Ai Ui Dev Handoff logo

Ai Ui Dev Handoff

Community
PaperMoonuu
ai-ui-dev-handoff

L2 × AI 设计交付 / 开发沟通:将已完成设计稿或可评审原型的 L2 中型功能整理为开发、测试和产品可共用的交付包。适用于包含完整任务路径,且同时涉及字段规则、异步或异常状态、角色或生命周期、动态操作、响应式要求中至少两项的功能;当用户要求做设计交付、开发沟通、补齐组件/字段/状态/验收规格,或识别交付阻塞项时使用。

Overview

PublisherPaperMoonuu
RepositoryDesign-workflow-skills
Skill nameai-ui-dev-handoff
Stars
250
Forks
2
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by PaperMoonuu on GitHub. Read the source before you install it.

Installation

Install the Ai Ui Dev Handoff AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/PaperMoonuu/Design-workflow-skills/tree/UI-Workflow-skills/ai-ui-dev-handoff
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/PaperMoonuu/Design-workflow-skills.git /tmp/Design-workflow-skills
mkdir -p .claude/skills
cp -r /tmp/Design-workflow-skills/ai-ui-dev-handoff .claude/skills/ai-ui-dev-handoff
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ai Ui Dev Handoff in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ai Ui Dev Handoff on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ai Ui Dev Handoff is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

L2 × AI 设计交付 / 开发沟通

将已确认的设计与业务信息转译为可实现、可测试且可追溯的交付规格。AI 是工程翻译、状态枚举和缺口检查助手;不要代替产品、设计负责人或技术负责人作最终决策。

准入判断

先检查输入,再开始整理。满足以下条件时按本 Skill 执行:

  • 有已完成设计稿、可评审原型或可运行实现,并能看到页面上下文。
  • 范围是一个完整功能、独立模块或 1–3 个紧密相关页面,而非纯视觉微调。
  • 可说明入口、关键操作与成功、失败或退出路径。
  • 在字段规则、异步/异常、角色/生命周期、动态操作、响应式中至少涉及两类。

按下表分流,不要硬套 L2:

情况处理
只有想法、PRD 或默认态截图,尚未形成可评审设计先做设计前需求校准;列出缺失规则,不输出“可开发”结论
只有文案、按钮、间距或一个单态的小改动降级为 L1 设计评审或轻量交付说明
多页面任务编排、跨模块一致性、复杂权限体系、指标口径或平台级组件策略升级为 L3 专题交付
关键权限、字段、状态或提交规则缺失继续产出可完成部分,但将其置为 P0 阻塞

执行流程

1. 建立事实台账

把每条输入分为三类:已确认事实、待验证假设、待确认项。为事实写明设计节点、PRD、代码或决策记录来源;不要把截图以外的接口、权限、错误码、埋点或技术实现写成事实。

将待确认项按下列规则分级:

  • P0:不确认即无法正确开发或验收,例如权限、提交映射、必填/校验、数据一致性、幂等、审计。
  • P1:可以先行实现局部 UI,但联调或上线前必须关闭,例如键盘避让、加载策略、移动端断点。
  • P2:不阻塞本次交付,但应记录为后续体验或指标优化项。

2. 描述任务路径与组件契约

从入口开始,写出关键动作、数据变化、成功结果、退出/返回路径。再为每个页面、区块、弹层和关键控件写组件契约,至少包含:新增或复用、用户目标、数据/字段、触发事件、可见条件、状态和设计来源。

优先使用 references/delivery-templates.md 中的表格。若无法追溯来源,标记为待确认,不要编造来源。

3. 补全字段、权限与生命周期

为每个关键字段明确含义、来源、必填、格式、默认值、校验、错误反馈和提交映射。涉及角色或业务阶段时,使用“角色 × 生命周期 × 行为”矩阵区分:可见、可阅读、可编辑、可提交、可撤销与审计/留痕。

不要把“用户看得见”推论为“用户能提交”;前端隐藏或禁用不能替代服务端权限校验。

4. 枚举状态、异常与响应式规则

按功能相关性覆盖默认、加载、空、错误、成功、禁用、无权限、弱网、长内容、重复操作及功能专属状态。对上传、保存、提交、查询、分页、刷新或重试,明确触发条件、用户可见反馈、数据保留策略和恢复路径。

