章节 1：从构建智能体到“代码即万物”的范式转变

📝 本节摘要：

本章作为开场，演讲者Barry首先回顾了上次演讲以来行业的快速变化，指出现有的智能体（Agents）虽然具备智力，但往往缺乏实际工作所需的专业技能（Expertise）。他引出了Anthropic的新战略重心：停止构建针对特定领域的独立智能体，转而在“代码即万物”（Code is all we need）的理念下，打造一种模型与运行时环境紧密结合的通用架构。他论证了代码不仅仅是一个用例，而是通往数字世界的通用接口，这使得智能体的底层架构可以变得极度精简和可扩展。

[原文] [Barry]: all right good morning and thank you for having us again last time we were here we're still figuring out what an agent even is

[译文] [Barry]: 好了，大家早上好，感谢再次邀请我们。上次我们来这里的时候，我们还在摸索到底什么是智能体（Agent）。

[原文] [Barry]: today many of us are using agents on a daily basis but we still notice gaps we still have slots right agents have intelligence and capabilities but not always expertise that we need for real work

[译文] [Barry]: 如今，我们许多人每天都在使用智能体，但我们仍然注意到了差距，仍然存在一些空缺，对吧？智能体拥有智力和能力，但并不总是具备我们实际工作所需的专业技能（Expertise）。

[原文] [Barry]: i'm Barry this is Mahes we created agent skills in this talk we'll show you why we stopped building agents and started building skills instead

[译文] [Barry]: 我是Barry，这位是Mahesh，我们开发了“智能体技能”（Agent Skills）。在本次演讲中，我们将向大家展示为什么我们停止构建智能体，转而开始构建技能。

[原文] [Barry]: a lot of things have changed since our last talk mcp became the standard for agent connectivity cloud Code our first coding agent launched to the world and our cloud agent SDK now provides a production ready agent out of the box

[译文] [Barry]: 自上次演讲以来，很多事情都发生了变化。MCP（模型上下文协议）成为了智能体连接的标准；Claude Code——我们的第一个编程智能体——面向全球发布了；而且我们的Claude Agent SDK现在提供了一个开箱即用的、生产就绪的智能体。

[原文] [Barry]: we have a more mature ecosystem and we're moving towards a new paradigm for agents that paradigm is a tighter coupling between the model and a runtime environment put simply we think code is all we need

[译文] [Barry]: 我们拥有了一个更成熟的生态系统，并且我们正在迈向智能体的新范式。这个范式是指模型与运行时环境之间更紧密的耦合。简单来说，我们认为“代码即是我们所需的一切”（Code is all we need）。

[原文] [Barry]: we used to think agents in different domains will look very different each one will need its own tools and scaffolding and that means we'll have a separate agent for each use case for each domain

[译文] [Barry]: 我们过去认为不同领域的智能体看起来会截然不同，每一个都需要其独特的工具和脚手架（scaffolding），这意味着我们需要为每个用例、每个领域构建一个独立的智能体。

[原文] [Barry]: well customization is still important for each domain the agent underneath is actually more universal than we thought what we realized is that code is not just a use case but the universal interface to the digital world

[译文] [Barry]: 虽然针对每个领域的定制化仍然很重要，但底层的智能体实际上比我们想象的要更加通用。我们意识到，代码不仅仅是一个使用场景（use case），而是通往数字世界的通用接口。

[原文] [Barry]: after we built cloud code we realized that cloud code is actually a general purpose agent think about generating a financial report the model can call the API to pull in data and do research it can organize that data in the file system it can analyze it with Python and then synthesize the insight in old file format all through code

[译文] [Barry]: 在构建了Claude Code之后，我们意识到Claude Code实际上是一个通用目的的智能体。试想一下生成财务报告的场景：模型可以调用API来拉取数据并进行调研，它可以在文件系统中组织这些数据，用Python进行分析，然后将洞察综合成旧的文件格式——所有这些都是通过代码完成的。

[原文] [Barry]: the core scaffolding can suddenly become as thin as just bash and file system which is great and really scalable

