Unverified50% confidenceFactExact time
This paper formalizes the SFIA skill extraction task as a structured prediction problem: extracting (skill, level) pairs from free text.
1
Sources
50%
Confidence
Long-term
Relevance
9/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedModels are suited for four types of tasks: classification, extraction, summarization, and drafting (not sending), with the common thread being unstructured input and output that is judged by humans or fed into soft next steps.69% similarUnverifiedSFIA (Skills Framework for the Information Age) defines 147 professional skills and maps them to seven responsibility levels.68% similarUnverifiedSkills consist of two parts—Description and Content; the Description is unconditionally loaded into the context at the start of every conversation, while the Content is only expanded and read when the model decides to use that Skill.67% similarUnverifiedSkill由三层结构组成：概要层（约100字）、主体层（约3000字）和细节层，采用渐进式披露策略66% similarUnverified好的Skill文档应该包含触发条件、执行步骤、预期输出、异常处理方式四个要素66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/961178API
curl https://kongchang.com/api/v1/knowledge/claims/961178MCP
get_claim(id=961178)