Best use case
project-guide is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
引导用户填写项目开发指导模板。激活条件：用户想要开发新项目、表达项目需求、创建应用。
Teams using project-guide should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/project-guide/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How project-guide Compares
| Feature / Agent | project-guide | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
引导用户填写项目开发指导模板。激活条件：用户想要开发新项目、表达项目需求、创建应用。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# 项目开发指导助手
## 概述
这个 Skill 用于引导和帮助用户完成项目开发指导模板的填写。当用户想要开发新项目或对现有项目进行重大修改时，使用此 Skill 来收集必要的信息。
## 触发条件
在以下情况下应该激活此 Skill：
1. 用户表达想要开发一个新项目
2. 用户提到"帮我整理一下项目需求"
3. 用户想要使用 AI 开发应用但不知道如何描述需求
4. 用户说"我要做一个 XX 系统"
5. 用户询问如何开始一个项目开发
## 工作流程
### 阶段一：项目概览采集
**目标：** 收集项目的基本信息
需要询问用户以下问题：
1. **项目名称**
- "你希望给项目起什么名字？"
- 或者 "这个项目叫什么？"
2. **项目类型**
- "这是一个什么类型的项目？Web应用、移动端、API服务还是桌面工具？"
3. **项目简介**
- "能用一两句话描述一下这个项目吗？它是做什么的？"
- "这个项目要解决什么问题？"
4. **核心目标**
- "你做这个项目最主要想要达成什么目标？"
- "除了主要目标，还有其他期望吗？"
### 阶段二：详细需求采集
**目标：** 收集详细的功能和业务需求
需要引导用户填写 `requirements.md`，询问：
1. **用户群体**
- "谁会使用这个产品？"
- "他们有什么特点和需求？"
2. **核心功能**
- "这个产品最核心的功能是什么？"
- "用户最常用的功能有哪些？"
- "有没有必须有的功能（P0），重要但不是必须的功能（P1），以及可选功能（P2）？"
3. **业务流程**
- "能描述一下典型的使用流程吗？"
- "比如用户进来后第一步做什么，然后呢？"
4. **数据需求**
- "需要存储什么类型的数据？"
- "有没有用户账号体系？需要哪些信息？"
5. **非功能需求**
- "对性能有要求吗？比如响应时间、并发数？"
- "有安全或合规方面的要求吗？"
- "需要支持哪些平台或浏览器？"
### 阶段三：技术约束采集
**目标：** 了解技术方面的限制和要求
1. **技术偏好**
- "有没有偏好的技术栈？比如必须用某种语言或框架？"
- "团队对哪些技术比较熟悉？"
2. **已有资源**
- "有没有已经可以复用的组件或服务？"
- "需要集成哪些第三方服务？"
3. **约束条件**
- "预算或时间有限制吗？"
- "有没有必须兼容的现有系统？"
### 阶段四：生成文档
**目标：** 将收集到的信息整理成完整的模板文档
1. 根据收集的信息，生成/更新 `main.md`
2. 根据收集的信息，生成/更新 `requirements.md`
3. 如果用户已确定技术选型，生成 `architecture.md`
4. 如果涉及接口，生成 `api.md`
## 输出格式
完成信息收集后，应该：
1. **总结确认**
- 向用户确认理解是否正确
- 询问是否有遗漏或需要补充的地方
2. **提供下一步建议**
- "根据你提供的信息，我已经整理出项目模板。"
- "接下来你可以："
- "1. 查看并完善 templates 目录下的模板文件"
- "2. 确认无误后告诉 AI '请从 main.md 开始阅读'"
- "3. AI 将根据这些信息开始项目开发"
## 模板文件位置
项目模板位于 `templates/` 目录下：
- `templates/main.md` - 项目概览和索引
- `templates/requirements.md` - 详细需求文档
- `templates/architecture.md` - 技术架构设计
- `templates/api.md` - API 接口设计
- `templates/update.md` - 需求变更记录
## 注意事项
1. **循序渐进**：不要一次性问所有问题，而是根据用户的回答逐步深入
2. **解释原因**：适时解释为什么需要这些信息，帮助用户理解
3. **提供示例**：如果用户不知道如何描述，可以提供示例
4. **记录不确定**：对于用户不确定的地方，先记录下来，后续再确认
5. **保持简洁**：问题要简洁明了，避免过度技术化的术语Related Skills
china-relocation-guide
Use when expats, international students, or digital nomads need guidance on relocating to China, choosing cities, understanding visa requirements, or planning their move.
kep-guide
Türkiye Kayıtlı Elektronik Posta (KEP) rehberi. KEP nedir, nasıl alınır, zorunlu mu, hangi kurumlar kullanıyor, entegrasyon yöntemleri. Use when asked about KEP, registered electronic mail, Türkkep, or Turkish official electronic communication.
project-watcher
项目规划与进度追踪。维护 roadmap，git commit 通知，远程部署感知，与飞书集成。
QuackExchange — Developer Guide
QuackExchange is a Q&A platform for AI agents and humans.
project-retrospective
自动项目复盘机制。当完成复杂项目后，自动提取最优路径生成skill，并记录踩坑经验到memory。
project-deep-analyzer
深度分析项目的系统边界、核心概念、模块架构、关键算法、技术选型以及错误排查。当用户需要深入理解代码库或定位疑难问题时调用。
OpenClaw Install Guide (WSL2 Windows)
Complete step-by-step installation guide for OpenClaw on Windows 10/11 with WSL2, includes common pitfalls and solutions from real installation experience.
epistemic-guide
Helps users examine the logical foundations of their beliefs through Socratic questioning when they make potentially dubious claims. Uses transparent verification (with user consent) and guided questioning to help users discover gaps in their reasoning. Privacy-friendly - can operate entirely offline using only Socratic method, or with explicit user consent for external fact-checking. Triggers on sensitive topics (philosophy, religion, science, conspiracy theories, misinformation) but always respects user autonomy and privacy.
project-evaluator
描述一个项目想法，AI 从市场/技术/商业/风险四个维度系统评估， 输出评估报告、竞品速查、MVP建议，帮你决策「值不值得做」。
memos-memory-guide
Use the MemOS Lite memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own preferences or history, or when you need to answer from prior context. When auto-recall returns nothing (long or unclear user query), generate your own short search query and call memory_search. Use task_summary when you need full task context, skill_get for experience guides, and memory_timeline to expand around a memory hit.
project-writing
Always wrap the main content of your response within <ama-doc></ama-doc> tags to clearly distinguish the core information from any introductory or concluding remarks.
tdd-guide
Test-driven development skill for writing unit tests, generating test fixtures and mocks, analyzing coverage gaps, and guiding red-green-refactor workflows across Jest, Pytest, JUnit, Vitest, and Mocha. Use when the user asks to write tests, improve test coverage, practice TDD, generate mocks or stubs, or mentions testing frameworks like Jest, pytest, or JUnit. Handles test generation from source code, coverage report parsing (LCOV/JSON/XML), quality scoring, and framework conversion for TypeScript, JavaScript, Python, and Java projects.