[译文] [Barry]: 核心的脚手架突然间可以变得像Bash（命令行）和文件系统一样轻量，这非常棒，而且极具可扩展性。

章节 2：解决专业鸿沟——什么是“智能体技能”？

📝 本节摘要：

在确立了代码作为通用接口的优势后，Barry 指出了当前智能体面临的核心痛点：缺乏领域专业知识（Domain Expertise）。他用一个生动的比喻（让数学天才做税务 vs. 让税务专家做税务）说明了高智商并不等同于工作能力。为解决这一问题，Anthropic 推出了“智能体技能（Agent Skills）”。本节详细定义了“技能”的技术本质——即包含文件和脚本的文件夹，并解释了这种设计如何利用现有的开发工具（如Git）解决传统工具的冷启动和上下文限制问题，同时介绍了通过“渐进式披露（Progressive Disclosure）”来优化上下文窗口的技术细节。

[原文] [Barry]: but we very quickly run into a different problem and that problem is domain expertise who do you want doing your taxes is it going to be Mahesh the 300 IQ mathematical genius or is it Barry an experienced tax professional right i would pick Barry every time

[译文] [Barry]: 但我们很快遇到了一个不同的问题，那个问题就是领域专业知识。你想让谁来做你的税务？是Mahesh这位智商300的数学天才，还是Barry这位经验丰富的税务专业人士？对吧，我每次都会选Barry。

[原文] [Barry]: i don't want Mahesh to figure out the 2025 tax code from first principles i need consistent execution from from a domain expert

[译文] [Barry]: 我不想让Mahesh从第一性原理去推导2025年的税法，我需要的是来自领域专家的、一致的执行力。

[原文] [Barry]: as agents today are a lot like Mahes they're brilliant but they lack expertise they can do no more slow they can do amazing things when you really put in the effort and give proper guidance but they're often missing the important context up front they can't really absorb your expertise super well and they don't learn over time

[译文] [Barry]: 如今的智能体很像Mahesh，它们很聪明，但缺乏专业技能。当你真正投入精力并给予适当指导时，它们能做出惊人的事情，但它们往往在一开始就缺少重要的背景信息，它们无法很好地吸收你的专业知识，而且它们不会随着时间的推移而学习。

[原文] [Barry]: that's why we created agent skills skills are organized collections of files that package composable procedural knowledge for agents in other words they're folders

[译文] [Barry]: 这就是为什么我们创建了“智能体技能”（Agent Skills）。技能是有组织的文件的集合，它们为智能体打包了可组合的程序性知识。换句话说，它们就是文件夹。

[原文] [Barry]: this simplicity is deliberate we want something that anyone human or agent can create and use as long as they have a computer these also work with what you already have you can version them in Git you can throw them in Google Drive and you can zip them up and share with your team

[译文] [Barry]: 这种简洁性是刻意的。我们需要一种任何人——无论是人类还是智能体——只要有一台电脑就能创建和使用的东西。这些技能也能与你现有的工具配合使用：你可以在Git中对它们进行版本控制，可以将它们丢进Google Drive，也可以将它们打包压缩并分享给你的团队。

[原文] [Barry]: we have used files for uh as a primitive for decades and we like them so why change now

[译文] [Barry]: 我们使用文件作为基本元素（primitive）已经几十年了，我们很喜欢这种方式，为什么要现在改变呢？

[原文] [Barry]: because of that skills can also include a lot of scripts as tools traditional tools have pretty obvious problems some tools have poorly written instructions and are pretty ambiguous and when the model is struggling it can't really make a change to the tool so it's just kind of stuck with a code start problem and they always live in the context window

[译文] [Barry]: 正因如此，技能还可以包含大量的脚本作为工具。传统工具有非常明显的问题：有些工具的指令写得很差，非常模棱两可；而当模型遇到困难时，它无法真正修改工具，所以它就陷入了一种冷启动（code start）的困境，而且这些工具总是占据着上下文窗口。

