skills.rest
eduardtomasek
eduardtomasekCOMMUNITY
Explore all skills by this author →
GitHub

grepai-quickstart

Guides installation, indexing, and semantic code search setup with GrepAI and Ollama.

Updated May 12, 2026
Search Tags:#semantic search#embeddings#code search#quickstart#call graph#ollama#grepai
One-click install
npx skills add https://github.com/eduardtomasek/codex-dev-stack --skill grepai-quickstart-eduardtomasek
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: grepai-quickstart
Source: https://github.com/eduardtomasek/codex-dev-stack/tree/main/skills/.agents/grepai-quickstart
Command: npx skills add https://github.com/eduardtomasek/codex-dev-stack --skill grepai-quickstart-eduardtomasek

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Setting up semantic code search requires installing multiple tools, configuring an embedding provider, and indexing a project, which is confusing for first-time users. This Skill walks through the entire GrepAI setup from installation to first search in about 5 minutes. ## Core Features & Use Cases - Step-by-step installation: Covers GrepAI and Ollama installation on macOS, Linux, and Windows with verification commands. - Project indexing workflow: Explains grepai init, watch daemon modes (foreground and background), and what happens during chunking and embedding. - Search and call tracing: Demonstrates semantic search with filters and JSON output, plus caller/callee tracing for function dependency analysis. - Use Case: A developer joins a new codebase and needs to find where authentication is handled. After following this quickstart, they run grepai search "authentication flow" and immediately get ranked code snippets with file locations. ## Quick Start Ask the assistant to walk you through installing GrepAI and Ollama, initializing your project, and running your first semantic code search.

Frequently Asked Questions about grepai-quickstart

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

FAQPage Schema
How do I set up GrepAI for semantic code search?▼

Install GrepAI via brew or the install script, install Ollama and pull the nomic-embed-text model, then run grepai init in your project and start indexing with grepai watch. Once indexing completes, use grepai search with a descriptive query.

How to run GrepAI indexing in the background?▼

Use grepai watch --background to run the indexing daemon in the background for long-running projects. Check its state with grepai watch --status and stop it with grepai watch --stop.

Does GrepAI require an external embedding API?▼

No, GrepAI can run embeddings locally through Ollama using the nomic-embed-text model, which is the default configuration created by grepai init. This keeps your code embeddings on your own machine.

How do I trace function callers with GrepAI?▼

Use grepai trace callers "FunctionName" to find what calls a function, or grepai trace callees to see what it calls. For a full dependency view, run grepai trace graph with a depth parameter.

Why does my GrepAI search return poor results?▼

Search quality depends on descriptive queries rather than literal keywords. Use phrases like "user authentication and session management" instead of "auth", describe intent in English, and confirm indexing completed with grepai status.

Related Skills

Explore More Software Engineering Skills→
yoanbernabeuyoanbernabeu
18

grepai-ollama-setup

Configure Ollama for private local embeddings in GrepAI.

Community
Advanced
yoanbernabeuyoanbernabeu
18

grepai-mcp-claude

Access GrepAI semantic code search and call graph analysis through MCP in Claude Code.

Community
Advanced
tao3ktao3k
15

code_tools

Search code repositories by structure, semantics, or exact text.

Official
Advanced
scooter-lacroixscooter-lacroix
8

search-router

Route search queries to TLDR Search, AST-grep, or Grep based on query type.

Community
Intermediate