agentleFS
kip-vibecodingkip-vibecoding/code-documents-auto-skill/skills/docs-prepare/SKILL.md

docs-prepare

Skill1 starsChanged 5 months agoMITView on GitHub

开发前准备,读取相关文档并输出开发方案。开始新任务前运行。

The file

Files
SKILL.md

/docs-prepare — 开发前准备

当用户输入 /docs-prepare <任务描述> 时,执行以下流程:

步骤 1:检查文档是否存在

  • 检查 .ai-context/ 目录是否存在
  • 如果不存在,提示用户先运行 /docs-scan
  • 如果存在,继续执行

步骤 2:解析任务描述

分析用户的任务描述,识别:

分析维度识别内容示例
涉及模块哪些模块需要修改"登录" → auth 模块
涉及功能什么类型的功能"跨域" → 配置相关
涉及层哪些架构层需要改动Controller/Service/Repository
变更类型新增/修改/删除新增接口、修改逻辑、删除废弃代码

步骤 3:读取相关文档

必读文档(每次都读):

  • .ai-context/architecture.md - 理解整体架构
  • .ai-context/guidelines/coding-style.md - 遵循编码规范

按需读取(根据任务涉及的模块):

  • .ai-context/modules/{相关模块}.md - 理解模块设计
  • .ai-context/api/{相关API}.md - 理解接口设计
  • .ai-context/database/README.md - 如果涉及数据模型变更
  • .ai-context/middleware/README.md - 如果涉及中间件变更

步骤 4:输出开发方案

必须输出完整的开发方案,不仅仅是读取摘要:

📖 已读取以下文档:

- architecture.md - 系统架构
- modules/auth.md - 认证模块
- api/chat.md - 对话接口
- database/README.md - 数据库设计

---

## 📋 开发方案

### 任务理解

{用一句话描述用户要做什么}

### 涉及模块

| 模块 | 文件路径 | 变更类型 | 说明 |
|------|----------|----------|------|
| auth | src/auth/... | 修改 | {具体变更} |
| chat | src/chat/... | 新增 | {具体变更} |

### 修改文件清单

| 文件 | 变更内容 | 优先级 |
|------|----------|--------|
| src/auth/AuthController.java | 新增登录接口 | 高 |
| src/auth/AuthService.java | 实现登录逻辑 | 高 |

### 实现步骤

1. **第一步**:{具体步骤}
   - 涉及文件:{文件列表}
   - 预计改动:{改动说明}

2. **第二步**:{具体步骤}
   - 涉及文件:{文件列表}
   - 预计改动:{改动说明}

### 影响范围

- **直接影响**:{直接修改的模块}
- **间接影响**:{可能受影响的模块}
- **无影响**:{确认不受影响的模块}

### 风险点

- ⚠️ {风险1}:{说明和规避方案}

### 需要确认的问题

- ❓ {问题1}:{需要用户确认的点}

---

✅ 准备就绪,可以开始开发!

步骤 5:等待用户确认

  • 如果用户有疑问,解答后更新方案
  • 如果用户确认,开始开发
  • 如果用户修改需求,重新执行步骤 2-4

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.