[原文] [Barry]: code solves some of these issues it's self-documenting it is modifiable and can live in the file system until they're really needed and used

[译文] [Barry]: 代码解决了一些这样的问题：它是自文档化的，它是可修改的，并且可以一直驻留在文件系统中，直到真正需要和使用它们为止。

[原文] [Barry]: here's an example of a script inside of a skill we kept seeing Claude write the same Python script over and over again to apply styling to slides so we just ask cloud to save it inside of the skill as a tool for his version for his future self now we can just run the script and that makes everything a lot more consistent and a lot more efficient

[译文] [Barry]: 这里有一个技能内部脚本的例子。我们发现Claude一遍又一遍地编写同一个Python脚本来给幻灯片应用样式，所以我们就让Claude把它作为一个工具保存在技能里，留给未来的自己版本使用。现在我们只需运行这个脚本，这让一切都变得更加一致且高效。

[原文] [Barry]: at this point skills can contain a lot of information and we want to protect the context window so that we can fit in hundreds of skills and make them truly composable that's why skills are progressively disclosed at runtime

[译文] [Barry]: 在这一点上，技能可能包含大量信息，而我们希望保护上下文窗口，以便能够容纳数百个技能并使它们真正可组合。这就是为什么技能是在运行时“渐进式披露”（progressively disclosed）的。

[原文] [Barry]: only this metadata is shown to the model just to indicate that he has the skill when an agent needs to use a skill it can read in the rest of the skill.md which contains the core instruction and directory for the rest of the folder everything else is just organized for ease of access so that's all skills are they're organized folders with scripts as tools

[译文] [Barry]: 我们只向模型展示这些元数据，仅为了表明它拥有这个技能。当智能体需要使用某个技能时，它可以读取其余的 skill.md 文件，其中包含了核心指令和文件夹其余部分的目录。其他一切都只是为了便于访问而组织的。所以这就是技能的全部内容：它们就是包含脚本作为工具的有组织的文件夹。

章节 3：生态爆发与技能多样性——从基础能力到企业级应用

📝 本节摘要：

在本章中，Mahesh 介绍了自发布以来“技能”生态系统的快速增长。他将目前的技能分为三类：Anthropic 自建的“基础技能”（如文档编辑）、合作伙伴开发的“第三方技能”（如生物信息分析、浏览器自动化），以及企业内部定制的“团队技能”（如代码规范、入职指引）。此外，他重点阐述了技能与MCP（模型上下文协议）的关系：MCP负责连接外部世界的数据，而技能负责提供处理这些数据的“专业知识”。最后，他提到了一个令人兴奋的趋势：大量非技术人员（如财务、法务）也开始构建技能，验证了该架构的普惠性。

[原文] [Mahesh]: since our launch five weeks ago this very simple design has translated into a very quickly growing ecosystem of thousands of skills and we've seen this be split across a couple of different types of skills

[译文] [Mahesh]: 自从我们五周前发布以来，这种非常简单的设计已经转化为一个快速增长的生态系统，包含了数千种技能，我们看到这些技能主要分为几种不同的类型。

[原文] [Mahesh]: there are foundational skills third party skills created by partners in the ecosystem and skills built within an enterprise and within teams to start foundational skills are those that give agents new general capabilities or domain specific capabilities that it didn't have before

[译文] [Mahesh]: 它们包括基础技能、由生态系统中的合作伙伴创建的第三方技能，以及在企业内部和团队内部构建的技能。首先，基础技能是指那些赋予智能体以前不具备的新的通用能力或特定领域能力的技能。

[原文] [Mahesh]: we ourselves with our launch built document skills that give Claude the ability to create and edit professional quality office documents

[译文] [Mahesh]: 我们自己在发布时就构建了文档技能，赋予了Claude创建和编辑专业质量办公文档的能力。

[原文] [Mahesh]: we're also really excited to see people like Cadence build scientific research skills that give Claude new capabilities like EHR data analysis and using common Python bioinformatics libraries better than it could before

