Unverified50% confidenceFactExact time
references 目录采用显式打包的结构化文档，与 RAG（检索增强生成）动态检索向量片段的思路一脉相承但方式不同
1
Sources
50%
Confidence
Long-term
Relevance
7/7/2026
First Seen
Sources
Agent Skills完全指南：原理、结构与实战应用拆解
bilibili学习的谁不疯7/5/2026
Related Claims
Unverifiedreferences 文件夹本质上是 RAG（检索增强生成）思想的一种静态化实现84% similarVerifiedThe core logic of RAG is to slice documents and store them as vectors, then retrieve relevant fragments through semantic similarity at query time and inject them into the context.70% similarVerifiedRAG通过将文档切分为语义块后经嵌入模型转化为高维向量存入向量数据库，查询时通过近似最近邻（ANN）搜索找到语义最相近的文档片段68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/183552API
curl https://kongchang.com/api/v1/knowledge/claims/183552MCP
get_claim(id=183552)