a5c-ai/babysitter / library/specializations/ai-agents-conversational/skills/rag-chunking-strategy
rag-chunking-strategy
VerifiedDocument chunking with multiple strategies including semantic, recursive, and fixed-size chunking
RAG Chunking Strategy Skill
Capabilities
- Implement multiple document chunking strategies
- Configure semantic chunking based on content boundaries
- Set up recursive character text splitting
- Design fixed-size chunking with overlap
- Implement document-aware chunking (markdown, code, etc.)
- Optimize chunk sizes for retrieval quality
Target Processes
- rag-pipeline-implementation
- chunking-strategy-design
Implementation Details
Chunking Strategies
- RecursiveCharacterTextSplitter: Hierarchical splitting with separators
- SemanticChunker: Embedding-based semantic boundaries
- TokenTextSplitter: Token-aware splitting
- MarkdownHeaderTextSplitter: Structure-aware markdown splitting
- CodeSplitter: Language-aware code chunking
Configuration Options
- Chunk size (characters or tokens)
- Chunk overlap percentage
- Separator hierarchy
- Embedding model for semantic chunking
- Document type detection
Best Practices
- Match chunk size to embedding model limits
- Use appropriate overlap for context preservation
- Test retrieval quality with different strategies
- Consider document structure in strategy selection
Dependencies
- langchain-text-splitters
- sentence-transformers (for semantic chunking)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |