Today’s agents are expected to remember everything, reason about everything, and do everything.
that’s like asking one engineer to also be the lawyer, accountant, doctor, and product manager.
skill function takes a different approach.
keep the agent lightweight.
move expertise into callable specialists with their own model, context, and reasoning.
agents shouldn’t know everything.
they should know who to ask.
https://t.co/SGDAsobiCW
Skills are coming to every platform. Microsoft in Excel. Google in Gemini Enterprise. But they’re all closed, locked to one vendor, one model, one ecosystem. Skill Function is the open infrastructure layer - callable from any agent, any model, any platform.
Own your intelligence.
Try it for free: https://t.co/OhGiFipUcL
MCP made tools callable.
Skill Function makes intelligence callable.
Every skill becomes an independently deployable AI service with its own model, context, permissions, lifecycle, and execution environment.
https://t.co/vxbP56sleK
Not every skill needs a flagship model. This is exactly why we built Skill Function. skill authors encode the right model into the skill itself. Paul spent hours optimizing for small models. That work shouldn’t be lost because a user’s agent overrides it with GPT-5.
👉🏼 https://t.co/SGDAsoaKNo
“works remarkably well with small models” is such specific great praise (thank you!) and something I spend a lot of time optimizing for, so it makes me quite happy to see it appreciated.
this is the usually unseen work that goes into impeccable. making a complicated flow like ‘critique’ or ‘live’ work with a model that doesn’t like to follow instructions is very challenging.
Introducing a new primitive in AI: Skill Function.
A Skill Function is a protected AI capability hosted as a callable endpoint. You send input. You get expert output. The instructions never leave the platform.
Not a file you download. A function you call.