Anthropic Unveils 'Skills for Claude': A Leap Towards Customizable AI Assistants

Skills for Claude will let you customize tasks with pre-set instructions - here's how

Bear in mind that more access to personal data means more risk. Anthropic launched Skills for Claude on Wednesday, a new feature aimed at making the company's flagship AI chatbot more customizable for individual users and businesses. You can think of Skills as little digital instruction manuals, each of which can be used by Claude to guide its behavior on a given task. Anthropic described them in a blog post as "custom onboarding materials that let you package expertise, making Claude a specialist on what matters most to you." Anthropic has developed its own, one-size-fits-all skills -- including those to help generate Word docs, Excel spreadsheets, and PowerPoint docs -- but users can also create and upload their own, custom skills. Claude can automatically determine which Skills it should use based on the prompt it's been given by a user. The core idea behind Skills is to make Claude more customizable: individuals and businesses all have their own unique preferences when it comes to using AI chatbots, and Skills are essentially a shortcut towards ensuring you receive the outputs you're looking for as quickly as possible. Also: Claude's latest model is cheaper and faster than Sonnet 4 - and free For example, say you're turning to Claude for help creating a pitch deck for a prospective new client. Rather than having to meticulously explain the subtleties of your brand's voice and approach to sales, Claude can automatically reference the "Brand guidelines" Skill you've previously uploaded, and from there, infer everything it needs to know to generate a PowerPoint presentation that's tailor-made for your company. (You can learn more about creating custom Skills here.) The launch of Skills, therefore, also marks a step towards making Claude more agentic, or able to carry out complex tasks with minimal user oversight, based on its growing ability to analyze the context and goals of particular users. Skills are available now for Pro, Max, Team, and Enterprise users, and can be viewed via Settings > Capabilities. Account admins for Team and Enterprise accounts must first enable organization-wide access before Skills can be used by individual employees. Skills work across the Claude app, Claude Code, and the Claude API, meaning developers only need to build them once before they can be deployed across their organizations. AI chatbots like ChatGPT, Claude, and Gemini were designed to be general-purpose tools, trained effectively on the entirety of the internet and able to respond to prompts covering virtually any topic. Increasingly, however, tech developers have been transforming their AI systems into more specialized tools. A predominant, burgeoning vision of AI that's started to flower across Silicon Valley is a future in which each of us has a personal AI assistant (or a collection of assistants), which knows us at an intimate level and is customized to execute tasks according to our particular preferences. Anthropic's Wednesday launch of Skills for Claude is just the latest in a long string of similar efforts throughout the AI industry. Just last week, for example, Microsoft debuted new connectors for Copilot, which allow the chatbot to pull user information from Gmail, Google Drive, and other apps. The previous week, Anthropic announced a new Slack integration for Claude. All of these personalization features also present new risks. The more personal data you elect to share with AI tools, the more rigorous your security protocols should be. Also: Claude now integrates directly with Microsoft 365 While every AI developer has their own data privacy policies, it's generally wise to operate under the assumption that any information you share with a chatbot will be stored by the system and added to its training data, thus presenting the possibility that it will be unintentionally surfaced by some other user in the future. The fact that Skills for Claude can enable the chatbot to auto-run code carries dangers of its own. "While powerful," Anthropic wrote in its blog post, "it means being mindful about which Skills you use -- stick to trusted sources to keep your data safe."

