# everything-ai-coding
**Repository Path**: gerogeyan/everything-ai-coding
## Basic Information
- **Project Name**: everything-ai-coding
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-07-21
- **Last Updated**: 2026-07-21
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
## 为什么选择 Everything AI Coding?
AI Coding Agent 越来越强,但周边生态仍然很分散。想找到可靠的 MCP Server、可复用 Skill、实用 Rule 或 Prompt,通常要在多个仓库和格式之间反复跳转。
Everything AI Coding 是一个**持续更新的知识库**,从 9+ 个上游源自动收集、去重、富化和评分资源。每个条目都包含质量信号 —— LLM 评估的编程相关性、文档质量、专业度,加上活跃度和社区热度等健康度指标 —— 帮你在安装之前先做评估。你可以直接在 GitHub 上浏览,通过[交互式 Web 目录](https://zgsm-ai.github.io/everything-ai-coding/)探索,或者用 [Coding Hub](#coding-hub) 工具一条命令搜索和安装。
## 📚 知识库
### [🔌 MCP 服务器](./catalog/mcp/) — 9742 个条目
将 AI Agent 连接到外部工具、数据库和服务的 Model Context Protocol 服务器。
| 名称 | ⭐ Stars | 评分 | 描述 |
|------|----------|------|------|
| [Headroom](https://github.com/chopratejas/headroom) | 60.4k | 98 | AI 智能体上下文压缩层,减少 60-95% token 使用,支持可逆压缩与跨智能体内存共享。 |
| [upstash/context7](https://github.com/upstash/context7) | 59.5k | 98 | 实时注入最新库文档和代码示例到 LLM 上下文的 MCP 服务器,消除 API 幻觉。 |
| [ChromeDevTools/chrome-devtools-mcp](https://github.com/ChromeDevTools/chrome-devtools-mcp) | 47.2k | 98 | 谷歌官方 MCP 服务器,让 AI 编程代理直接操控 Chrome DevTools 进行调试、性能分析和浏览器自动化。 |
| [microsoft/playwright-mcp](https://github.com/microsoft/playwright-mcp) | 35.3k | 98 | 微软官方 MCP 服务器,通过 Playwright 让 AI 精确控制浏览器进行网页自动化和数据抓取。 |
| [DeusData/codebase-memory-mcp](https://github.com/DeusData/codebase-memory-mcp) | 33.0k | 98 | 高性能代码智能 MCP 服务器,将整个代码库索引为持久化知识图谱,为 AI 代理提供调用关系、依赖与代码结构记忆,按需精准检索相关上下文。 |
[浏览全部 MCP 服务器 →](./catalog/mcp/) · [在线浏览 →](https://zgsm-ai.github.io/everything-ai-coding/#/browse?type=mcp)
---
### [🎯 Skills 技能](./catalog/skills/) — 13194 个条目
AI 编程助手的可复用能力和工作流。
| 名称 | 来源 | 评分 | 描述 |
|------|------|------|------|
| [bug-triage](https://github.com/AgentWrapper/agent-orchestrator/tree/main/skills/bug-triage) | github-trending | 96 | 针对 ReverbCode 仓库的错误分类技能,包含重复搜索、创建完整上下文的 GitHub issue 及推送修复 PR。 |
| [a-stock-data](https://github.com/simonlin1212/a-stock-data/tree/main/) | github-trending | 96 | A股全栈数据工具包,覆盖行情、研报、信号、资金面等七层数据,内嵌全部调用代码。 |
| [acpx](https://github.com/openclaw/acpx/tree/main/skills/acpx) | github-trending | 96 | 一个用于通过 ACP 编排 AI 编码代理的无头 CLI,支持会话管理、队列提示和定义多代理工作流。 |
| [crabbox](https://github.com/openclaw/acpx/tree/main/.agents/skills/crabbox) | github-trending | 96 | 用于远程Linux验证的CLI包装器,支持AWS、Blacksmith Testbox和SSH,用于CI/CD测试和端到端验证。 |
| [make-latex-model](https://github.com/huangwb8/ChineseResearchLaTeX/tree/main/skills/make-latex-model) | github-trending | 96 | 用于 ChineseResearchLaTeX 项目中 LaTeX 模板的高保真对齐、样式优化和像素级比对的专业 AI 技能。 |
[浏览全部 Skills →](./catalog/skills/) · [在线浏览 →](https://zgsm-ai.github.io/everything-ai-coding/#/browse?type=skill)
---
### [📋 Rules 规则](./catalog/rules/) — 245 个条目
编码规范和 AI 行为准则,确保开发一致性。
| 名称 | 来源 | 评分 | 分类 |
|------|------|------|------|
| [python-checklist-py2-总规范](https://github.com/yhangf/csc-plugins/tree/main/cospowers-integration-verification-plugin/rules/coding-standards/python-checklist-py2-总规范.md) | plugin-bundled-rule | 95 | backend |
| [shell_checklist](https://github.com/yhangf/csc-plugins/tree/main/cospowers-integration-verification-plugin/rules/coding-standards/shell_checklist.md) | plugin-bundled-rule | 95 | tooling |