[译文] [Mahesh]: 我们也非常高兴看到像Cadence这样的公司构建了科学研究技能，赋予Claude诸如EHR（电子健康记录）数据分析以及比以前更好地使用常见Python生物信息学库的新能力。

[原文] [Mahesh]: we've also seen partners in the ecosystem build skills that help Claude better with their own software and their own products browserbase is a pretty good example of this they built a skill for their open- source browser automation tooling stage hand and now Claude equipped that this skill and with stage hand can now go navigate the web and use a browser more effectively to get work done

[译文] [Mahesh]: 我们还看到生态系统中的合作伙伴构建了一些技能，帮助Claude更好地配合他们自己的软件和产品使用。Browserbase就是一个很好的例子，他们为自己的开源浏览器自动化工具Stagehand构建了一个技能，现在装备了这个技能并结合Stagehand的Claude，可以更有效地浏览网络和使用浏览器来完成工作。

[原文] [Mahesh]: and notion launched a bunch of skills that help claude better understand your notion workspace and do deep research over your entire workspace

[译文] [Mahesh]: Notion也推出了一系列技能，帮助Claude更好地理解你的Notion工作区，并在整个工作区内进行深度调研。

[原文] [Mahesh]: and I think where I've seen the most excitement and traction with skills is within large enterprises these are company and team specific skills built for an organization we've been talking to Fortune 100s that are using skills as a way to teach agents about their organizational best practices and the weird and unique ways that they use this bespoke internal software

[译文] [Mahesh]: 我认为我在技能方面看到最令人兴奋和最具吸引力的地方是在大型企业内部。这些是为组织构建的公司和团队特定技能。我们一直在与财富100强企业交流，他们正在使用技能来教导智能体了解其组织的最佳实践，以及他们使用定制内部软件的那些奇怪而独特的方式。

[原文] [Mahesh]: we're also talking to really large developer productivity teams these are teams serving thousands or even tens of thousands of developers in an organization that are using skills as a way to deploy agents like cloud code and teach them about code style best practices and other ways that they want their developers to work internally

[译文] [Mahesh]: 我们也在与非常庞大的开发者生产力团队交流，这些团队服务于组织内的数千甚至数万名开发者，他们利用技能来部署像Claude Code这样的智能体，并教导它们关于代码风格的最佳实践，以及他们希望开发者在内部工作的其他方式。

[原文] [Mahesh]: so all of these different types of skills are created and consumed by different people inside of an organization or in the world but what they have in common is anyone can create them and they give agents the new capabilities that they didn't have before

[译文] [Mahesh]: 因此，所有这些不同类型的技能都是由组织内部或世界各地的不同人群创建和使用的，但它们的共同点是任何人都可以创建它们，并且它们赋予了智能体以前不具备的新能力。

[原文] [Mahesh]: so as this ecosystem has grown we've started to observe a couple of interesting trends first skills are starting to get more complex the most basic skill today can still be a skill.md markdown file with some prompts and some really basic instructions but we're starting to see skills that package software executables binaries files code scripts assets and a lot more

[译文] [Mahesh]: 随着这个生态系统的成长，我们开始观察到几个有趣的趋势。首先，技能开始变得越来越复杂。如今最基本的技能仍然可以是一个包含一些提示词和基础指令的 skill.md Markdown文件，但我们开始看到一些技能打包了软件可执行文件、二进制文件、代码脚本、资产等等。

[原文] [Mahesh]: and a lot of the skills that are being built today might take minutes or hours to build and put into an agent but we think that increasingly much like a lot of the software we use today these skills might take weeks or months to build and be maintained

[译文] [Mahesh]: 如今构建的许多技能可能只需要几分钟或几小时就能完成并放入智能体中，但我们认为，就像我们今天使用的许多软件一样，这些技能将越来越多地需要数周或数月的时间来构建和维护。

[原文] [Mahesh]: we're also seeing that this ecosystem of skills is complementing the existing ecosystem of MCP servers that was built up over the course of this year developers are using and building skills that orchestrate workflows of multiple MCP tools stitched together to do more complex things with external data and connectivity

