vector-search-workflows_skill

Overview

This skill provides end-to-end workflows for indexing and querying codebases with MCP Vector Search. It guides setup, MCP integration, and strategies for maintaining fresh semantic indexes using ChromaDB and embeddings. The goal is reliable semantic search across repositories with automated reindexing options.

How this skill works

The skill initializes configuration, detects languages and file types, and builds an embedding-based index stored in ChromaDB. It supports one-off indexing, targeted reindexing, and an auto-index system that watches for changes and triggers reindexes. MCP integration is handled via native MCP commands when available or by adding a .mcp.json entry to enable the vector search service inside an MCP toolchain.

When to use it

• Enable semantic search across a codebase for faster discovery of implementation patterns and examples.
• After major refactors, dependency updates, or language additions that require a refreshed index.
• When integrating vector search into an MCP-driven local developer workflow or toolchain.
• To automate continuous indexing for active repositories where files change frequently.
• During development when testing different index configurations or embedding models.

Best practices

• Run setup once per repository to detect languages, initialize config, and create the initial index.
• Use --force for index and setup commands after tool upgrades or breaking parser changes.
• Enable file watching (MCP_ENABLE_FILE_WATCHING=true) for low-latency auto-indexing in active projects.
• Limit auto-reindex checks with --max-files or scoped paths to avoid excessive processing on large repos.
• Keep MCP integration consistent: prefer native claude mcp add when available, otherwise maintain a .mcp.json entry.

Example use cases

• Search for authentication logic across multiple services to consolidate or refactor security code.
• Reindex only modified files after a pull request to keep semantic search current without full rebuilds.
• Set up auto-indexing in a CI environment to trigger reindexes when dependencies or parsers change.
• Use status and doctor commands to validate index health and troubleshoot embedding or storage issues.
• Add the vector-search MCP server to a local toolchain to share search capabilities across developer tools.