Skills

explained:

How

Skills

compares

to

prompts,

Projects,

MCP,

and

subagents

Since introducing Skills, there's been interest in understanding how the various components of Claude's agentic ecosystem work together. 自从引入技能以来，人们一直有兴趣了解Claude代理生态系统中的各个组件如何协同工作。

Whether you're building sophisticated workflows in Claude Code, creating enterprise solutions with the API, or maximizing your productivity on Claude.ai, knowing which tool to reach for—and when—can transform how you work with Claude.无论你是在Claude Code中构建复杂的工作流程，使用API创建企业解决方案，还是在Claude.ai上最大化你的生产力，知道何时使用哪种工具——以及如何使用——可以改变你与Claude合作的方式。

This guide breaks down each building block, explains when to use what, and shows you how to combine them for powerful agentic workflows.本指南分解了每个构建模块，解释了何时使用什么，并向你展示了如何将它们组合起来用于强大的代理工作流程。

Understanding your agentic building blocks了解你的代理构建模块

What are Skills?什么是技能？

Skills are folders containing instructions, scripts, and resources that Claude discovers and loads dynamically when relevant to a task. Think of them as specialized training manuals that give Claude expertise in specific domains—from working with Excel spreadsheets to following your organization's brand guidelines.技能是包含指令、脚本和资源的文件夹，当与任务相关时，Claude会动态发现并加载它们。可以把它们想象成专门的培训手册，让Claude在特定领域拥有专业知识——从处理Excel电子表格到遵循你组织的品牌指南。

How Skills work: When Claude encounters a task, it scans available Skills to find relevant matches. Skills use progressive disclosure: metadata loads first (~100 tokens), providing just enough information for Claude to know when a Skill is relevant. Full instructions load when needed (<5k tokens), and bundled files or scripts load only as required.技能如何工作：当Claude遇到一个任务时，它会扫描可用的技能以找到相关的匹配项。技能使用渐进式披露：首先加载元数据（约100个token），提供足够的信息让Claude知道技能何时相关。需要时加载完整指令（<5k个token），捆绑的文件或脚本仅在需要时加载。

When to use Skills: Choose Skills when you need Claude to perform specialized tasks consistently and efficiently. They're ideal for:何时使用技能：当你需要Claude一致且高效地执行专门任务时，选择技能。它们非常适合：

• Organizational workflows: Brand guidelines, compliance procedures, document templates组织工作流程：品牌指南、合规程序、文档模板
• Domain expertise: Excel formulas, PDF manipulation, data analysis领域专业知识：Excel公式、PDF操作、数据分析
• Personal preferences: Note-taking systems, coding patterns, research methods个人偏好：笔记系统、编码模式、研究方法

Example: Create a brand guidelines Skill that includes your company's color palette, typography rules, and layout specifications. When Claude creates presentations or documents, it automatically applies these standards without you needing to explain them each time.示例：创建一个品牌指南技能，包括你公司的调色板、排版规则和布局规范。当Claude创建演示文稿或文档时，它会自动应用这些标准，而无需你每次都解释它们。

Learn more about Skills and check out our growing Skills library.了解更多关于技能的信息，并查看我们不断增长的技能库。

What are prompts?什么是提示？

Prompts are the instructions you provide to Claude in natural language during a conversation. They're ephemeral, conversational, and reactive—you provide context and direction in the moment.提示是你在对话中以自然语言提供给Claude的指令。它们是短暂的、对话式的和反应式的——你在当下提供上下文和方向。

When to use prompts: Use prompts for:何时使用提示：在以下情况下使用提示：

• One-off requests: "Summarize this article"一次性请求：“总结这篇文章”
• Conversational refinement: "Make that tone more professional"对话式优化：“让语气更专业”
• Immediate context: "Analyze this data and identify trends"即时上下文：“分析这些数据并识别趋势”
• Ad-hoc instructions: "Format this as a bulleted list"临时指令：“将其格式化为项目符号列表”

Example: 示例：

Please conduct a comprehensive security review of this code. I'm looking for:请对此代码进行全面的安全审查。我正在寻找：

1. Common vulnerabilities including:1. 常见漏洞，包括：

• Injection flaws (SQL, command, XSS, etc.)注入缺陷（SQL、命令、XSS等）
• Authentication and authorization issues身份验证和授权问题
• Sensitive data exposure敏感数据暴露
• Security misconfigurations安全配置错误
• Broken access control访问控制失效
• Cryptographic failures加密失败
• Input validation problems输入验证问题
• Error handling and logging issues错误处理和日志记录问题

2. For each issue you find, please provide:2. 对于你发现的每个问题，请提供：

• Severity level (Critical/High/Medium/Low)严重级别（严重/高/中/低）
• Location in the code (line numbers or function names)代码中的位置（行号或函数名）
• Explanation of why it's a security risk and how it could be exploited解释为什么这是一个安全风险以及如何被利用
• Specific fix recommendation with code examples where possible具体的修复建议，尽可能附带代码示例
• Best practice guidance to prevent similar issues防止类似问题的最佳实践指南

3. Code context: [Describe what the code does, the language/framework, and the environment it runs in - e.g., "This is a Node.js REST API that handles user authentication and processes payment data"]3. 代码上下文：[描述代码的功能、语言/框架以及运行环境——例如，“这是一个处理用户身份验证和处理支付数据的Node.js REST API”]

4. Additional considerations:4. 其他考虑因素：

• Are there any OWASP Top 10 vulnerabilities present?是否存在任何OWASP Top 10漏洞？
• Does the code follow security best practices for [specific framework/language]?代码是否遵循[特定框架/语言]的安全最佳实践？
• Are there any dependencies with known vulnerabilities?是否存在已知漏洞的依赖项？

Please prioritize findings by severity and potential impact.请按严重性和潜在影响对发现结果进行优先级排序。

Pro-tip: Prompts are your primary way of interacting with Claude, but they don't persist across conversations. For repeated workflows or specialized knowledge, consider capturing prompts as Skills or project instructions.专业提示：提示是你与Claude交互的主要方式，但它们不会跨对话持久保存。对于重复的工作流程或专门知识，考虑将提示捕获为技能或项目指令。

When to use a Skill instead: If you find yourself typing the same prompt repeatedly across multiple conversations, it's time to create a Skill. Transform recurring instructions like "review this code for security vulnerabilities using OWASP standards" or "format this analysis with executive summary, key findings, and recommendations" into Skills. This saves you from re-explaining procedures each time and ensures consistent execution.何时使用技能代替：如果你发现自己多次在多个对话中键入相同的提示，那么是时候创建一个技能了。将重复的指令（如“使用OWASP标准审查此代码的安全漏洞”或“将此分析格式化为包含执行摘要、关键发现和建议”）转化为技能。这可以节省你每次重新解释程序的时间，并确保一致的执行。

Check out our prompt library, prompting best practices, or our smart prompt maker to get started.查看我们的提示库、提示最佳实践或我们的智能提示生成器以开始使用。

What are Projects?什么是项目？

Available on all paid Claude plans, Projects are self-contained workspaces with their own chat histories and knowledge bases. Each project includes a 200K context window where you can upload documents, provide context, and set custom instructions that apply to all conversations within that project.在所有付费Claude计划中可用，项目是自包含的工作区，拥有自己的聊天历史记录和知识库。每个项目包括一个200K的上下文窗口，你可以在其中上传文档、提供上下文，并设置适用于该项目内所有对话的自定义指令。

How Projects work: Everything you upload to a project's knowledge base becomes available across all chats within that project. Claude automatically uses this context to provide more informed, relevant responses. When your project knowledge approaches context limits, Claude seamlessly enables Retrieval Augmented Generation (RAG) mode to expand capacity by up to 10x.项目如何工作：你上传到项目知识库的所有内容在该项目的所有聊天中都可用。Claude自动使用此上下文来提供更明智、更相关的响应。当你的项目知识接近上下文限制时，Claude无缝启用检索增强生成（RAG）模式，将容量扩展多达10倍。

When to use Projects: Choose Projects when you need:何时使用项目：当你需要以下内容时选择项目：

• Persistent context: Background knowledge that should inform every conversation持久上下文：应告知每个对话的背景知识
• Workspace organization: Separate contexts for different initiatives工作区组织：不同项目的独立上下文
• Team collaboration: Shared knowledge and conversation history (on Team and Enterprise plans)团队协作：共享知识和对话历史（团队和企业计划）
• Custom instructions: Project-specific tone, perspective, or approach自定义指令：项目特定的语气、视角或方法

Example: Create a "Q4 Product Launch" project containing market research, competitor analysis, and product specifications. Every chat in this project has access to this knowledge without you needing to re-upload or re-explain the context.示例：创建一个“Q4产品发布”项目，包含市场研究、竞争对手分析和产品规格。该项目中的每个聊天都可以访问这些知识，而无需你重新上传或重新解释上下文。

When to use a Skill instead: Projects give Claude persistent context for a specific body of work—your company's codebase, a research initiative, an ongoing client engagement. Skills teach Claude how to do something. A Project might contain all the background on your product launch, while a skill could teach Claude your team's writing standards or code review process. If you find yourself copying the same instructions across multiple Projects, that's a signal to create a skill instead.何时使用技能代替：项目为Claude提供特定工作体的持久上下文——你公司的代码库、研究计划、持续的客户参与。技能教Claude如何做某事。一个项目可能包含你产品发布的所有背景，而技能可以教Claude你团队的写作标准或代码审查流程。如果你发现自己将相同的指令复制到多个项目中，那就是创建技能的信号。

Learn more about Projects.了解更多关于项目的信息。

What are subagents?什么是子代理？

Subagents are specialized AI assistants with their own context windows, custom system prompts, and specific tool permissions. Available in Claude Code and the Claude Agent SDK, subagents handle discrete tasks independently and return results to the main agent.子代理是专门的AI助手，拥有自己的上下文窗口、自定义系统提示和特定的工具权限。在Claude Code和Claude Agent SDK中可用，子代理独立处理离散任务并将结果返回给主代理。

How subagents work: Each subagent operates with its own configuration—you define what it does, how it approaches problems, and which tools it can access. Claude automatically delegates tasks to appropriate subagents based on their descriptions, or you can explicitly request a specific subagent.子代理如何工作：每个子代理都有自己的配置——你定义它做什么、如何解决问题以及它可以访问哪些工具。Claude根据子代理的描述自动将任务委派给适当的子代理，或者你可以显式请求特定的子代理。

When to use subagents: Use subagents for:何时使用子代理：在以下情况下使用子代理：

• Task specialization: Code review, test generation, security audits任务专业化：代码审查、测试生成、安全审计
• Context management: Keep the main conversation focused while offloading specialized work上下文管理：保持主对话的专注，同时将专门工作外包
• Parallel processing: Multiple subagents can work on different aspects simultaneously并行处理：多个子代理可以同时处理不同方面
• Tool restriction: Limit specific subagents to safe operations (e.g., read-only access)工具限制：将特定子代理限制为安全操作（例如，只读访问）

Example:

Create a code-reviewer subagent with access to Read, Grep, and Glob tools but not Write or Edit. When you modify code, Claude automatically delegates to this subagent for quality and security review without risking unintended code changes.

When to use a Skill instead: If multiple agents or conversations need the same expertise—like security review procedures or data analysis methods—create a Skill rather than building that knowledge into individual subagents. Skills are portable and reusable, while subagents are purpose-built for specific workflows. Use Skills to teach expertise that any agent can apply; use subagents when you need independent task execution with specific tool permissions and context isolation.何时使用技能代替：如果多个代理或对话需要相同的专业知识——如安全审查程序或数据分析方法——创建技能，而不是将该知识构建到单个子代理中。技能是可移植和可重用的，而子代理是为特定工作流程专门构建的。使用技能来教授任何代理都可以应用的专业知识；当你需要具有特定工具权限和上下文隔离的独立任务执行时，使用子代理。

Learn more about subagents.了解更多关于子代理的信息。

What is MCP?什么是MCP？

The Model Context Protocol (MCP) is an open standard for connecting AI assistants to external systems where data lives—content repositories, business tools, databases, and development environments.模型上下文协议（MCP）是一个开放标准，用于将AI助手连接到数据所在的外部系统——内容存储库、业务工具、数据库和开发环境。

How MCP works: MCP provides a standardized way to connect Claude to your tools and data sources. Instead of building custom integrations for each data source, you build against a single protocol. MCP servers expose data and capabilities; MCP clients (like Claude) connect to these servers.MCP如何工作：MCP提供了一种标准化的方式，将Claude连接到你的工具和数据源。无需为每个数据源构建自定义集成，你只需针对单个协议进行构建。MCP服务器暴露数据和能力；MCP客户端（如Claude）连接到这些服务器。

When to use MCP: Choose MCP when you need Claude to:何时使用MCP：当你需要Claude执行以下操作时选择MCP：

• Access external data: Google Drive, Slack, GitHub, databases访问外部数据：Google Drive、Slack、GitHub、数据库
• Use business tools: CRM systems, project management platforms使用业务工具：CRM系统、项目管理平台
• Connect to development environments: Local files, IDEs, version control连接到开发环境：本地文件、IDE、版本控制
• Integrate with custom systems: Your proprietary tools and data sources集成自定义系统：你的专有工具和数据源

Example: Connect Claude to your company's Google Drive via MCP. Now Claude can search documents, read files, and reference internal knowledge without manual uploads—the connection persists and updates automatically.示例：通过MCP将Claude连接到你公司的Google Drive。现在Claude可以搜索文档、读取文件并引用内部知识，无需手动上传——连接持久存在并自动更新。

When to use a Skill instead: MCP connects Claude to data; Skills teach Claude what to do with that data. If you're explaining how to use a tool or follow procedures—like "when querying our database, always filter by date range first" or "format Excel reports with these specific formulas"—that's a Skill. If you need Claude to access the database or Excel files in the first place, that's MCP. Use both together: MCP for connectivity, Skills for procedural knowledge.何时使用技能代替：MCP将Claude连接到数据；技能教Claude如何处理这些数据。如果你在解释如何使用工具或遵循程序——比如“查询我们的数据库时，始终先按日期范围过滤”或“使用这些特定公式格式化Excel报告”——那就是技能。如果你需要Claude首先访问数据库或Excel文件，那就是MCP。两者一起使用：MCP用于连接，技能用于程序知识。

Learn more about MCP and check out documentation on how to build an MCP server.了解更多关于MCP的信息，并查看如何构建MCP服务器的文档。

How they work together它们如何协同工作

The real power emerges when you combine these building blocks. Each serves a distinct purpose, and together they create sophisticated agentic workflows.真正的力量在于将这些构建模块组合起来。每个都有不同的用途，它们一起创建了复杂的代理工作流程。

Comparison: choosing the right tool比较：选择正确的工具

Example agentic workflow: research agent示例代理工作流程：研究代理

Let's build a comprehensive research agent that combines multiple building blocks. This example shows how to assemble and activate an agent for competitive analysis.让我们构建一个结合多个构建模块的全面研究代理。此示例展示了如何组装和激活一个用于竞争分析的代理。

Step 1: Set up your Project步骤1：设置你的项目

Create a "Competitive Intelligence" project and upload:创建一个“竞争情报”项目并上传：

• Industry reports and market analyses行业报告和市场分析
• Competitor product documentation竞争对手产品文档
• Customer feedback from your CRM来自CRM的客户反馈
• Previous research summaries以前的研究摘要

Add project instructions:添加项目指令：

Analyze competitors through the lens of our product strategy. Focus on differentiation opportunities and emerging market trends. Present findings with specific evidence and actionable recommendations.通过我们的产品战略视角分析竞争对手。关注差异化机会和新兴市场趋势。用具体证据和可操作的建议呈现发现。

Step 2: Connect data sources via MCP步骤2：通过MCP连接数据源

Enable MCP servers for:为以下内容启用MCP服务器：

• Google Drive (to access shared research documents)Google Drive（访问共享的研究文档）
• GitHub (to review competitor open-source repositories)GitHub（审查竞争对手的开源存储库）
• Web search (for real-time market information)网络搜索（获取实时市场信息）

Step 3: Create specialized Skills步骤3：创建专门的技能

Create a "competitive-analysis" skill:创建一个“竞争分析”技能：

# My Company GDrive Navigation Skill

## Overview
Optimized search and retrieval strategy for Meridian Tech's Google Drive structure. Use this skill to efficiently locate internal documents, research, and strategic materials.

## Drive Organization

**Top-level structure:**
- `/Strategy & Planning/` - OKRs, quarterly plans, board decks
- `/Product/` - PRDs, roadmaps, technical specs
- `/Research/` - Market research, competitive intel, user studies
- `/Sales & Marketing/` - Case studies, pitch decks, campaign materials
- `/Customer Success/` - Implementation guides, success metrics
- `/Company Ops/` - Policies, org charts, team directories

**Naming conventions:**
- Format: `YYYY-MM-DD_DocumentName_vX`
- Final versions marked with `_FINAL`
- Drafts include `_DRAFT` or `_WIP`

