Verified70% confidenceFactTime unknown
Agent Skill adopts a lazy-loading mechanism whereby the Agent first reads only the metadata (name and description) of each Skill and loads the full instructions only after matching the user's need, so having multiple Skills coexisting does not increase Token consumption
4
Sources
70%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIn Agent Skills, when one Agent has multiple Skills mounted, the system performs automatic mapping from user intent to Skill through semantic similarity computation (cosine similarity based on embedding vectors).83% similarVerifiedSkill is a plugin mechanism for registering new callable tools with an Agent, allowing on-demand expansion of Agent capabilities without modifying the model itself.83% similarUnverified模型调用技能带有一段description，会进入Agent的上下文中，Agent可自行判断是否调用该技能80% similarVerifiedAgent Skills adopts a progressive loading mechanism that loads relevant sections on demand based on the current task, avoiding the context explosion problem.79% similarVerifiedAgent Skills adopts a vertical capability scaling approach within a single agent, which is more lightweight and easier to debug than Multi-Agent approaches.79% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/14897API
curl https://kongchang.com/api/v1/knowledge/claims/14897MCP
get_claim(id=14897)