| [Go单元测试规范](https://github.com/yhangf/csc-plugins/tree/main/cospowers-integration-verification-plugin/rules/testing-standards/Go单元测试规范.md) | plugin-bundled-rule | 95 | backend |
| [单元测试规范](https://github.com/yhangf/csc-plugins/tree/main/cospowers-integration-verification-plugin/rules/testing-standards/单元测试规范.md) | plugin-bundled-rule | 95 | tooling |
| [python-checklist-py2-总规范](https://github.com/yhangf/csc-plugins/tree/main/cospowers-tdd-development-plugin/rules/coding-standards/python-checklist-py2-总规范.md) | plugin-bundled-rule | 95 | backend |
[浏览全部 Rules →](./catalog/rules/) · [在线浏览 →](https://zgsm-ai.github.io/everything-ai-coding/#/browse?type=rule)
---
### [💡 Prompts 提示词](./catalog/prompts/) — 654 个条目
面向开发者的提示词模板,覆盖常见编码场景。
| 名称 | 来源 | 评分 | 分类 |
|------|------|------|------|
| [Comprehensive repository analysis](https://github.com/f/prompts.chat/blob/HEAD/PROMPTS.md#comprehensive-repository-analysis) | prompts.chat | 96 | security |
| [Frontend Developer Skill](https://github.com/f/prompts.chat/blob/HEAD/PROMPTS.md#frontend-developer-skill) | prompts.chat | 96 | frontend |
| [Backend Architect](https://github.com/f/prompts.chat/blob/HEAD/PROMPTS.md#backend-architect) | prompts.chat | 96 | database |
| [Frontend Developer](https://github.com/f/prompts.chat/blob/HEAD/PROMPTS.md#frontend-developer) | prompts.chat | 96 | frontend |
| [Mobile App Builder](https://github.com/f/prompts.chat/blob/HEAD/PROMPTS.md#mobile-app-builder) | prompts.chat | 96 | frontend |
[浏览全部 Prompts →](./catalog/prompts/) · [在线浏览 →](https://zgsm-ai.github.io/everything-ai-coding/#/browse?type=prompt)
---
### [🧩 Plugins 插件](./catalog/plugins/) — 1451 个条目
打包发布的市场插件(含 skills + commands + agents + MCP servers)。
> 主要适用 Claude Code,opencode 部分兼容(npm),cursor / windsurf / costrict 暂无等价机制。
| 名称 | 来源 | 评分 | 描述 |
|------|------|------|------|
| [superpowers](https://github.com/obra/superpowers.git) | Anthropic 官方 | 100 | 教授 Claude Code 系统化开发工作流,包括测试驱动开发、调试、代码审查和子代理驱动开发的详细技能文档。 |
| [chrome-devtools-mcp](https://github.com/ChromeDevTools/chrome-devtools-mcp.git) | Anthropic 官方 | 100 | Chrome DevTools MCP 服务器,供 AI 编程代理通过 CLI 和 MCP 工具调试、自动化和分析网页。 |
| [hyperframes](https://github.com/heygen-com/hyperframes.git) | Anthropic 官方 | 100 | HyperFrames 让开发者用 HTML/CSS/JS 编写确定性视频合成,支持 GSAP 动画、字幕、语音合成和 WebGL 特效。 |
| [claude-code-setup](https://github.com/anthropics/claude-plugins-official/tree/main/plugins/claude-code-setup) | Anthropic 官方 | 100 | 分析代码库并推荐定制的 Claude Code 自动化,如钩子、技能、MCP 服务器和子代理。 |
| [mcp-tunnels](https://github.com/anthropics/claude-plugins-official/tree/main/plugins/mcp-tunnels) | Anthropic 官方 | 100 | Claude插件,通过Anthropic隧道连接私有MCP服务器,提供Docker Compose快速启动。 |
[浏览全部 Plugins →](./catalog/plugins/) · [在线浏览 →](https://zgsm-ai.github.io/everything-ai-coding/#/browse?type=plugin)
---
## 数据来源与质量
Everything AI Coding 从多类上游源聚合资源,经富化、评分后发布清洗后的目录。
| 类型 | 来源 |
|------|------|
| MCP | [awesome-mcp-servers](https://github.com/wong2/awesome-mcp-servers) · [Awesome-MCP-ZH](https://github.com/yzfly/Awesome-MCP-ZH) · [mcp.so](https://mcp.so) · [registry.modelcontextprotocol.io](https://registry.modelcontextprotocol.io)(官方 registry,仅保留 `active` + `isLatest`,约 7,500 条) |