Anthropic turns to 'skills' to make Claude more useful at work

AI agents spent years as a concept and then as an experiment. Now, AI companies are devoting even more time and resources than before to make their agents actually useful for end users, whether they're consumers or professionals. Anthropic on Thursday announced its next step toward that goal: Skills for Claude. The tool is made up of "folders that include instructions, scripts, and resources that Claude can load when needed to make it smarter at specific work tasks -- from working with Excel [to] following your organization's brand guidelines," per a release. People can also build their own Skills for Claude relative to their specific jobs and use them across Claude.ai, Claude Code, Anthropic's API, and the Claude Agent SDK. Box, Rakuten, and Canva have already used the tool, according to the release. Essentially, the feature is designed to improve Claude's AI agent capabilities for your work specifically, so you don't have to spend as much time writing the perfect prompt or referring to past context every time you're trying to accomplish a task. It's available to Pro, Max, Team, and Enterprise users. Brad Abrams, a product lead at Anthropic, told The Verge that "the thing that's interesting to me about Skills is basically about agents." He said that Skills as a feature essentially provides organizations building agents a way to teach Claude to do a good job "in their specific context." He emphasized that it's not about meeting arbitrary benchmarks -- it's about being able to do the task you need at your own company. Using an Anthropic layer on top of Claude's PowerPoint Skill, "I had Claude create me a presentation about how Haiku 4.5 is doing in the market," Abrams said, adding that Claude created "well-formatted slides that are easy to digest." OpenAI, Anthropic, Google, Microsoft, and others have been working toward the goal of actually useful AI agents for years, with executives regularly bringing up agentic AI on earnings calls and redirecting internal resources toward building the tools. To date, though, progress has been largely incremental, with companies fighting to release new feature updates or iterations of agents. (Think: Anthropic's Computer Use -- or OpenAI's Operator, then Deep Research, and then ChatGPT Agent, which essentially combined the two.) Anthropic's news also follows an OpenAI announcement in the same realm earlier this month at the company's annual DevDay event. At the event, OpenAI unveiled AgentKit, a group of tools executives said were "designed to help you take agents from prototype to production" and targeted both big companies and individual developers. The example use case OpenAI demonstrated was Albertsons, which runs more than 2,000 US grocery stores, using a custom agent with custom data to create a plan to improve ice cream sales if they were down more than 30 percent. Box, Canva, Evernote, and Ramp were also mentioned as having tried the tool. OpenAI also announced a consumer-facing tool that allows people to work with apps inside ChatGPT, like Zillow and Uber Eats.

Anthropic brings mad Skills to Claude

Paying Anthropic customers can now teach their Claude new tricks, which the company calls Skills. Despite much talk about superintelligence, AI models can be clueless when it comes to interacting with specific applications. Sure, they can parse PDF text, but they probably don't know how to fill in a PDF form. Skills, or Agent Skills for jargon maximalists, offer a way to instill Claude with specific knowledge that it may not possess in its distillation of training data. Anthropic has already deployed a few of them within Claude to handle common tasks like creating spreadsheets or presentations. Now, paying Claude customers - not the freeloader tier - can create Skills that suit their specific needs. Just make sure to subtract the labor that went into creating them when tabulating time saved by AI. A Skill consists of a directory with a SKILL.md file - a mix of YAML and Markdown - and possibly other resources such as text, scripts, and data. This turducken of instructions and executable code can be stored locally (~/.claude/skills/) or uploaded to the cloud for use with the Claude API. Claude's context window when loaded appends metadata from available Skills in the system prompt. Thereafter, when Claude is asked to carry out a relevant task, it will launch the appropriate skill by invoking the Bash tool to read the SKILL.md file. Once done, the model should have the data necessary to perform the desired task, such as interacting with content in a third-party application like Box or creating a PowerPoint presentation. The AI model will do so through a process Anthropic calls progressive disclosure. "Progressive disclosure is the core design principle that makes Agent Skills flexible and scalable," the company explains in its engineering blog post on the subject. "Like a well-organized manual that starts with a table of contents, then specific chapters, and finally a detailed appendix, skills let Claude load information only as needed." The result is that Claude doesn't process tokens unnecessarily for Skills that won't be used, which helps keep operating costs down. Skills also provide a way to revert to programmatic code execution when a large language model would be the wrong tool for the job. As an example, Anthropic cites the inefficiency of sorting a list via token generation - a coded sorting algorithm will complete the task much faster and at less cost, and will produce the same output every time. Creating Skills can be complicated for those who want to create the relevant files manually, but they're less burdensome with Claude's help. Claude incorporates a "skill-creator" that enables the creation of new Skills through interactive chatbot banter. There's also a Claude Skills Cookbook for those who want to understand the creation process. Speaking of malware, Anthropic warns that Skills present some risk (not unlike giving Claude access to Bash). Malicious Skills, the company cautions, may introduce vulnerabilities or allow the exfiltration of data. "We recommend installing skills only from trusted sources," the company says. "When installing a skill from a less-trusted source, thoroughly audit it before use. Start by reading the contents of the files bundled in the skill to understand what it does, paying particular attention to code dependencies and bundled resources like images or scripts. Similarly, pay attention to instructions or code within the skill that instruct Claude to connect to potentially untrusted external network sources." With that in mind, we note that Anthropic says it hopes to enable AI agents to create their own Skills. ®

