Unverified50% confidenceSolutionExact time
In each Agent loop, the system loads only the Front Matter (name and description) of all skills into the context, and only loads the corresponding Body after the required skill has been identified.
1
Sources
50%
Confidence
Long-term
Relevance
10/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Skill mechanism uses on-demand loading: it first sends the metadata of all Skills to the large model, and after the large model selects the matching Skill, the full instructions are loaded.76% similarUnverified技能库采用懒加载设计，Agent Harness 只需解析 Front Matter 即可判断是否激活某个技能，从而规模化扩展而不显著增加 token 消耗74% 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.72% similarUnverifiedThe Skill mechanism guides the model to complete specific tasks by injecting structured Markdown instructions into the context, without requiring fine-tuning of the model itself.71% similarUnverifiedThe solution of the Skills mechanism is to decompose complex tasks into three stages: requirement decomposition, test point extraction, and test case generation, with each operation corresponding to one Skill.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/991338API
curl https://kongchang.com/api/v1/knowledge/claims/991338MCP
get_claim(id=991338)