Chunking Strategy

This handles the RAG chunking problem systematically, walking you through five strategy levels from basic fixed-size splits to semantic boundary detection with embedding similarity. It includes validation commands you can actually run to check coherence scores and retrieval precision, plus concrete parameter recommendations like starting at 512 tokens with 15% overlap. The iterative tuning guidance is solid: if precision drops below 0.7, reduce chunk size by 25%. What's useful here is the decision tree for matching strategies to document types, whether you're processing unstructured text, code with AST parsing, or complex documents with thematic shifts. It won't magically solve retrieval quality issues, but it gives you a methodical framework instead of guessing at chunk sizes.

skills.sh installs: 4K
GitHub stars: 369
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add giuseppe-trisciuoglio/developer-kit --skill chunking-strategy --agent claude-code

Installs into .claude/skills of the current project.

Files

Chunking Strategy for RAG Systems

Overview

Provides chunking strategies for RAG systems, vector databases, and document processing. Recommends chunk sizes, overlap percentages, and boundary detection methods; validates semantic coherence; evaluates retrieval metrics.

When to Use

Use when building or optimizing RAG systems, vector search pipelines, document chunking workflows, or performance-tuning existing systems with poor retrieval quality.

Instructions

Choose Chunking Strategy

Select based on document type and use case:

Fixed-Size Chunking (Level 1)
- Use for simple documents without clear structure
- Start with 512 tokens and 10-20% overlap
- Adjust: 256 for factoid queries, 1024 for analytical
Recursive Character Chunking (Level 2)
- Use for documents with structural boundaries
- Hierarchical separators: paragraphs → sentences → words
- Customize for document types (HTML, Markdown, JSON)
Structure-Aware Chunking (Level 3)
- Use for structured content (Markdown, code, tables, PDFs)
- Preserve semantic units: functions, sections, table blocks
- Validate structure preservation post-split