Eugene Mymrin/Moment via Getty
Follow ZDNET: Add us as a preferred source on Google.
ZDNET’s key takeaways
- Anthropic announced Skills for Claude on Wednesday.
- Users are able to create their own, custom Skills.
- 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.”
How do they work?
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.
From generalists to specialists
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.
Safety considerations
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.”
