Microsoft Skill Creator：为智能体创建混合技能，本地存储核心知识，动态查询Learn MCP

microsoft-skill-creator by github/awesome-copilot

7,400 周安装量

26,700 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/github/awesome-copilot --skill microsoft-skill-creator

AI/机器学习开发云服务

🇨🇳中文介绍

Microsoft Skill Creator

为 Microsoft 技术创建混合技能，这些技能在本地存储核心知识，同时支持动态的 Learn MCP 查询以获取更深入的详细信息。

关于技能

技能是模块化包，通过专业知识和工作流程扩展智能体的能力。一个技能可以将通用智能体转变为特定领域的专家。

技能结构

skill-name/
├── SKILL.md (必需)     # 前言（名称、描述）+ 使用说明
├── references/             # 按需加载到上下文中的文档
├── sample_codes/           # 可运行的代码示例
└── assets/                 # 输出中使用的文件（模板等）

核心原则

前言至关重要 : name 和 description 决定了技能何时触发——务必清晰全面
简洁是关键 : 只包含智能体尚不了解的内容；上下文窗口是共享的
避免重复 : 信息应存在于 SKILL.md 或参考文件中，而非两者皆有

Learn MCP 工具

工具	用途	使用时机

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

步骤 1：调研主题

使用 Learn MCP 工具分三个阶段建立深入理解：

阶段 1 - 范围发现：

microsoft_docs_search(query="{technology} overview what is")
microsoft_docs_search(query="{technology} concepts architecture")
microsoft_docs_search(query="{technology} getting started tutorial")

阶段 2 - 核心内容：

microsoft_docs_fetch(url="...")  # 获取阶段 1 中的页面
microsoft_code_sample_search(query="{technology}", language="{lang}")

阶段 3 - 深度挖掘：

microsoft_docs_search(query="{technology} best practices")
microsoft_docs_search(query="{technology} troubleshooting errors")

调研后，请验证：

能否用一段话解释该技术的功能
已识别 3-5 个关键概念
拥有基本用法的可运行代码
了解最常见的 API 模式
拥有用于深入主题的搜索查询

步骤 2：与用户澄清

展示发现并提出问题：

"我发现了这些关键领域：[列表]。哪些是最重要的？"
"智能体将主要使用此技能执行哪些任务？"
"代码示例应优先考虑哪种编程语言？"

步骤 3：生成技能

使用 skill-templates.md 中的相应模板：

技术类型	模板
客户端库，NuGet/npm 包	SDK/库
Azure 资源	Azure 服务
应用开发框架	框架/平台
REST API，协议	API/协议

生成的技能结构

{skill-name}/
├── SKILL.md                    # 核心知识 + Learn MCP 指导
├── references/                 # 详细的本地文档（如果需要）
└── sample_codes/               # 可运行的代码示例
    ├── getting-started/
    └── common-patterns/

步骤 4：平衡本地与动态内容

在以下情况本地存储：

基础性的（任何任务都需要）
频繁访问的
稳定的（不会改变）
难以通过搜索找到的

在以下情况保持动态：

详尽的参考（内容量过大）
特定于版本的
情境性的（仅针对特定任务）
索引良好的（易于搜索）

内容类型	本地	动态
核心概念 (3-5 个)	✅ 完整
Hello world 代码	✅ 完整
常见模式 (3-5 个)	✅ 完整
主要 API 方法	签名 + 示例	通过 fetch 获取完整文档
最佳实践	前 5 个要点	搜索更多
故障排除		搜索查询
完整 API 参考		文档链接

审查：本地内容是否足以应对常见任务？
测试：建议的搜索查询是否返回有用的结果？
验证：代码示例是否能无错误运行？

"{name} overview" → 目的，架构
"{name} getting started quickstart" → 设置步骤
"{name} API reference" → 核心类/方法
"{name} samples examples" → 代码模式
"{name} best practices performance" → 优化

"{service} overview features" → 功能
"{service} quickstart {language}" → 设置代码
"{service} REST API reference" → 端点
"{service} SDK {language}" → 客户端库
"{service} pricing limits quotas" → 限制

"{framework} architecture concepts" → 心智模型
"{framework} project structure" → 约定
"{framework} tutorial walkthrough" → 端到端流程
"{framework} configuration options" → 自定义

示例：创建 "Semantic Kernel" 技能

microsoft_docs_search(query="semantic kernel overview")
microsoft_docs_search(query="semantic kernel plugins functions")
microsoft_code_sample_search(query="semantic kernel", language="csharp")
microsoft_docs_fetch(url="https://learn.microsoft.com/semantic-kernel/overview/")

semantic-kernel/
├── SKILL.md
└── sample_codes/
    ├── getting-started/
    │   └── hello-kernel.cs
    └── common-patterns/
        ├── chat-completion.cs
        └── function-calling.cs

---
name: semantic-kernel
description: 使用 Microsoft Semantic Kernel 构建 AI 智能体。用于在 .NET 或 Python 中开发具有插件、规划器和记忆功能的 LLM 驱动应用。
---