Claude just got customizable 'Skills' -- here's how they could supercharge your workflow

A day after launching Haiku 4.5, Anthropic is giving users even more ways to level up their workflow. A new feature called Claude Skills allows users to teach Claude a new specialty on the fly, without code. This could mean everything from formatting Excel formulas to applying your company's branding within PowerPoint decks or even following a legal policy when reviewing contracts. These Skills are small, task-specific modules made up of folders, scripts and instructions that Claude can "load" when they're relevant. It's a way to give you a hand on demand without needing an extensive training program to make it happen. Claude Skills are now live across Claude apps, Claude Code, and API integrations, available to Pro, Max, Team and Enterprise users. Claude Skills are customizable workflows that teach Claude how to perform specific tasks exactly in the way you want them done. For example, you can build a Skill that makes Claude follow your team's design language when generating decks, or one that includes formatting rules for financial spreadsheets. Anthropic describes them as: If you've seen Claude generate Excel spreadsheets or PDFs in-app, you've already experienced built-in Skills. But now Anthropic is taking it a bit further. Claude will automatically detect and apply the right Skills without manual toggling; you'll even see which ones were used in its "chain of thought." There's also a "skill-creator" Skill that walks you through building your first one. It asks about your workflow, generates the folder structure and builds out the required files. No coding needed. integratewhileEnterprise teams, developers and creative professionals are the first to benefit. Canva, for example, is using Skills to plug Claude into their design workflows, and Box is using them to transform stored content into on-brand presentations and documents. For developers, Skills can be installed via plugins or version-controlled through Claude Code. You can also manage Skills through the Claude Console or via API with full version control, just know you'll need access to the Code Execution Tool beta, since some Skills run executable code. Anthropic cautions users to stick to trusted Skills, especially when using code execution features. Giving an AI access to run code always comes with privacy risks, but Claude is only as safe as the instructions it's following. Still, if you've been waiting for an AI assistant that actually understands how you work, Claude Skills might be the upgrade that finally delivers. Claude Skills move us one step closer to personalization with an AI assistant equipped with the knowledge and formatting preferences you need with very little training. This rollout is also a big step in the agentic direction, giving Claude more structured capabilities to support long-running workflows, multi-step planning and contextual awareness.

How Anthropic's 'Skills' make Claude faster, cheaper, and more consistent for business workflows

