Claude Skills Built Me an AI Agent Army (They Run Everything Now)

章节 1：Claude 生态概览：Project、Sub-agents 与 Skills 的区别

📝 本节摘要：

在本节中，Amir 首先介绍了本期访谈的核心主题——Claude Skills（技能），并将其称为自“子智能体（Sub-agents）”以来最重要的更新。他详细梳理了 Claude 生态中三个关键概念的区别：Projects（项目）是包含自定义指令和共享知识库的协作空间，适合团队协作；Sub-agents（子智能体）主要用于代码环境，负责将复杂任务拆解分发；而 Skills（技能）则是针对特定任务的自动化工作流，用户可以像培训“初级员工”一样，为其设定严格的护栏和操作步骤，以实现高度可重复的精确输出。

[原文] [Greg Isenberg]: in this episode Amir takes us through how to use Claude skills to build digital employees We go through AB testing idea agent marketing insight agent and then we build one live together

[译文] [Greg Isenberg]: 在这一集中，Amir 将带领我们了解如何使用 Claude Skills（技能）来构建数字员工。我们会通过 A/B 测试创意智能体、营销洞察智能体，然后我们将现场一起构建一个智能体。

[原文] [Greg Isenberg]: You're going to learn about what cloud skills is why it's the biggest thing that happened since sub agents and how to actually build them yourself

[译文] [Greg Isenberg]: 你将了解到什么是 Claude Skills，为什么它是自子智能体（sub-agents）以来发生的最大事件，以及如何亲自构建它们。

[原文] [Greg Isenberg]: Amir what are we learning today

[译文] [Greg Isenberg]: Amir，我们今天要学什么？

[原文] [Amir]: Today we're going to talk about claude skills I'm going to tell you what they actually are how they're different from projects and sub agents and claude and why this matters and how you can actually apply for work

[译文] [Amir]: 今天我们要谈谈 Claude Skills。我会告诉你它们到底是什么，它们与 Projects（项目）和 Claude 中的子智能体有何不同，为什么这很重要，以及你如何将其实际应用到工作中。

[原文] [Greg Isenberg]: Okay And by the end of this episode are we are we going to be able to apply Claude skills

[译文] [Greg Isenberg]: 好的。那么在本集结束时，我们能学会应用 Claude Skills 吗？

[原文] [Amir]: 100% I'm going to show you first I want to talk about what it actually is and why it matters But I'll show you how to use existing skills in claude that they just came out with and how to create your own and how to apply for your work So whether you're in marketing in data analysis or any sort of document creation you can actually use skills to do that

[译文] [Amir]: 100% 可以。首先我要讲讲它到底是什么以及为什么它很重要，但我也会向你展示如何使用 Claude 刚刚推出的现有技能，如何创建你自己的技能，以及如何将其应用到你的工作中。所以，无论你是在从事市场营销、数据分析还是任何类型的文档创作，你实际上都可以使用 Skills 来完成。

[原文] [Greg Isenberg]: Cool Let's do it

[译文] [Greg Isenberg]: 酷，咱们开始吧。

[原文] [Amir]: Cool So first thing is I want to talk about cloud So not a lot of people are familiar with cloud projects and I want to talk about what that actually is and why it matters and how it's kind of related to skills

[译文] [Amir]: 酷。首先我想谈谈 Claude。并不是很多人熟悉 Claude Projects（项目），我想谈谈它到底是什么，为什么它很重要，以及它与 Skills 有什么关联。

[原文] [Amir]: So within Cloud AI specifically you can actually create projects and they're essentially workspaces with a set of custom instructions So this is a system prompt and it has relevant context memories and tools

[译文] [Amir]: 具体在 Claude AI 中，你实际上可以创建 Projects（项目），它们本质上是带有一组自定义指令的工作区。这就是一个系统提示词（system prompt），并且它拥有相关的上下文、记忆和工具。

[原文] [Amir]: So say for example you're part of a a broader marketing team and you want to create a project that will uh have a set of instructions to analyze marketing data for example or generate a newsletter and you want it to connect to specific tools um have relevant context and files

[译文] [Amir]: 举个例子，假设你是一个大型营销团队的一员，你想创建一个项目，其中包含一组指令来分析营销数据，或者生成一份简报，并且你希望它连接到特定的工具，拥有相关的上下文和文件。

[原文] [Amir]: So this could be a glossery of terms you use within your organization your brand guidelines depending on the task it is that you wanted to do and then also have memories generated from the chats that you have within that project So it's really great for collaboration with other team members

[译文] [Amir]: 这可能包括你们组织内部使用的术语表、品牌指南，具体取决于你想让它执行的任务，然后它还拥有在该项目中通过聊天生成的记忆。所以这对于与其他团队成员协作非常棒。

[原文] [Amir]: Now you can also use it yourself as well but really uh the ability for you to create repeatable tasks and do you know certain set of instructions with external tools and data So if I'm in a marketing team this is something that I want to look at and essentially within cloud share with my team members and create projects around it

[译文] [Amir]: 当然你也可以自己使用它，但真正的核心在于让你能够创建可重复的任务，并使用外部工具和数据执行特定的指令集。所以如果我在一个营销团队，这就是我会关注的东西，本质上是在 Claude 内部与我的团队成员共享，并围绕它创建项目。

[原文] [Amir]: All right So the only thing with projects I would say that it's important to one work with your team members to actually refine the system instructions and then always have relevant context files As your business changes the data changes you need to update it and you have to go back and constantly update these context files Um and I'll talk about why context is important in this specific session and kind of how it ranks up against skills

