Unverified50% confidenceFactExact time
The Skills mechanism significantly reduces context occupancy and lowers token overhead by precisely injecting domain knowledge rather than piling up large amounts of background descriptions.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/3/2026
First Seen
Valid until: 12/2/2026
Sources
Related Entities
Related Claims
Unverified当技能描述过于详尽包含了完成任务所需的全部信息时，模型会跳过技能调用环节74% similarVerifiedResearch 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.73% similarUnverifiedOnce incorrect experience learned by an agent from limited interactions becomes entrenched, it can lead to systemic bias and reduced work efficiency.70% 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70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/848669API
curl https://kongchang.com/api/v1/knowledge/claims/848669MCP
get_claim(id=848669)