## Search Best Practices

1. **Start broad, then filter** - Use folder context + keywords
2. **Target document owners** - Sales materials from Sales/, not root
3. **Check recency** - Prioritize documents from last 6 months for current strategy
4. **Look for "source of truth"** - Files with `_FINAL`, `_APPROVED`, or in `/Archives/Official/`

## Research Agent Workflow

1. Identify topic category (product, market, customer)
2. Search relevant folder with targeted keywords
3. Retrieve 3-5 most recent/relevant documents
4. Cross-reference with `/Strategy & Planning/` for context
5. Cite sources with file names and dates

Step 4: Configure subagents (Claude Code/SDK only)步骤4：配置子代理（仅限Claude Code/SDK）

Create specialized subagents:创建专门的子代理：

market-researcher subagent:市场研究员子代理：

name: market-researcher
description: Research market trends, industry reports, and competitive landscape data. Use proactively for competitive analysis.
tools: Read, Grep, Web-search
---
You are a market research analyst specializing in competitive intelligence.

When researching:
1. Identify authoritative sources (Gartner, Forrester, industry reports)
2. Gather quantitative data (market share, growth rates, funding)
3. Analyze qualitative insights (analyst opinions, customer reviews)
4. Synthesize trends and patterns

Present findings with citations and confidence levels.

technical-analyst subagent:技术分析师子代理：

name: technical-analyst
description: Analyze technical architecture, implementation approaches, and engineering decisions. Use for technical competitive analysis.
tools: Read, Bash, Grep
---
You are a technical architect analyzing competitor technology choices.

When analyzing:
1. Review public repositories and technical documentation
2. Assess architecture patterns and technology stack
3. Evaluate scalability and performance approaches
4. Identify technical strengths and limitations

Focus on actionable technical insights that inform our product decisions.

Step 5: Activate your research agent步骤5：激活你的研究代理

Now when you ask Claude: "Analyze how our top three competitors are positioning their new AI features and identify gaps we can exploit"现在当你问Claude：“分析我们的三大竞争对手如何定位他们的新AI功能，并找出我们可以利用的差距”

Here's what happens:以下是发生的情况：

1. Project context loads: Claude accesses your uploaded research documents and follows project instructions项目上下文加载：Claude访问你上传的研究文档并遵循项目指令
2. MCP connections activate: Claude searches your Google Drive for recent competitor briefs and pulls GitHub dataMCP连接激活：Claude搜索你的Google Drive以获取最近的竞争对手简报，并拉取GitHub数据
3. Skills engage: The competitive-analysis Skill provides the analytical framework技能参与：竞争分析技能提供分析框架
4. Subagents execute (in Claude Code): The market-researcher gathers industry data while the technical-analyst reviews technical implementations子代理执行（在Claude Code中）：市场研究员收集行业数据，而技术分析师审查技术实现
5. Prompts refine: You provide conversational guidance: "Focus especially on enterprise customers in healthcare"提示优化：你提供对话式指导：“特别关注医疗保健领域的企业客户”

The result: A comprehensive competitive analysis that draws from multiple data sources, follows your analytical framework, leverages specialized expertise, and maintains context throughout your research project.结果：一份全面的竞争分析，从多个数据源提取，遵循你的分析框架，利用专业知识，并在整个研究项目中保持上下文。

Common questions常见问题

How do Skills work?技能如何工作？

Skills use progressive disclosure to keep Claude efficient. When working on tasks, Claude first scans Skill metadata (descriptions and summaries) to identify relevant matches. If a Skill matches, Claude loads the full instructions. Finally, if the Skill includes executable code or reference files, those load only when needed.技能使用渐进式披露来保持Claude的效率。在处理任务时，Claude首先扫描技能元数据（描述和摘要）以识别相关匹配。如果技能匹配，Claude加载完整指令。最后，如果技能包含可执行代码或参考文件，这些仅在需要时加载。

This architecture means you can have many Skills available without overwhelming Claude's context window. Claude accesses exactly what it needs, when it needs it.这种架构意味着你可以拥有许多可用的技能，而不会压倒Claude的上下文窗口。Claude在需要时精确访问所需内容。

Skills vs. subagents: when to use what技能与子代理：何时使用什么

Use Skills when: You want capabilities that any Claude instance can load and use. Skills are like training materials—they make Claude better at specific tasks across all conversations.在以下情况下使用技能：你希望任何Claude实例都可以加载和使用的能力。技能就像培训材料——它们使Claude在所有对话中更好地完成特定任务。

Use subagents when: You need complete, self-contained agents designed for specific purposes that handle workflows independently. Subagents are like specialized employees with their own context and tool permissions.在以下情况下使用子代理：你需要为特定目的设计的完整、自包含的代理，它们独立处理工作流程。子代理就像拥有自己的上下文和工具权限的专门员工。

Use them together when: You want subagents with specialized expertise. For example, a code-review subagent can use Skills for language-specific best practices, combining the independence of a subagent with the portable expertise of Skills.一起使用它们：当你希望子代理拥有专门知识时。例如，一个代码审查子代理可以使用技能来获取特定语言的最佳实践，结合了子代理的独立性和技能的可移植专业知识。

Skills vs. prompts: when to use what技能与提示：何时使用什么

Use prompts when: You're giving one-time instructions, providing immediate context, or having a conversational back-and-forth. Prompts are reactive and ephemeral.在以下情况下使用提示：你给出一次性指令、提供即时上下文或进行对话式来回交流。提示是反应性的和短暂的。

Use Skills when: You have procedures or expertise that you'll need repeatedly. Skills are proactive—Claude knows when to apply them—and persistent across conversations.在以下情况下使用技能：你有需要重复使用的程序或专业知识。技能是主动的——Claude知道何时应用它们——并且跨对话持久存在。

Use them together: Prompts and Skills complement each other naturally. Use Skills to provide foundational expertise, then use prompts to provide specific context and refinement for each task.一起使用它们：提示和技能自然互补。使用技能提供基础知识，然后使用提示为每个任务提供特定上下文和优化。

Skills vs. Projects: when to use what技能与项目：何时使用什么

Use Projects when: You need background knowledge and context that should inform all conversations about a specific initiative. Projects provide static reference material that's always loaded.在以下情况下使用项目：你需要背景知识和上下文，这些应告知关于特定计划的所有对话。项目提供始终加载的静态参考材料。

Use Skills when: You need procedural knowledge and executable code that activates only when relevant. Skills provide dynamic expertise that loads on-demand, saving your context window.在以下情况下使用技能：你需要仅在相关时激活的程序知识和可执行代码。技能提供按需加载的动态专业知识，节省你的上下文窗口。

Use them together when: You want both persistent context and specialized capabilities. For example, a "Product Development" project containing product specs and user research, combined with Skills for creating technical documentation and analyzing user feedback data.一起使用它们：当你同时需要持久上下文和专门能力时。例如，一个包含产品规格和用户研究的“产品开发”项目，结合用于创建技术文档和分析用户反馈数据的技能。

Key difference: Projects say "here's what you need to know." Skills say "here's how to do things." Projects provide a knowledge base you work within. Skills provide capabilities that work everywhere—any conversation, any project.关键区别：项目说“这是你需要知道的。”技能说“这是做事的方法。”项目提供你工作的知识库。技能提供在任何地方都能工作的能力——任何对话、任何项目。

Can subagents use Skills?子代理可以使用技能吗？

Yes. In Claude Code and the Agent SDK, subagents can access and use Skills just like the main agent. This creates powerful combinations where specialized subagents leverage portable expertise.是的。在Claude Code和Agent SDK中，子代理可以像主代理一样访问和使用技能。这创建了强大的组合，专门的子代理利用可移植的专业知识。

For example, your python-developer subagent can use the pandas-analysis Skill to perform data transformations following your team's conventions, while your documentation-writer subagent uses the technical-writing skill to format API documentation consistently.例如，你的python开发人员子代理可以使用pandas分析技能来按照你团队的约定执行数据转换，而你的文档编写子代理使用技术写作技能来一致地格式化API文档。

Getting started开始使用

Ready to build with Skills? Here's how to start:准备好使用技能构建了吗？以下是如何开始：

Claude.ai users:Claude.ai用户：

• Enable Skills in Settings → Features在设置→功能中启用技能
• Create your first project at claude.ai/projects在claude.ai/projects创建你的第一个项目
• Try combining project knowledge with Skills for your next analysis task尝试将项目知识与技能结合用于你的下一个分析任务

API developers:API开发者：

• Explore the Skills endpoint in documentation在文档中探索技能端点
• Check out our skills cookbook查看我们的技能食谱

Claude Code users:Claude Code用户：

• Install Skills via plugin marketplaces通过插件市场安装技能
• Check out our skills cookbook