Create Proposal logo

Create Proposal

Community
AntonHu
create-proposal

通用创建提案技能。根据需求是否有设计稿或 UI 描述、是否有接口、是页面还是功能组件等可选条件,决定设计稿分析、接口与数据层、以及实现后的 UI 还原验收等步骤。适用于各类需求提案,不限于纯 UI 页面。

Overview

PublisherAntonHu
Repositoryai-coding-project
Skill namecreate-proposal
Stars
111
Forks
35
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Create Proposal 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/AntonHu/ai-coding-project/tree/main/.agents/skills/create-proposal
  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/AntonHu/ai-coding-project.git /tmp/ai-coding-project
mkdir -p .claude/skills
cp -r /tmp/ai-coding-project/.agents/skills/create-proposal .claude/skills/create-proposal
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Create Proposal 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 Create Proposal 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 Create Proposal 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.

创建提案

使用时机

当需要为一个需求创建 OpenSpec 提案(proposal、tasks、spec)时使用本技能。需求可能是:

  • 新增/改版一个页面(有或没有设计稿)
  • 开发一系列功能组件(有或没有 UI 描述)
  • 有接口或无接口(后端未就绪时用 mock)
  • 纯逻辑、纯接口、或 UI + 接口 等组合

本技能根据「是否有设计稿/UI 描述」「是否有接口」「交付形态(页面/组件/其它)」等条件,决定执行哪些步骤、产出哪些任务。


步骤 1:明确需求类型与条件

在写 proposal / tasks / spec 之前,先确认下列条件,以便后续步骤按需执行。

条件选项影响
是否有设计稿或 UI 要求描述有 / 无有 → 可选用 design-analysis 产出 UI 分析清单;实现后可有 UI 还原验收步骤
是否有接口(已提供或约定)有 / 无 / 未就绪有 → 正常对接;无 → 可不做数据层;未就绪 → mock,见项目 Mock 数据策略
交付形态新页面 / 功能组件 / 能力模块 / 其它决定目录结构(routes vs components)、tasks 模板
是否仅样式/还原类是 / 否是 → 重点在 design-analysis + 验收

步骤 2:若有设计稿或 UI 描述 —— 设计稿分析(可选但推荐)

当需求包含界面且有设计稿(.pen、figma链接、设计图、标注)或有明确 UI 描述时:

  • 使用技能:.agents/skills/design-analysis/SKILL.md
  • 产出:docs/样式还原/<名称>-UI分析清单.md

这样后续开发可以依据分析清单精确实现,实现后的验收也以此清单为基准。不限定「必须先分析再写提案」:可以边写提案边分析,或先分析再写提案,只要在开发前有一份分析清单即可。

在 tasks 中可写明:页面/组件开发须依据 docs/样式还原/<名称>-UI分析清单.md 实现布局与样式。


步骤 3:定义组件与代码结构(涉及 UI 时)

若交付形态是页面或功能组件,根据 .agents/rules/04-组件规范.md 判断组件放置位置:

  • 多处复用 → src/components/<name>/
  • 单页或单能力内使用 → src/routes/<page>/components/<name>/ 或对应功能目录下

涉及页面时,常见约定:

  • 样式文件使用 .module.scss
  • interfaces/ 下为文件夹,含 model.ts、api.ts
  • 图标/图片未定时用占位元素(见 .agents/rules/08-通用约束.md)

步骤 4:接口与数据层(有接口或需 mock 时)

若需求涉及接口(已提供或未就绪):

  • 已提供接口:按 .agents/rules/03-项目结构.md 等规范,在 tasks 中安排 interfaces/、http/ 等。
  • 未就绪:按项目 Mock 数据策略,在 interfaces/<feature>/ 下定义 model.ts、api.ts,在 http/ 下提供 mock;tasks 中标注「mock,后续替换」。

若不涉及接口,可省略或仅写「无后端依赖」。


步骤 5:创建提案文档

5.1 proposal.md

根据需求类型书写,建议包含:

  • Why:业务价值或目标
  • What Changes:改动范围(新页面 / 新组件 / 新接口 / 样式还原等)
  • Impact:受影响或新增的 capability、目录、文件

若有设计稿或 UI:可写「图标/图片使用占位元素」「开发依据 docs/样式还原/xxx-UI分析清单.md」等。

5.2 tasks.md

按交付形态与条件勾选任务,例如:

  • 新页面:路由目录、Page、Loader、index.module.scss、与布局一致的结构;若有分析清单则写「依据 xxx-UI分析清单 实现」。
  • 功能组件:组件目录、index.tsx、index.module.scss、占位与规范。
  • 接口/数据层:interfaces/<feature>/、http/<feature>.ts 或 mock。
  • UI 还原验收:若有设计稿且产出了分析清单,可在 tasks 末尾加「实现后使用 .agents/skills/ui-verification/SKILL.md 进行 UI 还原验收,产出问题清单并反思分析不足」。

5.3 spec.md

定义需求规格:场景、验收标准、可选的状态与边界。若有 UI,可引用分析清单中的「验证检查清单」作为验收参考。


步骤 6:实现后的 UI 还原验收(可选)

当需求包含界面且有设计稿并已产出 UI 分析清单时,在实现完成后需要进行 UI 还原验收时:

  • 使用技能:.agents/skills/ui-verification/SKILL.md
  • 该技能通用指导如何进行 UI 验收:对照分析清单与设计稿、产出 UI 问题清单、修复与再验证、反思分析不足并反哺 design-analysis。

样式还原验证检查清单(供 create-route / create-component 引用)

当开发涉及 UI 还原(有设计稿或分析清单)时,可对照以下检查项自检;更完整项见 docs/样式还原/<名称>-UI分析清单.md 中的「验证检查清单」。

布局:区域位置、尺寸、间距是否与分析清单/设计稿一致;对齐方式(如 flex-start vs center)是否正确。
样式:颜色、字体、字号、字重、圆角、边框、阴影、效果(如 backdrop-filter)是否一致。
元素:是否缺少区块、图标、占位图;占位尺寸与比例是否正确。
交互:默认/hover/active 等状态是否还原(若有设计)。

create-route、create-component 等技能中「涉及 UI 还原时」可引用:.agents/skills/create-proposal/SKILL.md 中的「样式还原验证检查清单」及对应页面的 docs/样式还原/<名称>-UI分析清单.md。


相关规范与技能

  • .agents/rules/03-项目结构.md - 目录结构、Mock 数据策略
  • .agents/rules/04-组件规范.md - 组件放置决策
  • .agents/rules/08-通用约束.md - 占位元素等
  • .agents/rules/09-样式规范.md - 设计稿颜色提取
  • .agents/skills/design-analysis/SKILL.md - 设计稿分析(有设计稿时使用,产出 UI 分析清单)
  • .agents/skills/ui-verification/SKILL.md - UI 验收(实现后需验收时使用)

Frequently asked questions

What does the Create Proposal AI skill do?

通用创建提案技能。根据需求是否有设计稿或 UI 描述、是否有接口、是页面还是功能组件等可选条件,决定设计稿分析、接口与数据层、以及实现后的 UI 还原验收等步骤。适用于各类需求提案,不限于纯 UI 页面。

Why use Create Proposal on TypingMind?

Because you install it once and use it with any model. Create Proposal 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 Create Proposal in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AntonHu/ai-coding-project/tree/main/.agents/skills/create-proposal. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Create Proposal?

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 Create Proposal?

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

Is the Create Proposal AI skill free?

It is published on GitHub by AntonHu. 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 👇