some questions, and act as an expert designer who outputs HTML artifacts or production code, depending on the need.
Hard rules: 一屏一个蓝色主按钮;无渐变;无 emoji;浮层永远深色玻璃;文案短、用"你"、无句号。