@yoanbernabeu

grepai-storage-qdrant configures qdrant as a vector database backend for high-performance similarity search, with docker deployment, tls support, and cloud options for large codebases.

grepai-troubleshooting covers 13 common failure modes with diagnostic commands and config-based solutions, including indexing delays, connection failures, and search quality issues.

grepai-mcp-claude enables semantic code search and call graph analysis in claude code via model context protocol integration. covers setup, configuration, tool usage, and troubleshooting for single and multi-project workflows.

grepai-embeddings-openai configures openai as the embedding backend for grepai, supporting both small and large models with parallel request tuning, cost estimation, and migration paths from local alternatives.

grepai-trace-graph recursively maps function call dependencies up to configurable depth, supporting fast regex and precise ast modes. exports json, compact json, toon, and graphviz formats for architecture analysis and refactoring planning.

grepai-workspaces enables unified search and indexing across multiple related projects in monorepos and microservices. covers workspace creation, project management, multi-project search with per-project filtering, and mcp integration.

grepai-storage-postgres configures postgresql with pgvector as a shared vector storage backend for team environments and large codebases, covering docker setup, managed service options, ssl configuration, and performance tuning with ivfflat indexing.

grepai-storage-gob documents GOB binary serialization as GrepAI's default local storage backend, covering single-file indexing, performance characteristics up to 10K files, and migration paths to distributed backends.

grepai-embeddings-ollama configures local embedding generation via ollama for private code search. covers model selection, performance tuning, and troubleshooting with practical installation and configuration examples.

grepai-ollama-setup covers installing and configuring ollama as a local embedding provider, with platform-specific instructions for macos, linux, and windows plus model selection guidance and basic troubleshooting.

grepai-embeddings-lmstudio configures lm studio as a local embedding provider for grepai, with step-by-step setup, model selection guidance, and server verification. covers three embedding models and common failure scenarios.

grepai-trace-callees identifies all functions called by a specific function, supporting both fast and precise modes with json and toon output formats. useful for dependency mapping and code comprehension.

grepai-trace-callers locates all code locations that invoke a specific function, supporting 9+ languages with fast regex or precise ast-based modes. useful for refactoring impact analysis and codebase navigation.

supabase-audit-rls tests row level security policies for common misconfigurations and bypass vulnerabilities across tables. provides severity-tiered findings with sql remediation and evidence collection, though execution steps remain somewhat underspecified.

grepai-config-reference lists configuration options and file location but lacks actionable steps, validation logic, and guidance on actual option values or consequences.

grepai-chunking documents the purpose and context of code chunking in grepai but lacks concrete configuration steps, parameter details, or actionable procedures for users to optimize chunking behavior in practice.

grepai-watch-daemon covers daemon lifecycle and real-time code indexing setup, but lacks procedural detail and explicit failure handling needed for production use.

grepai-init covers running the init command to bootstrap grepai in a project, but lacks specifics on what configuration gets created, how to customize it, or what happens when init fails.

Tips and best practices for effective GrepAI searches. Use this skill to improve search result quality.

Configure search result boosting in GrepAI. Use this skill to prioritize certain paths and penalize others.

Multi-platform installation guide for GrepAI. Use this skill when installing GrepAI on macOS, Linux, or Windows.

Supported programming languages in GrepAI. Use this skill to understand which languages can be indexed and traced.

Integrate GrepAI with Cursor IDE via MCP. Use this skill to enable semantic code search in Cursor.

Get started with GrepAI in 5 minutes. Use this skill for a complete walkthrough from installation to first search.

grepai-ignore-patterns — an installable skill for AI agents, published by yoanbernabeu/grepai-skills.

Reference for all GrepAI MCP tools. Use this skill to understand available MCP tools and their parameters.

Advanced search options in GrepAI. Use this skill for JSON output, compact mode, and AI agent integration.

Basic semantic code search with GrepAI. Use this skill to learn fundamental search commands and concepts.