[译文] [Amir]: 好的。关于 Projects，我只想说重要的一点是，首先要与团队成员合作去真正完善系统指令，然后始终保持相关的上下文文件。随着业务变化、数据变化，你需要更新它，你必须回头不断更新这些上下文文件。我会详细谈谈为什么上下文在这个特定环节很重要，以及它与 Skills 相比如何。

[原文] [Amir]: Now the next part of it is sub agents With sub aents this is more relevant in cloud code specifically And I actually use uh sub aents in cloud code to spin up multiple agents And multiple agents are really great at breaking down complex multiworkflow tasks into individual tasks with specialized agents

[译文] [Amir]: 接下来的一部分是 Sub-agents（子智能体）。关于子智能体，这在 Claude Code（代码环境）中更为相关。实际上我在 Claude Code 中使用子智能体来启动多个智能体。多个智能体非常擅长将复杂的多工作流任务分解为由专门智能体处理的单个任务。

[原文] [Amir]: So what does that mean Say for example you're building a very complex feature and you want to delegate the front end to one agent and the back end to another So within the chat you can actually spin up these agents to say "Hey Claude create an agent that will work on the front end using this set of rules and then create another agent to spin up to do the back end for it."

[译文] [Amir]: 这意味着什么呢？举个例子，假设你正在构建一个非常复杂的功能，你想把前端委托给一个智能体，后端委托给另一个。所以在聊天中，你实际上可以启动这些智能体，说：“嘿 Claude，创建一个使用这套规则处理前端的智能体，然后再启动另一个智能体来为它处理后端。”

[原文] [Amir]: And what's interesting is the context is isolated to that conversation window Um and so whatever context is provided or gathered in that conversation is actually um used as an input but those agents have a set of system instructions as well

[译文] [Amir]: 有趣的是，上下文被隔离在那个对话窗口中。因此，在该对话中提供或收集的任何上下文实际上都被用作输入，但这些智能体同时也拥有一套系统指令。

[原文] [Amir]: Now where things get interesting is skills And I want to talk about kind of why this actually matters Um skills are automated workflows and tasks that you can apply globally at a project or individual level

[译文] [Amir]: 现在有趣的地方来了，那就是 Skills（技能）。我想谈谈为什么这真的很重要。Skills 是自动化的工作流和任务，你可以在项目层面或个人层面全局应用它们。

[原文] [Amir]: So whether you're an existing project you have a set of system instructions you can use skills which is an add-on or augmented skill set um within that project or individual chat and it can do a set of set of tasks create documents create PDFs analyze documents um it can actually help build MCPS for you You can use skills to create other skills or create you know visual art as well

[译文] [Amir]: 所以无论你是在现有的项目中，拥有一套系统指令，你都可以使用 Skills，这是一种附加组件或增强技能集，可以在该项目或个人聊天中使用。它可以执行一系列任务：创建文档、创建 PDF、分析文档，它甚至可以帮你构建 MCPs（模型上下文协议）。你可以用 Skills 来创建其他 Skills，或者创作视觉艺术。

[原文] [Amir]: Now when do you actually use this It's for very specialized tasks based on the constraints and guidelines and steps built by you the expert

[译文] [Amir]: 那么你究竟什么时候使用它呢？它是用于非常专门的任务，基于作为专家的你所构建的约束、准则和步骤。

[原文] [Amir]: I think uh it was Kaparthi um a couple days ago he had an excellent analogy where it's like AI is essentially your coworker or someone that like reports to you You want to train it You want to build the guidelines You know this is not verbatim but like basically what he was trying to say was yeah it's someone that you work with and you can kind of build the limit the constraints around it and guidelines on how you want it to respond to you

[译文] [Amir]: 我记得几天前 Karpathy（注：Andrej Karpathy）有一个极好的比喻，大意是 AI 本质上是你的同事或者向你汇报的人。你要训练它，你要建立准则。这不是原话，但他基本上想表达的是，是的，它是和你一起工作的人，你可以围绕它建立限制、约束，以及关于你希望它如何回应你的准则。

[原文] [Amir]: And this is kind of similar in some nature uh you can create for example let's say you are a paid media expert and you run campaigns for your clients and you want a very detailed analysis on your visit to booked appointments and what the conversion rates look like and how that attributes to the different channels you have and what's performing better than the other in terms of campaigns

[译文] [Amir]: 这在某种本质上是相似的。比如说，假设你是一名付费媒体专家，你为客户运营广告活动，你想要一份非常详细的分析，关于从访问到预约的转化情况，转化率是多少，以及这如何归因于你拥有的不同渠道，以及在广告活动方面哪个表现得更好。

[原文] [Amir]: You can create a scale that can follow a set of custom instructions but also scripts that you can build out yourself to analyze that data And I want to circle back later on why that actually is important

[译文] [Amir]: 你可以创建一个 Skill，它可以遵循一套自定义指令，同时也遵循你自己构建的脚本来分析这些数据。我想稍后再回过头来谈谈为什么这真的很重要。

[原文] [Amir]: Um but what's also interesting is that it actually only loads context when it's relevant to the task So when a project often times you have the LLM that's determining which context to retrieve and add into the conversation window and reference it Um but in this instance it's only con based on the judgment of the task whether or not it should pull relevant context and it's just relevant to exactly what you want to get done

[译文] [Amir]: 但另一个有趣的点是，它实际上只有在与任务相关时才加载上下文。在 Project（项目）中，通常是由大语言模型（LLM）决定检索哪些上下文并将其添加到对话窗口中进行引用。但在这种情况下（使用 Skills），它是基于对任务的判断来决定是否应该提取相关上下文，且仅与你想要完成的具体事项相关。