yoanbernabeu/grepai-skills▌

This skill covers using Qdrant as the storage backend for GrepAI, offering high-performance vector search.

This skill provides a complete walkthrough to get GrepAI running and searching your code in 5 minutes.

This skill covers using LM Studio as the embedding provider for GrepAI, offering a user-friendly GUI for managing local models.

This skill covers using GrepAI workspaces to manage multiple related projects with a unified search index.

This skill provides a complete reference for all tools available through GrepAI's MCP server.

Semantic code search by meaning rather than exact text strings. \n \n Searches code by intent and concept similarity using embeddings, returning ranked results with relevance scores (0.0–1.0) \n Requires GrepAI initialization, an active index created via grepai watch , and a running embedding provider like Ollama \n Supports natural language queries describing behavior or intent; 3–7 word phrases work best, with results limited via --limit flag \n Interprets scores: 0.90+ excellent match, 0.80–0

This skill covers using PostgreSQL with the pgvector extension as the storage backend for GrepAI.

This skill covers using OpenAI's embedding API with GrepAI for high-quality, cloud-based embeddings.

This skill covers integrating GrepAI with Cursor IDE using the Model Context Protocol (MCP).

This skill covers all methods to install GrepAI on any platform.

This skill covers integrating GrepAI with Claude Code using the Model Context Protocol (MCP).

This skill covers using GOB (Go Binary) as the storage backend for GrepAI, the default and simplest option.

This skill covers how to configure ignore patterns to exclude files and directories from GrepAI indexing.

This skill covers using Ollama as the embedding provider for GrepAI, enabling 100% private, local code search.

This skill covers the grepai init command and project initialization.

This skill covers the programming languages supported by GrepAI for indexing and call graph analysis.

This skill covers using grepai trace graph to build complete call graphs showing all dependencies recursively.

This skill covers configuring score boosting to prioritize relevant code paths and deprioritize tests, docs, and vendor code.

This skill covers using grepai trace callees to find all functions called by a specific function.

Structured code search with JSON, TOON, and compact output formats optimized for AI agents. \n \n Supports three output formats: standard JSON, compact JSON (80% fewer tokens), and TOON notation (50% more compact than JSON) \n Includes --limit , --json , --toon , and --compact command-line options for controlling result volume and token usage \n Integrates with MCP servers and AI agents (Claude, GPT) through format selection parameters \n Works with scripting tools (jq, Python, Node.js) and supp

This skill covers using grepai trace callers to find all code locations that call a specific function or method.

This skill covers the grepai watch command and daemon management for real-time code indexing.

This skill covers installing and configuring Ollama as the local embedding provider for GrepAI. Ollama enables 100% private code search where your code never leaves your machine.

This skill provides a complete reference for all GrepAI configuration options in .grepai/config.yaml.

This skill provides solutions for common GrepAI issues and diagnostic procedures.

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

This skill provides tips and best practices for writing effective semantic search queries.