Article complete

Anthropic Gives Claude New ‘Agent Skills’ to Master Real-World Tasks

Anthropic’s Agent Skills let developers give Claude task-specific expertise using structured files, scripts, and contextual knowledge.

Hands typing on a keyboard with abstract shapes in blue and white against an orange background.

Key takeaways

  • Introduce Agent Skills to enhance Claude's task-specific expertise using structured files and scripts.
  • Utilize SKILL.md files for metadata to activate specific skills based on context.
  • Enable code execution for computational tasks, improving accuracy and efficiency.
  • Adopt security best practices by auditing skills and installing only trusted resources.

Takeaways drafted with AI from the article text.

Agent Skills allow developers to package instructions, scripts, and resources into organised folders that Claude can load and interpret when needed. The system builds on the principle of progressive disclosure, letting the model read information incrementally, from metadata to detailed guides, without overloading its context window.

At the heart of each skill is a SKILL.md file containing YAML ‘frontmatter’ with metadata like name and description as the company describes. This helps Claude determine when to activate a specific skill. For example, a PDF skill can extend Claude’s native understanding of documents by adding the ability to fill forms or extract fields via bundled Python scripts.

Anthropic said the approach allows for “composable, scalable, and portable” capabilities, turning general-purpose models into specialised agents. By referencing additional files such as forms.md or reference.md, developers can create layered skill structures that Claude reads only when relevant to the task.

Agent Skills also support code execution, enabling Claude to run deterministic scripts for computational tasks instead of relying solely on token generation. This combination of structured context and executable tools helps ensure both accuracy and efficiency.

“Skills are a simple concept with a correspondingly simple format,” the company stated.

Anthropic emphasised security best practices, advising users to install only trusted skills and audit files for malicious dependencies.

The new feature is now available across Claude.ai, Claude Code, the Claude Agent SDK, and the Claude Developer Platform. Anthropic plans to expand capabilities in the coming weeks, allowing agents to eventually create, edit, and evaluate skills autonomously.

Published

Corrections: AIM corrects errors of fact and notes the change on the story. Spotted one? Tell the editors. Read our editorial standards.

More in this story

Anthropic · 5 stories
  1. Transformer Co-Author Niki Parmar Joins Anthropic After Founding Two AI Startups
  2. You are here: Anthropic Gives Claude New ‘Agent Skills’ to Master Real-World Tasks
  3. Accenture, Anthropic Launch Cyber.AI to Expedite Cybersecurity Operations
  4. TCS Eyes Deeper Ties with OpenAI, Anthropic, Mistral Beyond Traditional GTM
  5. Anthropic to Pay SpaceX $1.25 Bn Per Month, Hits $10.9 Bn Quarterly Revenue
About the author

Editor

I am a tech aficionado and a computer science graduate with a keen interest in AI, Coding, Open Source, Global SaaS, and Cloud. Have a tip? Reach out to

All stories
Belamy · Daily

The day’s AI news, before your first meeting.