Proj Analyze Req logo

Proj Analyze Req

Community
zhangloveyan
proj-analyze-req

需求分析与确认(阶段一)。用于理解用户需求、澄清细节、明确功能边界,生成需求分析文档。

Overview

Publisherzhangloveyan
Repositorybackend-skill
Skill nameproj-analyze-req
Stars
102
Forks
31
Bundled files
1
LicenseMIT
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Proj Analyze Req 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/zhangloveyan/backend-skill/tree/main/.claude/skills/proj-analyze-req
  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/zhangloveyan/backend-skill.git /tmp/backend-skill
mkdir -p .claude/skills
cp -r /tmp/backend-skill/.claude/skills/proj-analyze-req .claude/skills/proj-analyze-req
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Proj Analyze Req 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 Proj Analyze Req 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 Proj Analyze Req 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.

需求分析(阶段一)

目标:理解用户真实需求,明确功能边界和业务逻辑,生成需求分析文档。 产出:需求分析文档(用户确认后进入阶段二)


执行流程

Step 0: 初始化任务文档 → Step 1: 需求理解 → Step 2: 规模判断 → Step 3: 需求澄清(与用户交互) → Step 4: 输出需求文档 → Step 5: 用户确认

Step 0: 初始化任务文档

在用户输入需求后,必须创建全流程任务文档骨架:

  • 文件位置:docs/task/{YYYYMMDD}_{中文模块名}_任务.md
  • 内容要求:仅记录流程状态、产物清单、上下文快照、下一步指令
  • 禁止写细节:不写技术实现与字段设计

Step 1: 需求理解

从用户描述中初步提取:

维度提取内容
功能目标要实现什么功能
使用角色谁来使用
涉及端Web后台/小程序/App/开放接口
涉及模块影响哪些现有模块
关键操作核心功能点

注意:此步骤仅做初步理解,禁止假设任何细节。


Step 2: 规模判断

规模特征后续流程
简单改字段、加接口、改配置可简化澄清,但仍需确认
中等新模块、独立功能标准流程
复杂跨模块、架构调整、核心流程完整流程,详细文档

判断依据:

  • 涉及 1 个文件 → 简单
  • 涉及 1 个模块(多文件) → 中等
  • 涉及多个模块 → 复杂

Step 3: 需求澄清(必须执行)

3.1 必问问题清单

AI 必须向用户询问以下问题,根据需求复杂度选择性提问:

维度问题说明
功能范围这个功能给谁用?Web端?移动端?都需要?明确端类型
用户角色涉及哪些角色?各角色能做什么操作?明确权限边界
功能清单具体需要哪些功能点?列表/详情/创建/编辑/删除/导出/审批...
业务流程主要业务流程是怎样的?有哪些状态流转?明确流程节点
业务规则有哪些业务限制或校验规则?明确约束条件
数据要求需要记录哪些信息/字段?明确数据结构
关联关系与现有哪些模块有关联?明确依赖关系
参考资料有没有参考产品或原型图?获取更多上下文

3.2 提问原则

  1. 先思考再提问 - 根据需求类型,预判可能涉及的细节点(如:是否多端、是否有状态流转、是否需要关联用户等)
  2. 一次性列出 - 将所有待确认问题整理后一次性提出,减少交互轮次
  3. 不要假设答案 - 不确定的必须问
  4. 追问细节 - 用户回答模糊时继续追问
  5. 确认理解 - 复述用户的回答确保理解正确

3.3 提问示例

我来帮您分析这个需求。为了准确理解,请回答以下问题:

**1. 功能范围**
- 这个功能给谁用?Web后台管理端?小程序端?还是都需要?

**2. 用户角色**
- 涉及哪些角色?各角色分别能做什么操作?

**3. 功能清单**
- 需要哪些具体功能?(如:列表查询、详情查看、新增、编辑、删除、导出...)

**4. 业务流程**
- 主要的业务流程是怎样的?
- 是否有状态流转?(如:待处理→处理中→已完成)

**5. 数据要求**
- 需要记录哪些信息/字段?
- 哪些是必填项?

请逐一回答,我会根据您的回答进一步澄清。

Step 4: 输出需求文档

在充分澄清后,使用模板输出需求分析文档。

模板文件:需求文档模板

保存位置:docs/req/{YYYYMMDD}_{中文模块名}_需求.md

同步更新任务文档:

  • 将“需求分析”状态标记为进行中/已完成
  • 在产物清单中记录需求文档路径
  • 更新上下文快照与下一步指令

Step 5: 用户确认

5.1 确认话术

输出需求文档后,必须使用以下话术请求确认:

以上是我对需求的理解,请确认:
1. 功能范围是否完整?
2. 业务流程是否正确?
3. 是否有遗漏的功能点或业务规则?

确认后我将进入技术方案设计阶段(/proj-analyze-design)。

5.2 用户反馈处理

用户反馈处理方式
"确认"/"没问题"/"可以"进入阶段二:/proj-analyze-design
"需要补充xxx"更新需求文档,再次确认
"需要修改xxx"修改对应内容,再次确认
"取消"/"不做了"结束流程

确认后同步更新任务文档:

  • 标记“需求确认”状态为已完成
  • 更新“下一步指令”为进入技术方案设计

文档规范要求

需求文档 vs 技术文档边界

需求文档应包含:

  • 业务背景和目标
  • 用户角色和使用场景
  • 功能需求详述(做什么)
  • 业务流程和规则
  • 数据需求(业务视角)
  • 非功能性需求
  • 验收标准

需求文档禁止包含:

  • 数据库表设计
  • 接口定义(URL、参数、响应格式)
  • 技术架构设计
  • 代码结构设计
  • 具体技术选型

业务流程图要求

  • 简单流程(≤3步):用文字描述
  • 复杂流程(>3步或有分支):必须使用Mermaid流程图
  • 流程图必须体现业务逻辑,不是技术实现

用户场景描述

每个主要功能都要有典型使用场景:

场景X:{场景名称}
{用户角色}在{什么情况下}需要{做什么事情},期望{达到什么目标}。

文档完整性要求

必须包含以下章节:

  1. 功能概述(业务背景、功能定位、核心价值)
  2. 用户角色与场景(角色定义、典型场景)
  3. 功能需求详述(每个功能的详细描述)
  4. 业务流程(主要流程的Mermaid图)
  5. 数据需求(业务视角的数据实体)
  6. 非功能性需求(性能、安全、兼容性)
  7. 约束条件(技术约束、业务约束)
  8. 验收标准(功能验收、性能验收)
  9. 风险评估(技术风险、业务风险)

技术实现澄清点

需求文档中应澄清以下技术相关问题:

  • 消息通知方式:是否需要实时推送?轮询频率要求?
  • 数据实时性要求:哪些数据需要实时查询?
  • 数据保留策略:永久保存 vs 定期清理?业务数据 vs 日志数据?
  • 系统集成方式:与现有系统如何集成?
  • 性能要求:并发量?响应时间?数据量?

注意事项

  1. 禁止假设 - 用户没说的不要自己编
  2. 禁止跳过 - 必须完成澄清才能输出文档
  3. 禁止合并 - 需求确认前不要开始技术方案
  4. 保持耐心 - 复杂需求可能需要多轮澄清
  5. 记录变更 - 如果澄清过程中需求有变化,及时更新文档
  6. 严格边界 - 需求文档不能包含技术实现细节
  7. 业务导向 - 从用户和业务角度描述需求,不涉及技术如何实现
  8. 任务文档 - 需求开始必须创建并持续更新全流程任务文档

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 Proj Analyze Req AI skill do?

需求分析与确认(阶段一)。用于理解用户需求、澄清细节、明确功能边界,生成需求分析文档。

Why use Proj Analyze Req on TypingMind?

Because you install it once and use it with any model. Proj Analyze Req 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 Proj Analyze Req in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zhangloveyan/backend-skill/tree/main/.claude/skills/proj-analyze-req. 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 Proj Analyze Req?

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 Proj Analyze Req?

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

Is the Proj Analyze Req AI skill free?

Yes. It is published on GitHub by zhangloveyan under the MIT license. 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 👇