| Skills | Tier 1: [anthropics/skills](https://github.com/anthropics/skills) · [Ai-Agent-Skills](https://github.com/skillcreatorai/Ai-Agent-Skills) · [antigravity-awesome-skills](https://github.com/sickn33/antigravity-awesome-skills) · [ai-agents-public](https://github.com/vasilyu1983/ai-agents-public) · [skills.sh](https://skills.sh)(通过 [mastra-ai/skills-api](https://github.com/mastra-ai/skills-api) 接入,`install_count ≥ 1000`)
Tier 2: [awesome-repo-configs](https://github.com/Chat2AnyLLM/awesome-repo-configs) · [awesome-openclaw-skills](https://github.com/VoltAgent/awesome-openclaw-skills) · [openclaw/skills](https://github.com/openclaw/skills)
Tier 3: `catalog/skills/curated.json` |
| Rules | [awesome-cursorrules](https://github.com/PatrickJS/awesome-cursorrules) · [rules-2.1-optimized](https://github.com/Mr-chen-05/rules-2.1-optimized) · [SchneiderSam/awesome-windsurfrules](https://github.com/SchneiderSam/awesome-windsurfrules) + [balqaasem/awesome-windsurfrules](https://github.com/balqaasem/awesome-windsurfrules)(双仓库 cross-repo 去重) |
| Prompts | [prompts.chat](https://github.com/f/prompts.chat) · [wonderful-prompts](https://github.com/langgptai/wonderful-prompts) |
### 质量评分
每个条目都有 0–100 的综合评分:`final_score = LLM × 0.85 + 健康度 × 0.15`
**LLM 维度**(1–5 分,最多 6 个):编程相关性、文档完整度、描述准确性、写作质量、专业度、安装清晰度(仅 MCP 和 Skill)
**健康度信号**:活跃度(🟢 活跃 / 🟡 停滞 / 🔴 停更)、流行度(GitHub Stars)、来源可信度(上游声誉)
**决策阈值**:接受(≥ 65)· 复审(50–64)· 拒绝(< 50)
各子目录 README 展示按此综合评分排名的 Top 100 条目。
### 流水线
1. **同步** — `scripts/sync_*.py` 每周从上游拉取数据
2. **合并** — `scripts/merge_index.py` 跨源去重,合并元数据
3. **评估** — 单次 LLM 调用:6 维评分 + 富化(tags、summary、tech_stack)+ 健康度信号
4. **发布** — GitHub Actions 自动刷新目录、生成 README 表格、更新 Web 目录
项目结构
```text
everything-ai-coding/
├── install.sh / install.ps1 # 一键安装脚本
├── catalog/ # 生成后的资源目录数据
│ ├── index.json # 完整合并索引(4000+ 条目)
│ ├── search-index.json # 轻量搜索索引
│ ├── mcp/ # MCP 服务器 — 索引 + README
│ ├── skills/ # Skills — 索引 + README
│ ├── rules/ # Rules — 索引 + README
│ └── prompts/ # Prompts — 索引 + README
├── platforms/ # 各平台 skill 与命令定义
├── scripts/ # 同步、合并、评分、生成脚本
└── .github/workflows/ # CI 自动化
```
---
## 🛠 Coding Hub — 搜索与安装
Everything AI Coding 同时提供命令行工具,让你在 AI 编程助手中直接搜索、浏览和安装资源。
### 快速开始
按平台执行安装命令即可:
**macOS / Linux**
```bash
# Costrict CLI(在项目根目录执行)
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform costrict
# VSCode Costrict 插件
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform vscode-costrict
# Claude Code
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform claude-code
# Opencode(在项目根目录执行)
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform opencode
```
**Windows (PowerShell)**
```powershell
# Costrict CLI
irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1 | iex
# 自动检测失败时手动指定平台
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1))) -Platform costrict
```
安装后可以先试一个搜索命令:
```bash
# Claude Code
/eac:search typescript
# Opencode / Costrict CLI / VSCode Costrict (Roo Code)
/eac-search typescript
```
也可以把下面的提示词直接交给另一个 AI Agent:
```text
你是一个自动安装助手。请访问下面的 URL,阅读其中的 "For Agents" 小节,
然后严格按说明完成 Everything AI Coding 安装。
不要 clone 仓库,只读取这个 raw 文件:
https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/README.md
安装结束后,请说明你使用了哪个平台路径,以及验证是否成功。
```
### 平台支持
Everything AI Coding 当前支持四个 AI Coding 平台,共用同一份资源目录,但命令格式与安装路径略有差异。
| | Claude Code | Costrict | Opencode | VSCode Costrict (Roo Code) |
|---|---|---|---|---|
| 搜索 | `/eac:search [type:mcp]` | `/eac-search [type:mcp]` | `/eac-search [type:mcp]` | `/eac-search [type:mcp]` |
| 浏览 | `/eac:browse [category]` | `/eac-browse [category]` | `/eac-browse [category]` | `/eac-browse [category]` |
| 推荐 | `/eac:recommend` | `/eac-recommend` | `/eac-recommend` | `/eac-recommend` |
| 安装 | `/eac:install ` | `/eac-install ` | `/eac-install ` | `/eac-install ` |
| 卸载 | `/eac:uninstall ` | `/eac-uninstall ` | `/eac-uninstall ` | `/eac-uninstall ` |
| 更新 | `/eac:update` | `/eac-update` | `/eac-update` | `/eac-update` |
| 进化 | `/eac:evo ` | `/eac-evo ` | `/eac-evo ` | `/eac-evo ` |
平台路径差异
| | Claude Code | Costrict | VSCode Costrict | Opencode |
|---|---|---|---|---|
| 全局 Skill 路径 | `~/.claude/skills/eac/` | `~/.costrict/skills/eac/` | `~/.costrict/skills/eac/` | `~/.opencode/skills/eac/` |
| 命令路径 | 同一全局目录 | `.costrict/eac/commands/`(项目级) | `~/.roo/commands/`(全局) | `.opencode/command/`(项目级) |
| 分隔符 | `:` | `-` | `-` | `-` |
- **Costrict CLI** 需要在每个项目根目录安装命令文件。
- **VSCode Costrict / Roo Code** 将命令文件安装到全局 `~/.roo/commands/`。
- **Claude Code** 可以从全局技能目录直接加载完整 skill 与子命令。
- **Opencode** 需要在每个项目下安装 `.opencode/command/` 中的命令文件。
### 给 Agent 的安装说明
> 如果你是自动安装 Everything AI Coding 的 AI Agent,请严格按本节操作。
#### 第 1 步:运行安装脚本
安装脚本会尽量自动识别你当前所在的平台。
**macOS / Linux**
```bash
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash
```
**Windows (PowerShell)**
```powershell
irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1 | iex
```
自动识别依赖以下进程级环境变量:
| 环境变量 | 平台 |
|----------|------|
| `COSTRICT_CALLER=vscode` | VSCode Costrict 插件 |
| `COSTRICT_RUNNING=1` | Costrict CLI |
| `CLAUDECODE=1` | Claude Code |
| `OPENCODE=1` | Opencode |
如果自动识别失败,请手动指定平台。
**macOS / Linux**
```bash
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform
```
**Windows (PowerShell)**
```powershell
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1))) -Platform
```
示例:
```bash
# Claude Code (macOS/Linux)
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform claude-code
# Opencode(在项目根目录执行)
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform opencode
```
```powershell
# Claude Code (Windows)
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1))) -Platform claude-code
```
备选方案:手动下载文件,不使用 curl | bash
当你不能直接执行安装脚本时,可以按平台分别下载 skill 和命令文件。
**Costrict CLI**(Skill 全局 + Commands 项目级)
```bash
mkdir -p ~/.costrict/skills/eac
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/costrict/skills/eac/SKILL.md" -o ~/.costrict/skills/eac/SKILL.md
mkdir -p .costrict/eac/commands
for cmd in search browse recommend install uninstall update; do
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/costrict/commands/eac/eac-${cmd}.md" -o .costrict/eac/commands/eac-${cmd}.md
done
```
**VSCode Costrict 插件 / Roo Code**(Skill 全局 + Commands 全局)
```bash
mkdir -p ~/.costrict/skills/eac
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/vscode-costrict/skills/eac/SKILL.md" -o ~/.costrict/skills/eac/SKILL.md