说明端类型、断点、信息优先级、固定操作区、键盘遮挡、长文本/文件名、多语言和极端数据处理。避免“支持异常处理”“适配移动端”这类无法测试的表述。

5. 处理配置驱动的动态操作区(如适用)

若存在操作栏、下拉动作或动态表单,额外输出动作配置矩阵。每个动作至少覆盖:

  • 动作 code、名称、位置与配置来源。
  • 页面配置、服务端权限、当前节点/任务资格三项条件。
  • 动态字段、人员/节点范围、必填、默认值、校验与提交映射。
  • 动作切换时的草稿保留、清空或阻止切换规则。
  • loading、成功、失败、重复提交与恢复反馈。

严格遵守:动作展示不等于动作可执行。只有页面配置、服务端权限与当前节点资格均满足时,才能把动作写为可执行;缺少后端契约时标为 P0。

6. 输出交付包与就绪结论

按“输出契约”完整输出。每个验收场景须能追溯到用户目标、设计来源或业务规则,并写清前置条件、操作、预期结果和责任方。

最后只能给出以下一种结论:

  1. 可进入开发:没有 P0,规格足以实现和测试。
  2. 可并行开发但有 P1 待确认:可先搭建不依赖 P1 的部分,同时指定关闭时间。
  3. P0 阻塞,暂不进入开发:可以说明静态 UI 或复用组件能否并行,但不可将完整功能标为可交付。

输出契约

按以下顺序交付,除不适用项外不要省略:

  1. 交付就绪结论与范围判断。
  2. 输入完整性:事实、假设、缺失项、优先级、责任方与最晚确认时点。
  3. 功能/任务路径图。
  4. 组件契约清单。
  5. 字段与交互规则表。
  6. 角色 × 生命周期 × 行为矩阵。
  7. 状态与异常矩阵。
  8. 响应式、内容与可达性边界。
  9. 动作配置矩阵(仅配置驱动操作适用)。
  10. 开发待确认项与联调依赖。
  11. 验收矩阵,以及设计、开发、测试、产品各自要确认的事项。

硬性边界

  • 不猜测接口字段、错误码、权限规则、附件限制、幂等键、审计、通知、埋点、安全或性能方案。
  • 不把默认态设计稿当作完整实现规格;异步功能必须说明 loading、error、success 和重复操作策略。
  • 不只罗列字段名;必须补足来源、校验、默认值与提交映射,或明确其为 P0。
  • 不让动态动作切换静默丢失或串用数据;草稿策略必须被定义。
  • 不以“已有截图/原型”证明服务端权限、资格、附件契约或线上可执行性。

交付前自检

在结束前逐项确认:

  • 每一条主路径都包含完成结果和至少一个失败/退出处理。
  • 每个关键组件、字段和验收项都能回溯到来源或待确认项。
  • 含角色/阶段差异时,已区分可见、编辑与提交。
  • 含提交/上传/查询时,已写明数据保留、刷新/分页一致性与重复操作策略。
  • P0 没有被埋在正文,且就绪结论与 P0 状态一致。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ai Ui Dev Handoff AI skill do?

L2 × AI 设计交付 / 开发沟通:将已完成设计稿或可评审原型的 L2 中型功能整理为开发、测试和产品可共用的交付包。适用于包含完整任务路径,且同时涉及字段规则、异步或异常状态、角色或生命周期、动态操作、响应式要求中至少两项的功能;当用户要求做设计交付、开发沟通、补齐组件/字段/状态/验收规格,或识别交付阻塞项时使用。

Why use Ai Ui Dev Handoff on TypingMind?

Because you install it once and use it with any model. Ai Ui Dev Handoff is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ai Ui Dev Handoff in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/PaperMoonuu/Design-workflow-skills/tree/UI-Workflow-skills/ai-ui-dev-handoff. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ai Ui Dev Handoff?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ai Ui Dev Handoff?

As many as you like. As long as a model supports skills, you can use Ai Ui Dev Handoff with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ai Ui Dev Handoff AI skill free?

It is published on GitHub by PaperMoonuu. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