[译文] [Mahesh]: 我们还看到，这个技能生态系统正在补充今年建立起来的MCP（模型上下文协议）服务器生态系统。开发者正在使用和构建技能，来编排多个MCP工具的工作流，将它们拼接在一起，利用外部数据和连接性来做更复杂的事情。

[原文] [Mahesh]: and in these cases MCP MCP is providing the connection to the outside world while skills are providing the expertise

[译文] [Mahesh]: 在这些案例中，MCP提供了与外部世界的连接，而技能则提供了专业知识（Expertise）。

[原文] [Mahesh]: and finally and I think most excitingly for me personally is we're seeing skills that are being built by people that aren't technical these are people in functions like finance recruiting accounting legal and a lot more

[译文] [Mahesh]: 最后，这也是我个人认为最令人兴奋的一点，我们看到技能正在由非技术人员构建。这些是来自财务、招聘、会计、法务等职能部门的人员。

[原文] [Mahesh]: um and I think this is pretty early validation of our initial idea that skills help people that aren't doing coding work extend these general agents and they make these agents more accessible for the day-to-day of what these people are working on

[译文] [Mahesh]: 嗯，我认为这对我们的初步设想是一个相当早期的验证，即技能可以帮助那些不从事编码工作的人扩展这些通用智能体，并使这些智能体在这些人的日常工作中更易于使用。

章节 4：通用智能体的新兴架构与未来演进

📝 本节摘要：

在本章中，Mahesh 将之前的讨论整合成一个统一的“通用智能体新兴架构”：即“智能体循环（Agent Loop）”负责管理上下文，配合提供文件系统和代码能力的“运行时环境”，再通过 MCP 连接外部数据，最后按需挂载“技能库”。他指出，这种“MCP + 技能”的组合模式已成功帮助 Claude 快速部署到金融服务和生命科学等垂直领域。面对技能日益增加的复杂度，他提出了未来的技术路线图：必须像对待软件一样对待技能，引入测试评估、版本控制（Versioning）以及明确的依赖关系管理（Dependencies），以确保智能体行为的稳定性和可预测性。

[原文] [Mahesh]: so tying this all together let's talk about how these all fit into this emerging architecture of general agents

[译文] [Mahesh]: 那么将所有这些联系起来，让我们谈谈这些如何融入这个正在浮现的通用智能体架构中。

[原文] [Mahesh]: first we think this architecture is converging on a couple of things the first is this agent loop that helps manage the the model's internal context and manages what tokens are going in and out and this is coupled with a runtime environment that provides the agent with a file system and the ability to read and write code

[译文] [Mahesh]: 首先，我们认为这个架构正在向几个方面收敛。首先是“智能体循环（Agent Loop）”，它有助于管理模型的内部上下文，并管理输入和输出的 Token；它与一个“运行时环境”相结合，该环境为智能体提供了文件系统以及读写代码的能力。

[原文] [Mahesh]: this agent as many of us have done throughout this year can be connected to MCP servers and these are tools and data from the outside world that make the the agent more relevant and more effective

[译文] [Mahesh]: 正如我们许多人在这一年中所做的那样，这个智能体可以连接到 MCP 服务器，这些是来自外部世界的工具和数据，能让智能体变得更相关且更有效。

[原文] [Mahesh]: and now we can give the same agent a library of hundreds or thousands of skills that it can decide to pull into context only at runtime when it's deciding to work on a particular task

[译文] [Mahesh]: 而现在，我们可以给同一个智能体提供一个包含数百甚至数千种技能的库，它可以仅在决定处理特定任务时，才在运行时决定将哪些技能拉入上下文中。

[原文] [Mahesh]: today giving an agent a new capability in a new domain might just involve equipping it with the right set of MCP servers and the right library of skills

[译文] [Mahesh]: 如今，赋予智能体在某个新领域的新能力，可能只需要为它装备一套合适的 MCP 服务器和合适的技能库。

[原文] [Mahesh]: and this emerging pattern of an agent with an MCP server and a set of skills is something that's already helping us at Enthropic deploy Claude to new verticals