# Semantic Kernel

用于通过插件、规划器和记忆将 LLM 集成到应用程序中的编排 SDK。

## 关键概念

- **Kernel** : 管理 AI 服务和插件的中央编排器
- **Plugins** : AI 可以调用的函数集合
- **Planner** : 编排插件函数以实现目标
- **Memory** : 用于 RAG 模式的向量存储集成

## 快速开始

参见 [getting-started/hello-kernel.cs](sample_codes/getting-started/hello-kernel.cs)

## 了解更多

| 主题 | 如何查找 |
|-------|-------------|
| 插件开发 | `microsoft_docs_search(query="semantic kernel plugins custom functions")` |
| 规划器 | `microsoft_docs_search(query="semantic kernel planner")` |
| 记忆 | `microsoft_docs_fetch(url="https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/agent-memory")` |

## CLI 替代方案

如果 Learn MCP 服务器不可用，请改用 `mslearn` CLI：

| MCP 工具 | CLI 命令 |
|----------|-------------|
| `microsoft_docs_search(query: "...")` | `mslearn search "..."` |
| `microsoft_code_sample_search(query: "...", language: "...")` | `mslearn code-search "..." --language ...` |
| `microsoft_docs_fetch(url: "...")` | `mslearn fetch "..."` |

使用 `npx @microsoft/learn-cli <command>` 直接运行，或使用 `npm install -g @microsoft/learn-cli` 全局安装。

2026 年 2 月 11 日

🇺🇸English

Microsoft Skill Creator

Create hybrid skills for Microsoft technologies that store essential knowledge locally while enabling dynamic Learn MCP lookups for deeper details.

About Skills

Skills are modular packages that extend agent capabilities with specialized knowledge and workflows. A skill transforms a general-purpose agent into a specialized one for a specific domain.

Skill Structure

skill-name/
├── SKILL.md (required)     # Frontmatter (name, description) + instructions
├── references/             # Documentation loaded into context as needed
├── sample_codes/           # Working code examples
└── assets/                 # Files used in output (templates, etc.)

Key Principles

Frontmatter is critical : name and description determine when the skill triggers—be clear and comprehensive
Concise is key : Only include what agents don't already know; context window is shared
No duplication : Information lives in SKILL.md OR reference files, not both

Learn MCP Tools

Tool	Purpose	When to Use
`microsoft_docs_search`	Search official docs	First pass discovery, finding topics
`microsoft_docs_fetch`	Get full page content	Deep dive into important pages
`microsoft_code_sample_search`	Find code examples	Get implementation patterns

CLI Alternative

If the Learn MCP server is not available, use the mslearn CLI from a terminal or shell (for example, Bash, PowerShell, or cmd) instead:

# Run directly (no install needed)
npx @microsoft/learn-cli search "semantic kernel overview"

# Or install globally, then run
npm install -g @microsoft/learn-cli
mslearn search "semantic kernel overview"

MCP Tool	CLI Command
`microsoft_docs_search(query: "...")`	`mslearn search "..."`
`microsoft_code_sample_search(query: "...", language: "...")`	`mslearn code-search "..." --language ...`
`microsoft_docs_fetch(url: "...")`	`mslearn fetch "..."`

Generated skills should include this same CLI fallback table so agents can use either path.

Creation Process

Step 1: Investigate the Topic

Build deep understanding using Learn MCP tools in three phases:

Phase 1 - Scope Discovery:

microsoft_docs_search(query="{technology} overview what is")
microsoft_docs_search(query="{technology} concepts architecture")
microsoft_docs_search(query="{technology} getting started tutorial")

Phase 2 - Core Content:

microsoft_docs_fetch(url="...")  # Fetch pages from Phase 1
microsoft_code_sample_search(query="{technology}", language="{lang}")

Phase 3 - Depth:

microsoft_docs_search(query="{technology} best practices")
microsoft_docs_search(query="{technology} troubleshooting errors")

Investigation Checklist

After investigating, verify:

Can explain what the technology does in one paragraph
Identified 3-5 key concepts
Have working code for basic usage
Know the most common API patterns
Have search queries for deeper topics

Step 2: Clarify with User

Present findings and ask:

"I found these key areas: [list]. Which are most important?"
"What tasks will agents primarily perform with this skill?"
"Which programming language should code samples prioritize?"

Step 3: Generate the Skill

Use the appropriate template from skill-templates.md:

Technology Type	Template
Client library, NuGet/npm package	SDK/Library
Azure resource	Azure Service
App development framework	Framework/Platform
REST API, protocol	API/Protocol

Generated Skill Structure

{skill-name}/
├── SKILL.md                    # Core knowledge + Learn MCP guidance
├── references/                 # Detailed local documentation (if needed)
└── sample_codes/               # Working code examples
    ├── getting-started/
    └── common-patterns/

Step 4: Balance Local vs Dynamic Content

Store locally when:

Foundational (needed for any task)
Frequently accessed
Stable (won't change)
Hard to find via search

Keep dynamic when:

Exhaustive reference (too large)
Version-specific
Situational (specific tasks only)
Well-indexed (easy to search)

Content Guidelines

Content Type	Local	Dynamic
Core concepts (3-5)	✅ Full
Hello world code	✅ Full
Common patterns (3-5)	✅ Full
Top API methods	Signature + example	Full docs via fetch
Best practices	Top 5 bullets	Search for more
Troubleshooting		Search queries
Full API reference		Doc links

Step 5: Validate

Review: Is local content sufficient for common tasks?
Test: Do suggested search queries return useful results?
Verify: Do code samples run without errors?

