ARCHITECTURE.md 生成指南
基于项目目录结构和技术栈分析生成，不复制空壳章节。
应从项目分析中提取：
- 依赖文件 → 技术选型表（层级 / 技术 / 说明）
- src/ 目录扫描 → 核心模块列表及职责描述
- 入口文件分析 → 数据流描述（Mermaid 或 ASCII）
- 前后端分离的项目 → 分别描述各层的职责和边界
质量目标： 让新协作者读完后能理解"代码在哪里、各部分做什么、数据怎么流动"。
/project-init
@08ab532项目初始化工具。读取全局协议 ~/.claude/CLAUDE.md，分析项目实际情况，生成项目特定的 CLAUDE.md 和 docs/ 上下文。本技能应在用户说"初始化项目"、"项目设置"、"配置 Claude Code"、"新建项目配置"时使用，或在进入一个新项目需要快速配置时使用。不要用于：Skill 内容开发或验收（用 skill-lint）、单次 Skill 安装（用 skill-manager）、代码生成。
Ask your Agent
Use this Skill: https://skilld.dev/gh/cat-xierluo/legal-skills/project-init
This session only. Nothing lands on disk.
≈129 tokens on demand. Your agent reads this file only when SKILL.md points to it.
Source: SKILL.md on GitHub
Third-party checks
No alerts15d3 checks · Risk SAFE
- Gen Agent Trust Hub15d
The project-init skill is a legitimate utility for setting up new AI agent project environments. It automates directory creation, generates documentation based on project analysis, and configures agent permissions. The skill includes security-focused templates that explicitly deny destructive system commands.
- Socket15d
No alerts
- Snyk15d
Risk: LOW · No issues
Provenance
Signed by skilld at 08ab532. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.
Last checked against GitHub yesterday.
Activeupdated 2 days ago
Capability
- homepage
- https://github.com/cat-xierluo/legal-skills
- author
- 杨卫薪律师（微信ywxlaw）
- version
- 1.2.6