Unverified50% confidenceBenchmarkExact time
If the skill is designed so that the model reads the reference document through a tool, the token overhead is 1.7 to 2.8 times that of the streamlined skill.
1
Sources
50%
Confidence
Long-term
Relevance
11/6/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedSkills 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.71% similarUnverifiedA skill's description always occupies the context window and consumes tokens; the more skills there are, the less budget is available for the actual task on each request.70% similarUnverified当Skill数量超过模型Context Window的承载上限时，向量检索成为实现动态Skill发现的必要手段70% similarUnverifiedVersion 2.1.261 adds the /skill-doctor command, which can identify unused loaded skills and calculate their context costs.68% similarUnverified每一个可被自动调用的技能都会占用上下文窗口，技能越多，模型决策时需要处理的描述信息越多，增加token消耗并可能导致错误的调用判断68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1142423API
curl https://kongchang.com/api/v1/knowledge/claims/1142423MCP
get_claim(id=1142423)