Anthropic launched a new capability on Thursday that allows its Claude AI assistant to tap into specialized expertise on demand, marking the company's latest effort to make artificial intelligence more practical for enterprise workflows as it chases rival OpenAI in the intensifying competition over AI-powered software development. The feature, called Skills, enables users to create folders containing instructions, code scripts, and reference materials that Claude can automatically load when relevant to a task. The system marks a fundamental shift in how organizations can customize AI assistants, moving beyond one-off prompts to reusable packages of domain expertise that work consistently across an entire company. "Skills are based on our belief and vision that as model intelligence continues to improve, we'll continue moving towards general-purpose agents that often have access to their own filesystem and computing environment," said Mahesh Murag, a member of Anthropic's technical staff, in an exclusive interview with VentureBeat. "The agent is initially made aware only of the names and descriptions of each available skill and can choose to load more information about a particular skill when relevant to the task at hand." The launch comes as Anthropic, valued at $183 billion after a recent $13 billion funding round, projects its annual revenue could nearly triple to as much as $26 billion in 2026, according to a recent Reuters report. The company is currently approaching a $7 billion annual revenue run rate, up from $5 billion in August, fueled largely by enterprise adoption of its AI coding tools -- a market where it faces fierce competition from OpenAI's recently upgraded Codex platform. How 'progressive disclosure' solves the context window problem Skills differ fundamentally from existing approaches to customizing AI assistants, such as prompt engineering or retrieval-augmented generation (RAG), Murag explained. The architecture relies on what Anthropic calls "progressive disclosure" -- Claude initially sees only skill names and brief descriptions, then autonomously decides which skills to load based on the task at hand, accessing only the specific files and information needed at that moment. "Unlike RAG, this relies on simple tools that let Claude manage and read files from a filesystem," Murag told VentureBeat. "Skills can contain an unbounded amount of context to teach Claude how to complete a task or series of tasks. This is because Skills are based on the premise of an agent being able to autonomously and intelligently navigate a filesystem and execute code." This approach allows organizations to bundle far more information than traditional context windows permit, while maintaining the speed and efficiency that enterprise users demand. A single skill can include step-by-step procedures, code templates, reference documents, brand guidelines, compliance checklists, and executable scripts -- all organized in a folder structure that Claude navigates intelligently. The system's composability provides another technical advantage. Multiple skills automatically stack together when needed for complex workflows. For instance, Claude might simultaneously invoke a company's brand guidelines skill, a financial reporting skill, and a presentation formatting skill to generate a quarterly investor deck -- coordinating between all three without manual intervention. What makes Skills different from OpenAI's Custom GPTs and Microsoft's Copilot Anthropic is positioning Skills as distinct from competing offerings like OpenAI's Custom GPTs and Microsoft's Copilot Studio, though the features address similar enterprise needs around AI customization and consistency. "Skills' combination of progressive disclosure, composability, and executable code bundling is unique in the market," Murag said. "While other platforms require developers to build custom scaffolding, Skills let anyone -- technical or not -- create specialized agents by organizing procedural knowledge into files." The cross-platform portability also sets Skills apart. The same skill works identically across Claude.ai, Claude Code (Anthropic's AI coding environment), the company's API, and the Claude Agent SDK for building custom AI agents. Organizations can develop a skill once and deploy it everywhere their teams use Claude, a significant advantage for enterprises seeking consistency. The feature supports any programming language compatible with the underlying container environment, and Anthropic provides sandboxing for security -- though the company acknowledges that allowing AI to execute code requires users to carefully vet which skills they trust. Early customers report 8x productivity gains on finance workflows Early customer implementations reveal how organizations are applying Skills to automate complex knowledge work. At Japanese e-commerce giant Rakuten, the AI team is using Skills to transform finance operations that previously required manual coordination across multiple departments. "Skills streamline our management accounting and finance workflows," said Yusuke Kaji, general manager of AI at Rakuten in a statement. "Claude processes multiple spreadsheets, catches critical anomalies, and generates reports using our procedures. What once took a day, we can now accomplish in an hour." That's an 8x improvement in productivity for specific workflows -- the kind of measurable return on investment that enterprises increasingly demand from AI implementations. Mike Krieger, Anthropic's chief product officer and Instagram co-founder, recently noted that companies have moved past "AI FOMO" to requiring concrete success metrics. Design platform Canva plans to integrate Skills into its own AI agent workflows. "Canva plans to leverage Skills to customize agents and expand what they can do," said Anwar Haneef, general manager and head of ecosystem at Canva in a statement. "This unlocks new ways to bring Canva deeper into agentic workflows -- helping teams capture their unique context and create stunning, high-quality designs effortlessly." Cloud storage provider Box sees Skills as a way to make corporate