skills.rest
juanjaragavi
juanjaragaviCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

mgrep-code-search

Perform semantic search across large codebases using natural language queries.

Updated Dec 19, 2025
Search Tags:#codebase#search#nlp#semantic-search#code-search#watch#mgrep
One-click install
npx skills add https://github.com/juanjaragavi/topfinanzas-us-next --skill mgrep-code-search-juanjaragavi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mgrep-code-search
Source: https://github.com/juanjaragavi/topfinanzas-us-next/tree/main/.agents/skills/mgrep-code-search
Command: npx skills add https://github.com/juanjaragavi/topfinanzas-us-next --skill mgrep-code-search-juanjaragavi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Locating features, implementation details, and code discussions in large codebases can be time-consuming when using exact-match searches; semantic search with mgrep speeds up discovery across many files and nested directories.

Core Features & Use Cases

  • Semantic search across codebases using natural language queries to find concepts, features, and intent.
  • Indexing and watching workflows to keep an up-to-date search index while respecting ignore files.
  • Guidance on when to use semantic search versus traditional grep/ripgrep for precise pattern hits.

Quick Start

Index the repository with the watcher, then perform semantic searches using natural language queries.

Frequently Asked Questions about mgrep-code-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I perform semantic code search across a large codebase?▼

Semantic code search across large codebases is performed using natural language queries to locate features and implementation details. You index the repository with the mgrep watcher, then query with natural language to find concepts and intent efficiently.

What is the best way to find code intent and features without exact matches?▼

Semantic search is the best way to find code intent and features without exact matches, using natural language queries to discover concepts across many non-gitignored files. It speeds up discovery in nested directories where traditional pattern matching fails.

Can I use semantic search for repositories with many nested directories?▼

Yes, semantic search targets codebases with many non-gitignored files and nested directories. It relies on the mgrep watcher for indexing and respects .gitignore and .mgrepignore patterns to efficiently search through large repository structures.

When should I use semantic search versus traditional grep or ripgrep?▼

Use semantic search for locating features, intent, and implementation details using natural language, and use traditional grep or ripgrep for precise pattern hits. The Skill provides guidance on when to use each approach for optimal codebase search results.

How does the mgrep watcher keep the search index up to date?▼

The mgrep watcher keeps the search index up to date by continuously indexing the repository while respecting ignore files. This indexing and watching workflow ensures semantic search queries run against the latest codebase state efficiently.

Related Skills

Explore More Software Engineering Skills→
tmcfarlanetmcfarlane
105

mgrep-code-search

Indexes large repositories and performs semantic searches across codebases using natural language queries.

Community
Intermediate
masrurimzmasrurimz

explorer

Locate code implementations and trace usage with semantic search, grep, and glob.

Community
Basic
jungmini0601jungmini0601

mgrep-code-search

Index and search code repositories for semantic content matching natural language queries.

Community
Intermediate
massgenmassgen
1.1k

file-search

Locate text and structural code patterns across large codebases using ripgrep and ast-grep.

Official
Basic