GeistHaus
log in · sign up

Introducing Agent Skills | Claude

claude.com

Claude can now use Skills to improve how it performs specific tasks. Skills are folders that include instructions, scripts, and resources that Claude can load when needed. Claude will only access a skill when it's relevant to the task at hand.

20 pages link to this URL
Paolo’s Weblog | Paolo Valdemarin's blog - since 2002

Paolo Valdemarin’s blog, since 2002. An Italian living in London, blogging about life on the internet, cats, food, and any other thing that comes to mind.

0 inbound links website en AI-promptingAI AgentsArtificial IntelligencetechnologyFuture of WorkSoftware DevelopmentVisionProhistorylifecoronavirusmindNew Normalfoodquarantinemarketing ClaudeAIprogressstrategySkillschatGPTactivate-intelligenceaipcommunicationinstitutional-knowledgeknowledge-managementllmmcpproductivityteamworktranslationAI collaborationOpenAIartificial intelligencecodingeducationjunior developerstech careerssemantic searchautomationbloggingwordpressOcadoactivate intelligenceapplemactechnologygraphic designGPTPhotography
The AI App Experience Matters More Than Benchmarks Now

I was catching up on different articles after the release of Claude Opus 4.5 earlier this week, and this part from Simon Willison’s blog post about it stood out to me: I’m not saying the new model isn’t an improvement on Sonnet 4.5—but I can’t say with confidence that the challenges I posed it were

1 inbound link article en notes AIartificial intelligencefeaturedLLMs
The AI App Experience Matters More Than Benchmarks Now

I was catching up on different articles after the release of Claude Opus 4.5 earlier this week, and this part from Simon Willison’s blog post about it stood out to me: I’m not saying the new model isn’t an improvement on Sonnet 4.5—but I can’t say with confidence that the challenges I posed it were

1 inbound link article en notes AIartificial intelligencefeaturedLLMs
Introducing Labs

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

5 inbound links website en
Paolo’s Weblog | Playing with Claude skills

Using skills we can capture *why* software components are built, not just the *how*, giving developers better context when working with unfamiliar code. This isn’t about replacing developers,…

0 inbound links article en AIAI AgentsArtificial Intelligenceprompting AIClaudeSkills
Optimize for Humans | Tom Bedor's Blog

I recently wrote about optimizing repos for AI, and since then I've been maintaining separate docs for humans (README, contributing guides) and AI agents (.cursorrules, CLAUDE.md, etc.). The problem? I keep writing the same information twice.

0 inbound links article en
Hacker News