content repositories more actionable. "Skills teaches Claude how to work with Box content," said Yashodha Bhavnani, head of AI at Box. "Users can transform stored files into PowerPoint presentations, Excel spreadsheets, and Word documents that follow their organization's standards -- saving hours of effort." The enterprise security question: Who controls which AI skills employees can use? For enterprise IT departments, Skills raise important questions about governance and control -- particularly since the feature allows AI to execute arbitrary code in sandboxed environments. Anthropic has built administrative controls that allow enterprise customers to manage access at the organizational level. "Enterprise admins control access to the Skills capability via admin settings, where they can enable or disable access and monitor usage patterns," Murag said. "Once enabled at the organizational level, individual users still need to opt in." That two-layer consent model -- organizational enablement plus individual opt-in -- reflects lessons learned from previous enterprise AI deployments where blanket rollouts created compliance concerns. However, Anthropic's governance tools appear more limited than some enterprise customers might expect. The company doesn't currently offer granular controls over which specific skills employees can use, or detailed audit trails of custom skill content. Organizations concerned about data security should note that Skills require Claude's code execution environment, which runs in isolated containers. Anthropic advises users to "stick to trusted sources" when installing skills and provides security documentation, but the company acknowledges this is an inherently higher-risk capability than traditional AI interactions. From API to no-code: How Anthropic is making Skills accessible to everyone Anthropic is taking several approaches to make Skills accessible to users with varying technical sophistication. For non-technical users on Claude.ai, the company provides a "skill-creator" skill that interactively guides users through building new skills by asking questions about their workflow, then automatically generating the folder structure and documentation. Developers working with Anthropic's API get programmatic control through a new /skills endpoint and can manage skill versions through the Claude Console web interface. The feature requires enabling the Code Execution Tool beta in API requests. For Claude Code users, skills can be installed via plugins from the anthropics/skills GitHub marketplace, and teams can share skills through version control systems. "Skills are included in Max, Pro, Teams, and Enterprise plans at no additional cost," Murag confirmed. "API usage follows standard API pricing," meaning organizations pay only for the tokens consumed during skill execution, not for the skills themselves. Anthropic provides several pre-built skills for common business tasks, including professional generation of Excel spreadsheets with formulas, PowerPoint presentations, Word documents, and fillable PDFs. These Anthropic-created skills will remain free. Why the Skills launch matters in the AI coding wars with OpenAI The Skills announcement arrives during a pivotal moment in Anthropic's competition with OpenAI, particularly around AI-assisted software development. Just one day before releasing Skills, Anthropic launched Claude Haiku 4.5, a smaller and cheaper model that nonetheless matches the coding performance of Claude Sonnet 4 -- which was state-of-the-art when released just five months ago. That rapid improvement curve reflects the breakneck pace of AI development, where today's frontier capabilities become tomorrow's commodity offerings. OpenAI has been pushing hard on coding tools as well, recently upgrading its Codex platform with GPT-5 and expanding GitHub Copilot's capabilities. Anthropic's revenue trajectory -- potentially reaching $26 billion in 2026 from an estimated $9 billion by year-end 2025 -- suggests the company is successfully converting enterprise interest into paying customers. The timing also follows Salesforce's announcement this week that it's deepening AI partnerships with both OpenAI and Anthropic to power its Agentforce platform, signaling that enterprises are adopting a multi-vendor approach rather than standardizing on a single provider. Skills addresses a real pain point: the "prompt engineering" problem where effective AI usage depends on individual employees crafting elaborate instructions for routine tasks, with no way to share that expertise across teams. Skills transforms implicit knowledge into explicit, shareable assets. For startups and developers, the feature could accelerate product development significantly -- adding sophisticated document generation capabilities that previously required dedicated engineering teams and weeks of development. The composability aspect hints at a future where organizations build libraries of specialized skills that can be mixed and matched for increasingly complex workflows. A pharmaceutical company might develop skills for regulatory compliance, clinical trial analysis, molecular modeling, and patient data privacy that work together seamlessly -- creating a customized AI assistant with deep domain expertise across multiple specialties. Anthropic indicates it's working on simplified skill creation workflows and enterprise-wide deployment capabilities to make it easier for organizations to distribute skills across large teams. As the feature rolls out to Anthropic's more than 300,000 business customers, the true test will be whether organizations find Skills substantively more useful than existing customization approaches. For now, Skills offers Anthropic's clearest articulation yet of its vision for AI agents: not generalists that try to do everything reasonably well, but intelligent systems that know when to access specialized expertise and can coordinate multiple domains of knowledge to accomplish complex tasks. If that vision catches on, the question won't be whether your company uses AI -- it will be whether your AI knows how your company actually works.

