菜单
Route RAG handling for code documentation, APIs, images, tables, diagrams, and multimodal content.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use this skill when building, debugging, or improving Retrieval-Augmented Generation systems, including chunking, vector database selection, hybrid search, reranking, multimodal RAG, code documentation RAG, retrieval latency, and production RAG architecture.
Chunk nested documents into parent-child levels so retrieval can move from broad sections to fine-grained passages.
Use semantic boundaries and embedding similarity to chunk text for higher-relevance retrieval.
Route RAG chunking decisions across semantic, hierarchical, sliding-window, contextual-header, and framework-selection strategies.
Use overlapping windows to preserve context across chunk boundaries while controlling retrieval size.
Reduce retrieval latency with caching, batching, and index-level optimization.
| name | data-type-handling |
| title | Data Type Handling |
| description | Route RAG handling for code documentation, APIs, images, tables, diagrams, and multimodal content. |
| category | data-type-handling |
| tags | ["data-types","code","multimodal","rag"] |
| allowed-tools | ["Read","Grep","Glob"] |
Use this parent skill when source material is not plain prose or when different data types need different parsing, metadata, chunking, and retrieval strategies.
Code, APIs, tables, images, diagrams, and mixed media lose important meaning when treated as generic text. RAG systems need data-specific handling to preserve symbols, structure, and visual context.
Identify whether the corpus is code-heavy, image-heavy, table-heavy, or mixed.
Use parsers and metadata that retain symbols, captions, headers, page numbers, and source locations.
Index text, summaries, captions, code symbols, table schemas, or multimodal embeddings as appropriate.
