Ripgrep

This lets Claude use ripgrep to search through codebases, documentation, and large files without loading everything into context. It's 10-100x faster than grep and respects gitignore by default. The skill covers the practical stuff: searching by file type, using regex patterns, multiline matching, and filtering output. Honest take: this is essential if you're working with large codebases or log files. Instead of Claude reading a 50MB file to find one function definition, it searches directly and shows just the matches. The documentation includes real patterns for finding imports, function definitions, and TODOs across different languages. If you've ever watched Claude burn tokens reading files just to grep them, you need this.