Unverified50% confidenceOpinionExact time
当 Skill 数量膨胀到一定程度，Skill 路由从简单的选择问题演变为检索问题
1
Sources
50%
Confidence
Long-term
Relevance
7/20/2026
First Seen
Sources
Related Claims
UnverifiedSkill的正确使用方式是渐进式优化：使用→发现问题→加规则→再测试，而非追求一次完美79% similarUnverifiedResearch shows that pure prompt optimization yields limited improvements on complex reasoning tasks, and that substantively breaking through capability ceilings requires the introduction of tool calling, chain-of-thought, memory mechanisms, and multi-agent division of labor.72% similarUnverifiedSkill分为能力型Skill和偏好型Skill，能力型随模型变强会被淘汰，偏好型更持久需要用评估保护防止性能倒退72% similarUnverifiedThe core challenge of reinforcement learning lies in the exploration-exploitation tradeoff, where agents need to find a balance between exploiting known effective strategies and exploring unknown possibilities.71% similarUnverifiedThe core challenge of 'knowledge + toolkit' products is that knowledge itself is difficult to form a competitive moat around, because tutorials and strategies can be imitated once made public.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/565213API
curl https://kongchang.com/api/v1/knowledge/claims/565213MCP
get_claim(id=565213)