Anthropic's Claude gets new Skills system to help you work smarter

What's happened? Anthropic has just rolled out a major upgrade called 'Skills,' a new toolkit designed to enhance the capabilities and ease of customization of its AI assistant, Claude, for real-world applications. Skills are essentially folders containing instructions, scripts, and resources that teach Claude to handle specific tasks Each Skill acts like a 'preset' that gives Claude context before you even start typing. You can build your own custom Skills if you want the AI assistant to follow certain rules or workflows automatically. They'll be available across all versions of Claude, from the web app to the API and even the developer tools. This follows the launch of Anthropic's hybrid reasoning model, highlighting the company's steady push to make Claude more intelligent, adaptable, and ready for complex work. Recommended Videos This is important because: You no longer have to repeat instructions; teach Claude once, and it remembers. Thanks to Skills and Claude's powerful file tools, Anthropic's chatbot is turning into a teammate rather than just another chat window. Think of it as Claude finally learning the ropes -- your brand style, tools, and how you like things done. Breaking things into simple, reusable pieces helps teams save time and get more consistent results across prompts. It also powers scalability: once a Skill is built, many users or teams can reuse it, rather than reinventing from scratch. Compared to pure 'prompt engineering,' Skills represent a more structured, maintainable layer on top of AI. Why should I care? If you're a user, developer, or working in a team that uses AI, using Skills will make Claude smarter, faster, and tailored to what you actually need. You won't have to repeat the same prompts every day. Small teams can get big-company-level AI efficiency with minimal setup. Developers can use Skills to create smarter, reusable setups for their apps or clients. If you are a beginner, here's a guide on how to use Claude to get the most out of it.

Anthropic's Skills for Claude helps AI agents perform certain tasks better than before - SiliconANGLE

Anthropic's Skills for Claude helps AI agents perform certain tasks better than before Anthropic PBC wants to make artificial intelligence agents more effective when it comes to doing real work, and its latest idea is to provide them with additional "skills" that can help them when assigned a very specific task. The company announced Skills for Claude today, explaining that it's a tool that comes with various folders that include "instructions, scripts and resources for Claude" that can be loaded up when necessary. For instance, if Claude is told to create an Excel spreadsheet or a PowerPoint presentation, it can access a special skill for those tools and use them more effectively. Users will also be able to create their own Skills for Claude and make the large language model better able to perform specific work that might have to take into account things like brand guidelines, the company said. The Skills can be used with Claude.ai, Claude Code, the Claude Agent software development kit and the Anthropic application programming interface. In a deep dive blog post, Anthropic explained that Claude will only access the Skills when they're relevant to whatever task it has been instructed to perform. The Skills are meant to help it perform more specialized work using specific tools or guidelines, and will be ignored when not needed. In other words, they help make Claude "better" at doing something. The idea is that by giving Claude special Skills, users won't have to be so specific when it comes to prompting the agent, or refer to previous context each time they're trying to tell it what they need it to do. Anthropic said that Skills, which are available now to Pro, Team, Max and Enterprise subscribers, can be thought of as "custom onboarding materials that let you package expertise", so as to transform Claude into an expert at the tasks that matter most to users. Anthropic Product Lead Brad Abrams told The Verge in an interview that he loaded up Claude's PowerPoint skill and instructed it to create a presentation that shows how the company's Haiku 4.5 model is performing in the market compared to competing models. He said it created a number of "well-formatted slides that are easy to digest". Other kinds of Skills pertain to creating PDF files, Word files, canvas design, image editing and writing code in specific programming languages. The company hopes that Skills for Claude will help to make AI agents more powerful and useful, and encourage businesses to use them more often, so they ultimately become more reliant on them over time. It's a goal that's shared by other AI companies, including Google LLC and OpenAI, which are also focused on agentic AI productivity. OpenAI made a similar move recently with the launch of its AgentKit earlier this month, saying that it's a group of tools that will help enterprises "take agents from prototype to production". The company showed how the U.S. grocery chain Albertsons Companies Inc. was able to build a custom agent based on its corporate data that was able to develop a marketing plan to improve ice cream sales at its more than 2,000 stores.

These New AI Features Could Cut Hours of Work From Your Marketing and Presentations

In a blog post, Anthropic wrote that Claude can now use a feature called skills. These skills operate like a folder that contains instructions for how Claude should perform a specific task and any relevant resources needed to help it do that task. Here's how it works in practice, according to a video demo posted by Anthropic. Say you need to make marketing materials for a new video game you're working on. By uploading a .ZIP file containing brand guidelines for your game and text instructions for how Claude should convert those guidelines, you create a skill that Claude can call upon whenever it needs to make documents or art assets in your brand's style. Skills are also how Claude connects to external apps, such as Google Drive and Microsoft 365. When Claude needs to create a PowerPoint presentation, for example, it calls upon the PowerPoint skill. That skill gives Claude the information and guidance it needs to create working presentations.