[译文] [Mahesh]: 这种由“智能体 + MCP 服务器 + 一套技能”组成的新兴模式，已经在帮助我们 Anthropic 将 Claude 部署到新的垂直领域中。

[原文] [Mahesh]: just after we launched skills 5 weeks ago we immediately launched new offerings in financial services and life sciences and each of these came with a set of MCP servers and a set of skills that immediately make Claude more effective for professionals in each of these domains

[译文] [Mahesh]: 就在我们五周前推出技能后，我们紧接着推出了在金融服务和生命科学领域的新产品，每一个产品都配备了一套 MCP 服务器和一套技能，这立即让 Claude 对这些领域的专业人士来说变得更加高效。

[原文] [Mahesh]: we're also starting to think about some of the other open questions and areas that we want to focus on for how skills evolve in the future as they start to become more complex we really want to support developers enterprises and other skill builders by starting to treat skills like we treat software

[译文] [Mahesh]: 我们也开始思考其他一些悬而未决的问题以及我们希望关注的领域，关于技能在未来如何演变。随着它们开始变得越来越复杂，我们真的希望能通过“像对待软件一样对待技能”的方式，来支持开发者、企业和其他技能构建者。

[原文] [Mahesh]: this means exploring testing and evaluation better tooling to make sure that these agents are loading and triggering skills at the right time and for the right task and tooling to help measure the output quality of an agent equipped with the skill to make sure that's on par with what the agent is supposed to be doing

[译文] [Mahesh]: 这意味着探索测试和评估，开发更好的工具来确保这些智能体在正确的时间、针对正确的任务加载和触发技能；以及开发工具来帮助衡量装备了该技能的智能体的输出质量，以确保其水平符合智能体的预期表现。

[原文] [Mahesh]: we'd also like to focus on versioning as a skill evolves and the resulting agent behavior uh evolves we want this to be uh clearly tracked and to have a clear lineage over time

[译文] [Mahesh]: 我们还想关注版本控制（Versioning）。随着技能的演进以及随之而来的智能体行为的演变，我们希望这能被清晰地追踪，并且随着时间的推移有一个清晰的血统（lineage）。

[原文] [Mahesh]: and finally we'd also like to explore skills that can explicitly depend on and refer to either other skills MCP servers and dependencies and packages within the agents environment

[译文] [Mahesh]: 最后，我们还想探索那些可以显式依赖并引用其他技能、MCP 服务器以及智能体环境内依赖项和包的技能。

[原文] [Mahesh]: we think that this is going to make agents a lot more predictable in different runtime environments and the composability of multiple skills together will help agents like Claude elicit even more complex and relevant behavior from these agents

[译文] [Mahesh]: 我们认为这将使智能体在不同的运行时环境中变得更加可预测，而且多个技能的组合性将帮助像 Claude 这样的智能体激发出更复杂、更相关的行为。

[原文] [Mahesh]: overall these set of things should hopefully make skills easier to build and easier to integrate into agent products even those besides claude

[译文] [Mahesh]: 总的来说，这一系列举措应该有望使技能更容易构建，也更容易集成到智能体产品中，甚至是 Claude 以外的产品。

章节 5：知识的复利——从团队共享到自我进化的智能体

📝 本节摘要：

本章重点阐述了“技能”作为知识载体的两大核心价值：共享（Sharing）与持续学习（Continuous Learning）。Mahesh 首先指出，技能不仅是个人工具，更是企业的“演进式知识库”。当新员工加入时，通过现有的技能库，他们能立即获得团队的上下文和工作流。

随后（话筒转回 Barry），演讲进入了更具前瞻性的视野：让 Claude 自己创建技能。这使得“记忆”不再是抽象的上下文，而是变成了可保存、可优化的代码文件。这意味着 Claude 在第 30 天的工作能力将远超第 1 天，实现了真正的能力复利。

