Unverified60% confidenceFactTime unknown
The definition description of each Skill is injected into the context upon activation; even if that Skill is not used in the current task, its description text still occupies token space
2
Sources
60%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe core approach to improving the distinctiveness of Skill descriptions is to write not 'what this Skill is' but 'when to use it'; Anthropic officially emphasizes that the description should include trigger scenarios.79% similarUnverifiedEven when Skills are not invoked, simply listing them in the available tools list consumes token space in the context window in the form of Tool Definitions.78% 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.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/13936API
curl https://kongchang.com/api/v1/knowledge/claims/13936MCP
get_claim(id=13936)