Unverified50% confidenceOpinionExact time
The creator "坤鹏talk" points out that after long-term use of an Agent, more than 90% of Skills will never be used beyond the first time.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/25/2026
First Seen
Valid until: 11/8/2026
Sources
Related Entities
Related Claims
UnverifiedA skill-enabled vs. skill-disabled comparison Eval can be used to measure whether a skill is worth occupying context window space; if the baseline accuracy already exceeds 90%, adding a skill may yield minimal gains or even mislead the model.65% similarUnverified一个90%成功、10%出错的工具调用系统几乎无法投入实际使用，只有可靠性跨过某个阈值AI才从玩具变成工具64% similarUnverifiedCharter's author believes that for 99% of use cases, an agent harness is a smarter and higher-performing choice than building workflows from scratch.62% similarUnverifiedThe UP host believes that more than 90% of Agent tutorials suffer from one of two extremes: discussing only concepts without practical implementation, or directly dumping code without explaining the problem.61% similarUnverifiedWithout hook injection, even if the Skill files are in place, the Agent will not actively call them.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1095743API
curl https://kongchang.com/api/v1/knowledge/claims/1095743MCP
get_claim(id=1095743)