[原文] [Mahesh]: finally a huge part of the value of skills we think is going to come from sharing and distribution

[译文] [Mahesh]: 最后，我们认为技能的很大一部分价值将来自于分享和分发。

[原文] [Mahesh]: barry and I think a lot about the future of companies that are deploying these agents at scale and the vision that excites us most is one of a collecting and collective and evolving knowledge base of capabilities that's curated by people and agents inside of an organization

[译文] [Mahesh]: Barry和我经常思考那些大规模部署这些智能体的公司的未来，而最让我们兴奋的愿景是：一个由组织内部的人员和智能体共同策划的、汇集的、集体的且不断演进的能力知识库。

[原文] [Mahesh]: we think skills are a big step towards this vision they provide the procedural knowledge for your agents to do useful things and as you interact with an agent and give it feedback and more institutional knowledge it starts to get better and all of the agents inside your team and your org get better as well

[译文] [Mahesh]: 我们认为技能是朝着这个愿景迈出的一大步。它们为你的智能体提供了做有用之事的程序性知识；当你与智能体互动、给予反馈并提供更多的机构知识时，它开始变得更好，而且你团队和组织内的所有智能体也会随之变得更好。

[原文] [Mahesh]: and when someone joins your team and starts using Claude for the first time it already knows what your team cares about it knows about your day-to-day and it knows about how to be most effective for the work that you're doing

[译文] [Mahesh]: 当有人加入你的团队并第一次开始使用Claude时，它已经知道你的团队关心什么，知道你的日常工作内容，也知道如何针对你正在做的工作发挥最大效能。

[原文] [Mahesh]: and as this grows and this ecosystem starts to develop even more this was going to this compounding value is going to extend outside of just your organ into the broader community

[译文] [Mahesh]: 随着这种模式的发展以及生态系统开始进一步壮大，这种复利价值将不仅仅局限于你的组织内部，还会扩展到更广泛的社区。,

[原文] [Mahesh]: so just like when someone else across the world builds an MCP server that makes your agent more useful a skill built by someone else in the community will help make your own agents more capable reliable and useful as well

[译文] [Mahesh]: 就像世界上其他地方的人构建了一个MCP服务器能让你的智能体更有用一样，社区中其他人构建的技能也将帮助你的智能体变得更加能干、可靠和有用。

[原文] [Barry]: this vision of a evolving knowledge base gets even more powerful when claw starts to create these skills we design skills specifically as a concrete steps towards uh continuous learning

[译文] [Barry]: 当Claude开始自己创建这些技能时，这个不断演进的知识库的愿景会变得更加强大。我们特意将技能设计为通向“持续学习”的具体步骤。

[原文] [Barry]: when you first start using cloud this standardized format gives a very important guarantee anything that cloud writes down can be used efficiently by a future version of itself this makes the learning actually transferable

[译文] [Barry]: 当你刚开始使用Claude时，这种标准化的格式提供了一个非常重要的保证：Claude写下的任何东西都可以被未来的自己高效地使用。这使得学习实际上变得可迁移了。

[原文] [Barry]: as you build up the context skills makes the concept of memory more tangible they don't capture everything they don't capture every type of information just procedural knowledge that cloud can use on specific tasks

[译文] [Barry]: 随着你不断积累上下文，技能让“记忆”这个概念变得更加有形（tangible）。它们不会捕捉所有东西，不会捕捉每一类信息，只捕捉Claude可以在特定任务中使用的程序性知识。

[原文] [Barry]: when you have worked with cloud for quite a while the flexibility of skills matters even more cloud can acquire new capabilities instantly evolve them as needed and then drop the ones that become obsolete

[译文] [Barry]: 当你与Claude共事很长一段时间后，技能的灵活性就变得更加重要了。Claude可以瞬间获得新能力，按需演进它们，然后丢弃那些变得过时的能力。,

[原文] [Barry]: this is what we have always known the power of in in context learning makes this a lot more cost- effective for information that change on daily basis