mkdir -p ~/.roo/commands
for cmd in search browse recommend install uninstall update; do
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/vscode-costrict/commands/eac/eac-${cmd}.md" -o ~/.roo/commands/eac-${cmd}.md
done
```
**Claude Code**(Skill + Commands 全局安装)
```bash
mkdir -p ~/.claude/skills/eac
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/claude-code/skills/eac/SKILL.md" -o ~/.claude/skills/eac/SKILL.md
for cmd in search browse recommend install uninstall update; do
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/claude-code/commands/eac/${cmd}.md" -o ~/.claude/skills/eac/${cmd}.md
done
```
**Opencode**(Skill 全局 + Commands 项目级)
```bash
mkdir -p ~/.opencode/skills/eac
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/opencode/skills/eac/SKILL.md" -o ~/.opencode/skills/eac/SKILL.md
mkdir -p .opencode/command
for cmd in search browse recommend install uninstall update; do
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/opencode/command/eac-${cmd}.md" -o .opencode/command/eac-${cmd}.md
done
```
#### 第 2 步:验证安装是否成功
运行搜索命令确认命令是否可用:
```text
# Costrict CLI / Opencode
/eac-search typescript
# VSCode Costrict 插件
在聊天窗口发送:"用 eac 搜索 typescript"
# Claude Code
/eac:search typescript
```
期望结果:返回一个 Markdown 表格,列出匹配资源。如果命令不存在,说明文件没有安装到正确的平台路径。
#### 可用命令
| 命令 | 说明 |
|------|------|
| `search <关键词> [type:mcp\|skill\|rule\|prompt]` | 搜索资源,可按类型过滤 |
| `browse [分类] [type:...]` | 按分类浏览 |
| `recommend [type:...]` | 根据当前项目技术栈推荐资源 |
| `install <名称>` | 安装资源 |
| `uninstall <名称>` | 卸载资源 |
| `update` | 更新到最新版本 |
| `evo ` | 对已在本机装好的 skill / prompt / rule 做 7 维质量评分与改进(rubric 改编自 [darwin-skill](https://github.com/alchaincyf/darwin-skill)) |
#### 数据接口
搜索、浏览、推荐依赖轻量搜索索引,安装则读取单条资源 API:
| 用途 | URL |
|------|-----|
| 搜索索引 | `https://zgsm-ai.github.io/everything-ai-coding/api/v1/search-index.json` |
| 单条 API | `https://zgsm-ai.github.io/everything-ai-coding/api/v1/{type}/{id}.json` |
| 类型索引 | `https://zgsm-ai.github.io/everything-ai-coding/api/v1/{type}/index.json` |
| 全量索引回退地址 | `https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/catalog/index.json` |
## 为什么推荐 Costrict?
如果你喜欢 Everything AI Coding 的工作流,也可以试试 **[Costrict](https://github.com/zgsm-ai/costrict)** —— 我们更完整的 AI Coding Agent 平台,适合更强的自动化与团队协作场景。
[立即了解 Costrict →](https://github.com/zgsm-ai/costrict)
## 参与贡献
欢迎提交 PR,为 `catalog/` 下相应目录补充优质资源。提交前请确保:
- 资源与编程或 AI 辅助开发相关,
- `source_url`、`description`、tags 等字段准确,
- 数据格式符合 `catalog/schema.json`。
如果你需要的是维护视角的上下文,而不是快速安装说明,可以继续看仓库内 wiki:[`docs/wiki/`](./docs/wiki/README.md)。
## 致谢
`/eac:evo` 命令的质量评分 rubric 改编自 **[darwin-skill](https://github.com/alchaincyf/darwin-skill)**(MIT License © 花叔)—— 一个受 Karpathy autoresearch 启发的自主 skill 优化系统。darwin-skill 首次在 SKILL.md 语境下系统化提出"结构 + 效果"双重评估与棘轮机制(只保留可测量的改进)。Everything AI Coding 在客户端按需场景下作了简化适配:暂缓动态实测维和棘轮机制,保留并重写了工作流清晰度、指令具体性、边界条件覆盖、检查点设计、整体架构等核心维度,以适配 evo 按需调用的交互节奏。完整 rubric 规范见 [`docs/wiki/evo-rubric.md`](./docs/wiki/evo-rubric.md)。
感谢花叔把想法与原 skill 开源出来。
## 免责声明
Everything AI Coding 是一个第三方开源资源的索引与安装辅助项目。目录中的 MCP Server、Skill、Rule、Prompt 的版权与责任均归原作者所有。
本仓库 **不对** 第三方资源的安全性、可用性、准确性或合规性作任何保证。请在使用前自行审查源码与许可证;如果发现安全或版权问题,欢迎通过 Issue 反馈。
本项目遵循 [MIT License](LICENSE) 发布。