Anthropic this morning introduced Claude Skills, a new pattern for making new abilities available to their models: Claude can now use Skills to improve how it performs specific tasks. Skills …

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

Claude now remembers your team's projects and preferences across conversations. Memory helps maintain context for complex work, with project-specific boundaries and full user control over what's remembered.

Design, test, and distribute Agent Skills with reusable templates, collaborative reviews, and multi-surface deployment.

Build custom Skills to teach Claude specialized tasks. Create once, use everywhere—from spreadsheets to coding. Available across Claude.ai, API, and Code.