grepai-init

Initialize GrepAI configuration and directories in a project.

18|2|Updated Jan 28, 2026
One-click install
npx skills add https://github.com/yoanbernabeu/grepai-skills --skill grepai-init
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: grepai-init
Source: https://github.com/yoanbernabeu/grepai-skills/tree/main/skills/configuration/grepai-init
Command: npx skills add https://github.com/yoanbernabeu/grepai-skills --skill grepai-init

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Initializing GrepAI in a new project is tedious and error-prone. This skill automates the first-time setup, ensuring consistent configuration and ready-to-watch indexing.

Core Features & Use Cases

  • Creates a standard GrepAI layout: generates the .grepai/ directory with default config.yaml, index.gob, and symbols.gob.
  • Guides initial configuration: presets embedder, store, chunking, and trace settings for immediate use.
  • Supports monorepos and multi-project workspaces: simplifies setup across multiple packages and isolated indices.

Quick Start

Go to your project root and run grepai init Verify the new .grepai/config.yaml exists Start indexing with grepai watch

Frequently Asked Questions about grepai-init

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

FAQPage Schema
How do I initialize grepai configuration for a new project?

To initialize grepai, run `grepai init` in your project root to automatically generate the `.grepai` directory with default `config.yaml`, `index.gob`, and `symbols.gob` files for immediate indexing.

What is the default grepai setup process for monorepos and multi-project workspaces?

Grepai setup for monorepos involves running `grepai init` to create isolated `.grepai` directories and index files across multiple packages, ensuring separate configuration and indexing for each workspace.

Can I start indexing with grepai watch immediately after running the init command?

Yes, you can start indexing immediately after initialization. The init command presets embedder, store, chunking, watch, and trace defaults so you can run `grepai watch` without further configuration.

Does grepai init support custom configuration for embedder and chunking settings?

Grepai init generates a standard `config.yaml` with preset embedder, store, chunking, and trace settings. You can verify and modify these default configurations in the file after the initial setup.

Why do I need to create a .grepai directory for my project setup?

Creating a `.grepai` directory is necessary to store the `config.yaml` and `.gob` index files. This standard layout ensures consistent configuration and prevents errors during first-time setup and indexing.

What is the best way to automate first-time setup for grepai indexing?

The best way to automate first-time setup is using `grepai init`, which eliminates manual configuration errors by generating a standard layout with ready-to-watch indexing defaults.