Back to Details

microsoft-skill-creator

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Microsoft Skill Creator

Microsoft Skill 创建器

Create hybrid skills for Microsoft technologies that store essential knowledge locally while enabling dynamic Learn MCP lookups for deeper details.
为Microsoft技术创建混合技能，这类技能会将核心知识存储在本地，同时支持通过动态调用Learn MCP来获取更详细的信息。

About Skills

关于Skill

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是模块化的软件包，可通过专业知识和工作流扩展Agent的能力。一项Skill能将通用Agent转变为特定领域的专用Agent。

Skill Structure

Skill 结构

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.)
skill-name/
├── SKILL.md (必填项)     # 前端元数据（名称、描述）+ 使用说明
├── references/             # 可按需加载到上下文的文档
├── sample_codes/           # 可运行的代码示例
└── assets/                 # 输出中用到的文件（模板等）

Key Principles

核心原则

  • 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
  • 前端元数据至关重要：
    name
    和
    description
    决定Skill何时触发——表述需清晰全面
  • 简洁为要：仅包含Agent原本不具备的知识；上下文窗口是共享资源
  • 避免重复：信息仅存在于SKILL.md或参考文件中，不可同时存在于两者

Learn MCP Tools

Learn MCP 工具

ToolPurposeWhen to Use
microsoft_docs_search
Search official docsFirst pass discovery, finding topics
microsoft_docs_fetch
Get full page contentDeep dive into important pages
microsoft_code_sample_search
Find code examplesGet implementation patterns
工具用途使用场景
microsoft_docs_search
搜索官方文档首次主题探索、查找相关话题
microsoft_docs_fetch
获取完整页面内容深入研究重要页面
microsoft_code_sample_search
查找代码示例获取实现模式

Creation Process

创建流程

Step 1: Investigate the Topic

步骤1：调研主题

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")
分三个阶段使用Learn MCP工具建立深度理解：
阶段1 - 范围探索：
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中的页面内容
microsoft_code_sample_search(query="{technology}", language="{lang}")
阶段3 - 深度拓展：
microsoft_docs_search(query="{technology} best practices")
microsoft_docs_search(query="{technology} troubleshooting errors")

Investigation Checklist

调研检查清单

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
调研完成后，需验证：
  • 能否用一段话解释该技术的作用
  • 已识别3-5个核心概念
  • 拥有基础用法的可运行代码
  • 了解最常见的API模式
  • 具备用于深度探索的搜索查询语句

Step 2: Clarify with User

步骤2：与用户确认

Present findings and ask:
  1. "I found these key areas: [list]. Which are most important?"
  2. "What tasks will agents primarily perform with this skill?"
  3. "Which programming language should code samples prioritize?"
展示调研结果并询问：
  1. "我发现了以下关键领域：[列表]。其中哪些是最重要的？"
  2. "Agent主要会使用该Skill执行哪些任务？"
  3. "代码示例应优先支持哪种编程语言？"

Step 3: Generate the Skill

步骤3：生成Skill

Use the appropriate template from skill-templates.md:
Technology TypeTemplate
Client library, NuGet/npm packageSDK/Library
Azure resourceAzure Service
App development frameworkFramework/Platform
REST API, protocolAPI/Protocol
从skill-templates.md中选择合适的模板：
技术类型模板
客户端类库、NuGet/npm包SDK/类库
Azure资源Azure服务
应用开发框架框架/平台
REST API、协议API/协议

Generated Skill Structure

生成的Skill结构

{skill-name}/
├── SKILL.md                    # Core knowledge + Learn MCP guidance
├── references/                 # Detailed local documentation (if needed)
└── sample_codes/               # Working code examples
    ├── getting-started/
    └── common-patterns/
{skill-name}/
├── SKILL.md                    # 核心知识 + Learn MCP 使用指南
├── references/                 # 详细本地文档（如有需要）
└── sample_codes/               # 可运行代码示例
    ├── getting-started/
    └── common-patterns/

Step 4: Balance Local vs Dynamic Content

步骤4：平衡本地与动态内容

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)
以下内容存储在本地：
  • 基础性内容（完成任何任务都需要）
  • 高频访问内容
  • 稳定内容（不会变更）
  • 难以通过搜索找到的内容
以下内容保持动态获取：
  • 详尽的参考内容（体积过大）
  • 特定版本内容
  • 场景化内容（仅适用于特定任务）
  • 索引完善的内容（易于搜索）

Content Guidelines

内容指南

Content TypeLocalDynamic
Core concepts (3-5)✅ Full
Hello world code✅ Full
Common patterns (3-5)✅ Full
Top API methodsSignature + exampleFull docs via fetch
Best practicesTop 5 bulletsSearch for more
TroubleshootingSearch queries
Full API referenceDoc links
内容类型本地存储动态获取
核心概念（3-5个）✅ 完整存储
Hello World代码✅ 完整存储
常见模式（3-5个）✅ 完整存储
热门API方法签名 + 示例通过fetch获取完整文档
最佳实践前5条要点搜索获取更多内容
故障排查搜索查询语句
完整API参考文档链接

Step 5: Validate

步骤5：验证

  1. Review: Is local content sufficient for common tasks?
  2. Test: Do suggested search queries return useful results?
  3. Verify: Do code samples run without errors?
  1. 审核：本地内容是否足以支持常见任务？
  2. 测试：建议的搜索查询能否返回有用结果？
  3. 验证：代码示例能否无错误运行？

Common Investigation Patterns

常见调研模式

For SDKs/Libraries

针对SDK/类库

"{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
"{name} overview" → 用途、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" → 优化方案

For Azure Services

针对Azure服务

"{service} overview features" → capabilities
"{service} quickstart {language}" → setup code
"{service} REST API reference" → endpoints
"{service} SDK {language}" → client library
"{service} pricing limits quotas" → constraints
"{service} overview features" → 功能特性
"{service} quickstart {language}" → 设置代码
"{service} REST API reference" → 端点
"{service} SDK {language}" → 客户端类库
"{service} pricing limits quotas" → 限制条件

For Frameworks/Platforms

针对框架/平台

"{framework} architecture concepts" → mental model
"{framework} project structure" → conventions
"{framework} tutorial walkthrough" → end-to-end flow
"{framework} configuration options" → customization
"{framework} architecture concepts" → 心智模型
"{framework} project structure" → 约定规范
"{framework} tutorial walkthrough" → 端到端流程
"{framework} configuration options" → 自定义配置

Example: Creating a "Semantic Kernel" Skill

示例：创建「Semantic Kernel」Skill

Investigation

调研过程

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/")
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

生成的Skill

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

Generated SKILL.md

生成的SKILL.md

markdown
---
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.
---
markdown
---
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

Semantic Kernel

Orchestration SDK for integrating LLMs into applications with plugins, planners, and memory.
用于将大语言模型集成到应用中的编排SDK，支持插件、规划器和记忆功能。

Key Concepts

核心概念

  • 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
  • Kernel：管理AI服务和插件的中央编排器
  • Plugins：AI可调用的函数集合
  • 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

Quick Start

快速开始

See getting-started/hello-kernel.cs
查看 getting-started/hello-kernel.cs

Learn More

了解更多

TopicHow 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")
undefined
主题获取方式
插件开发
microsoft_docs_search(query="semantic kernel plugins custom functions")
规划器
microsoft_docs_search(query="semantic kernel planner")
记忆功能
microsoft_docs_fetch(url="https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/agent-memory")
undefined