Grepai Chunking

This walks you through configuring how GrepAI splits your code into chunks for embedding and search. The default is 512 tokens with 50 token overlap, which works fine for most codebases, but you might want smaller chunks (384) for precise results in concise languages like Rust, or larger chunks (768) for verbose Java where you need to capture entire methods. The guide explains the tradeoffs clearly: smaller chunks give you precision but lose context, larger chunks do the opposite, and overlap prevents you from losing important code at boundaries. Worth reading if your search results feel fragmented or noisy, since tweaking these numbers and re-indexing can make a real difference.

skills.sh installs: 729
GitHub stars: 20
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add yoanbernabeu/grepai-skills --skill grepai-chunking --agent claude-code

Installs into .claude/skills of the current project.

Files

GrepAI Chunking Configuration

This skill covers how GrepAI splits code files into chunks for embedding, and how to optimize chunking for your codebase.

When to Use This Skill

Optimizing search accuracy
Adjusting for code style (verbose vs. concise)
Troubleshooting search results
Understanding how indexing works

What is Chunking?

Chunking is the process of splitting source files into smaller segments for embedding:

┌─────────────────────────────────────┐
│         Large Source File           │
│         (1000+ tokens)              │
└─────────────────────────────────────┘
                  ↓
┌─────────┐ ┌─────────┐ ┌─────────┐
│ Chunk 1 │ │ Chunk 2 │ │ Chunk 3 │
│ ~512    │ │ ~512    │ │ ~512    │
│ tokens  │ │ tokens  │ │ tokens  │
└─────────┘ └─────────┘ └─────────┘
                  ↓
          Each chunk gets
          its own embedding