skills.rest
floflo777
floflo777COMMUNITY
Explore all skills by this author →
GitHub

chunking-advisor

Analyze document characteristics and suggest chunking configurations for RAG pipelines.

33|3|Updated Jan 18, 2026
Search Tags:#RAG#chunking#document-processing#semantic-chunking#text-splitting#embedding-model
One-click install
npx skills add https://github.com/floflo777/claude-rag-skills --skill chunking-advisor
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: chunking-advisor
Source: https://github.com/floflo777/claude-rag-skills/tree/main/chunking-advisor
Command: npx skills add https://github.com/floflo777/claude-rag-skills --skill chunking-advisor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you design and select effective chunking strategies for RAG pipelines by analyzing document types, use cases, and embedding models.

Core Features & Use Cases

  • Content-type aware guidance: supports technical docs, legal texts, FAQs, tables, and long-form articles.
  • Use-case driven recommendations: for new pipelines, performance tuning, and model-specific constraints.
  • Quick-start example: Given a set of documents and an embedding model, receive a ready-to-use chunking plan with chunk size, overlap, and separators.

Quick Start

Invoke the /chunking-advisor command in a Claude Code session to receive a tailored chunking strategy for your documents.

Frequently Asked Questions about chunking-advisor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
What is the best chunking strategy for RAG pipelines?▼

The optimal RAG chunking strategy depends on your document type and embedding model. A tailored plan specifies exact chunk_size, chunk_overlap, separators, and metadata to preserve for maximum retrieval accuracy.

How do I determine the right chunk size and overlap for technical documents?▼

To determine chunk size and overlap for technical documents, analyze the content structure and embedding model constraints. You receive a ready-to-use configuration with specific separators and metadata fields to maintain context.

Can I use semantic chunking for legal contracts and long-form articles?▼

Yes, semantic chunking applies to legal contracts and long-form articles by analyzing document characteristics. It outputs concrete technical requirements including chunk_size, chunk_overlap, and separators to optimize retrieval performance.

How do I tune text splitting configuration when my RAG pipeline performance drops?▼

To tune text splitting for RAG performance drops, analyze your document types and embedding model constraints. You receive a revised chunking plan with adjusted chunk_size, chunk_overlap, and separators to improve retrieval accuracy.

Does chunking strategy need to change for different embedding models?▼

Yes, chunking strategy must adapt to different embedding models due to token limits and semantic representation differences. The configuration outputs chunk_size, chunk_overlap, and separators specifically aligned to your model's constraints.

Related Skills

Explore More Software Engineering Skills→
patricio0312revpatricio0312rev
5

doc-to-vector-dataset-generator

Convert documents into chunked JSONL datasets for embeddings.

Community
Advanced
ricardorochericardoroche
2

rag-design-patterns

Standardizes chunking, vector database integration, embedding management, and retrieval reranking for RAG pipelines.

Community
Intermediate
patricio0312revpatricio0312rev
5

embedding-pipeline-builder

Automate document embedding pipelines for semantic search.

Community
Advanced
latestaiagentslatestaiagents
5

chunking-strategies

Guide document chunking strategies for RAG systems with code examples.

Official
Intermediate