Unverified60% confidenceFactExact time
In Semantic Kernel, a skill is essentially a callable function with a semantic description that a large model can automatically select and execute through a function-calling mechanism.
2
Sources
60%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
微软开源.NET Skills：让AI编程Agent精通C#开发
githubGitHub Trending7/5/2026
Related Claims
Unverified在LangChain、AutoGen、Semantic Kernel等主流Agent框架中，Skill或Tool被定义为封装特定功能的可调用单元，包含输入输出规范、功能描述和执行逻辑三要素78% similarUnverifiedCombining multiple related tools into semantically meaningful Skill modules allows Agents to select high-level semantic units rather than low-level function signatures during reasoning, reducing prompt engineering complexity and facilitating version management and access control.77% similarUnverifiedFunction Calling偏向执行单一动作，而Skill是包含完整工作流、判断逻辑和上下文知识的更高层次能力封装76% similarVerifiedThe essence of the Skill mechanism is to make implicit prompt knowledge explicit and versioned, so that it can be stored, shared, and iterated upon just like code.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/491080API
curl https://kongchang.com/api/v1/knowledge/claims/491080MCP
get_claim(id=491080)