[译文] [Barry]: 这就是我们一直所知的“上下文内学习（in-context learning）”的力量，它使得处理那些每天都在变化的信息变得更加具有成本效益。

[原文] [Barry]: our goal is that claude on day 30 of working with you is going to be a lot better on cloud on day one cl can already create skills for you today using our skill creator skill and we're going to continue pushing in that direction

[译文] [Barry]: 我们的目标是，与你工作到第30天的Claude将比第1天的Claude强得多。Claude今天已经可以使用我们的“技能创建者技能（skill creator skill）”为你创建技能了，我们将继续朝着这个方向推进。

章节 6：终极类比与行动号召——模型是CPU，技能是App

📝 本节摘要：

在演讲的最后，Barry 提出了一个宏大的技术类比，将 AI 智能体的发展历程与计算机历史对标。他提出：模型（Models）就像处理器（Processors），虽然强大但需巨额投资；智能体运行时（Agent Runtime）就像操作系统（OS），负责资源调度；而技能（Skills）则对应应用程序（Applications）。

>

他强调，正如历史上有数百万开发者通过编写软件创造了巨大价值一样，AI 的未来在于开发者将“领域专业知识”编码进技能中。最后，他发出了强有力的行动号召：停止重复造轮子（Rebuilding Agents），开始构建技能（Building Skills），并通过简单的文件夹结构为世界解决具体问题。

[原文] [Barry]: we're going to conclude by comparing the agent stack to what we have already seen computing in a rough analogy models are like processors both require massive investment and contain immense potential but only so useful by themselves

[译文] [Barry]: 我们将通过把智能体技术栈与我们在计算领域已见证的发展进行比较来结束本次演讲。做一个粗略的类比：模型就像处理器。两者都需要巨大的投资并包含巨大的潜力，但单靠它们自己用处有限。

[原文] [Barry]: then we start building operating system the OS made processors far more valuable by orchestrating the processes resources and data around the processor

[译文] [Barry]: 然后我们开始构建操作系统。操作系统通过编排处理器周围的进程、资源和数据，使处理器变得更有价值。

[原文] [Barry]: in AI we believe that agent runtime is starting to play this role we're all trying to build the cleanest most efficient and most scalable uh abstractions to get the right tokens in and out of the model

[译文] [Barry]: 在AI领域，我们认为智能体运行时（Agent Runtime）正开始扮演这一角色。我们都在努力构建最干净、最高效且最具可扩展性的抽象层，以便让正确的Token进出模型。,

[原文] [Barry]: but once we have a platform the real value comes from applications a few companies build uh processors and operating systems but millions of developers like us have built software that encoded domain expertise and our unique points of view

[译文] [Barry]: 但是一旦我们拥有了平台，真正的价值便来自于应用程序。只有少数几家公司制造处理器和操作系统，但像我们这样的数百万开发者构建了软件，这些软件编码了领域专业知识以及我们独特的观点。

[原文] [Barry]: we hope that skills can help us open up this layer for everyone this is where we get creative and solve concrete problem for ourselves for each other and for the world just by putting stuff in the folder

[译文] [Barry]: 我们希望“技能”可以帮助我们为每个人打开这一层级。这是我们发挥创造力，为我们自己、为彼此以及为世界解决具体问题的地方——仅仅通过把东西放进文件夹里。

[原文] [Barry]: so skills are just the starting point to close out we think we're now converging on this general architecture for general agents we've created skills as a new paradigm for shipping and sharing new capabilities

[译文] [Barry]: 所以技能仅仅是一个起点。总结一下，我们认为我们现在正趋同于这个通用智能体的通用架构。我们要创造技能，作为一种发布和分享新能力的新范式。

[原文] [Barry]: so we think it's time to stop rebuilding agents and start building skills instead and if you're excited about this come work with us and start building some skills today thank you

[译文] [Barry]: 所以我们认为，现在是时候停止重复构建智能体，转而开始构建技能了。如果你对此感到兴奋，欢迎加入我们，或者从今天就开始构建一些技能吧。谢谢大家。,