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.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.
9
skills.sh installs
416
GitHub stars
58
last updated
Aug 21, 2026

Install

$ npx -y skills add ratacat/claude-skills --skill ripgrep --agent claude-code

Installs into .claude/skills of the current project.

Files

Ripgrep (rg) - Fast Text Search Tool

Overview

Ripgrep is a line-oriented search tool that recursively searches directories for regex patterns. It's 10-100x faster than grep and respects .gitignore by default. Use it instead of grep, find, or manually reading large files.

Core principle: When you need to find text in files, use ripgrep. Don't read entire files into context when you can search them.

When to Use

Use ripgrep when:

  • Searching for text patterns across a codebase or directory
  • Finding all occurrences of a function, variable, or string
  • Searching through books, documentation, or large text files
  • Files are too large to read fully into context
  • Looking for specific content in many files at once
  • Finding files that contain (or don't contain) certain patterns
  • Extracting matching lines for analysis

Don't use when:

  • You need the full file content (use Read tool)
  • Simple glob pattern matching for filenames only (use Glob tool)
  • You need structured data extraction (consider jq, awk)

Quick Reference

Sponsors

Details

Repository
github.com/ratacat/claude-skills
First seen
Jun 3, 2026

More from ratacat/claude-skills

All 3

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs