One-click install
npx skills add https://github.com/hongbietcode/synthetic-claude --skill repomix-hongbietcode
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: repomix
Source: https://github.com/hongbietcode/synthetic-claude/tree/main/plugins/basic-workflow/skills/repomix
Command: npx skills add https://github.com/hongbietcode/synthetic-claude --skill repomix-hongbietcode

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Repomix packages entire code repositories into AI-friendly single files, enabling efficient analysis by large language models while preserving context and structure across large codebases.

Core Features & Use Cases

  • AI-optimized repository packaging with clear separators and metadata
  • Multiple output formats: XML, Markdown, JSON, Plain Text
  • Token counting for AI context management and efficiency
  • Preserve file structure and context with configurable include/exclude patterns
  • Use cases include feeding codebases to LLMs, creating repository snapshots for context, security audits, and documentation generation

Quick Start

Check Installation: repomix --version Install: npm install -g repomix Basic Usage: repomix Basic Usage (style): repomix --style markdown Remote packaging: npx repomix --remote owner/repo Custom output: repomix --include "src/**/*.ts" --remove-comments -o output.md

Frequently Asked Questions about repomix

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

FAQPage Schema
How do I package a codebase into a single file for LLM context?

Packaging a codebase for LLM context involves aggregating repository files into an AI-friendly snapshot using configurable include/exclude patterns. This preserves file structure and metadata, enabling efficient large language model analysis without losing context.

Can I package remote repositories for AI analysis without cloning them locally?

Yes, remote repositories can be packaged directly for AI analysis using the remote packaging feature. By specifying the owner/repo identifier, the tool fetches and consolidates the codebase into an AI-friendly snapshot without requiring a local clone.

What output formats are available when creating repository snapshots for AI?

Repository snapshots for AI can be generated in multiple output formats including XML, Markdown, JSON, and Plain Text. These formats ensure compatibility with various large language models while maintaining clear separators and structural metadata.

Does repomix support token counting for AI context management?

Yes, repomix includes token counting functionality for AI context management. This feature helps track the token size of the packaged codebase, ensuring the generated snapshot fits within the context window limits of target LLMs.

How do I run security audits on a codebase using an AI-friendly snapshot?

Security audits use the packaged codebase snapshot to feed repository code into LLMs for vulnerability analysis. By consolidating the files with optional security checks enabled, the AI can review the complete structural context to identify potential issues.

What is the best way to generate documentation from a large codebase using LLMs?

Generating documentation from a large codebase using LLMs requires packaging the repository into a consolidated, AI-friendly format with preserved file structure. This snapshot provides the comprehensive context the LLM needs to accurately map architecture and generate docs.