Common Investigation Patterns

For SDKs/Libraries

"{name} overview" → purpose, architecture
"{name} getting started quickstart" → setup steps
"{name} API reference" → core classes/methods
"{name} samples examples" → code patterns
"{name} best practices performance" → optimization

For Azure Services

"{service} overview features" → capabilities
"{service} quickstart {language}" → setup code
"{service} REST API reference" → endpoints
"{service} SDK {language}" → client library
"{service} pricing limits quotas" → constraints

For Frameworks/Platforms

"{framework} architecture concepts" → mental model
"{framework} project structure" → conventions
"{framework} tutorial walkthrough" → end-to-end flow
"{framework} configuration options" → customization

Example: Creating a "Semantic Kernel" Skill

Investigation

microsoft_docs_search(query="semantic kernel overview")
microsoft_docs_search(query="semantic kernel plugins functions")
microsoft_code_sample_search(query="semantic kernel", language="csharp")
microsoft_docs_fetch(url="https://learn.microsoft.com/semantic-kernel/overview/")

Generated Skill

semantic-kernel/
├── SKILL.md
└── sample_codes/
    ├── getting-started/
    │   └── hello-kernel.cs
    └── common-patterns/
        ├── chat-completion.cs
        └── function-calling.cs

Generated SKILL.md

---
name: semantic-kernel
description: Build AI agents with Microsoft Semantic Kernel. Use for LLM-powered apps with plugins, planners, and memory in .NET or Python.
---

# Semantic Kernel

Orchestration SDK for integrating LLMs into applications with plugins, planners, and memory.

## Key Concepts

- **Kernel**: Central orchestrator managing AI services and plugins
- **Plugins**: Collections of functions the AI can call
- **Planner**: Sequences plugin functions to achieve goals
- **Memory**: Vector store integration for RAG patterns

## Quick Start

See [getting-started/hello-kernel.cs](sample_codes/getting-started/hello-kernel.cs)

## Learn More

| Topic | How to Find |
|-------|-------------|
| Plugin development | `microsoft_docs_search(query="semantic kernel plugins custom functions")` |
| Planners | `microsoft_docs_search(query="semantic kernel planner")` |
| Memory | `microsoft_docs_fetch(url="https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/agent-memory")` |

## CLI Alternative

If the Learn MCP server is not available, use the `mslearn` CLI instead:

| MCP Tool | CLI Command |
|----------|-------------|
| `microsoft_docs_search(query: "...")` | `mslearn search "..."` |
| `microsoft_code_sample_search(query: "...", language: "...")` | `mslearn code-search "..." --language ...` |
| `microsoft_docs_fetch(url: "...")` | `mslearn fetch "..."` |

Run directly with `npx @microsoft/learn-cli <command>` or install globally with `npm install -g @microsoft/learn-cli`.

Weekly Installs

7.4K

Repository

github/awesome-copilot

GitHub Stars

26.7K

First Seen

Feb 11, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

Installed on

codex7.3K

gemini-cli7.3K

opencode7.3K

github-copilot7.3K

cursor7.3K

kimi-cli7.3K

Microsoft Skill Creator：为智能体创建混合技能，本地存储核心知识，动态查询Learn MCP

🇨🇳中文介绍

Microsoft Skill Creator

关于技能

技能结构

核心原则

Learn MCP 工具

相关 Skills

CLI 替代方案

创建流程

步骤 1：调研主题

调研检查清单

步骤 2：与用户澄清

步骤 3：生成技能

生成的技能结构

步骤 4：平衡本地与动态内容

内容指南

步骤 5：验证

常见调研模式

对于 SDK/库

对于 Azure 服务

对于框架/平台

示例：创建 "Semantic Kernel" 技能

调研

生成的技能

生成的 SKILL.md

🇺🇸English

Microsoft Skill Creator

About Skills

Skill Structure

Key Principles

Learn MCP Tools

CLI Alternative

Creation Process

Step 1: Investigate the Topic

Investigation Checklist

Step 2: Clarify with User

Step 3: Generate the Skill

Generated Skill Structure

Step 4: Balance Local vs Dynamic Content

Content Guidelines

Step 5: Validate

Common Investigation Patterns

For SDKs/Libraries

For Azure Services

For Frameworks/Platforms

Example: Creating a "Semantic Kernel" Skill

Investigation

Generated Skill

Generated SKILL.md