skills.rest
aitchwhy
aitchwhyCOMMUNITY
Explore all skills by this author →
GitHub

repomix

Pack codebases into compressed XML, Markdown, JSON, or plain output.

Updated Aug 27, 2026
Search Tags:#MCP#repomix#token-optimization#skill-generation#pack_codebase#codepack
One-click install
npx skills add https://github.com/aitchwhy/dotfiles --skill repomix-aitchwhy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: repomix
Source: https://github.com/aitchwhy/dotfiles/tree/main/config/agents/skills/repomix
Command: npx skills add https://github.com/aitchwhy/dotfiles --skill repomix-aitchwhy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps prepare and compress codebases for AI analysis, enabling efficient understanding and generation of Claude skills.

Core Features & Use Cases

  • Pack local directories for AI-ready output.
  • Generate skills from codebases; optimize token usage with compression strategies.
  • Include targeted files; read and search outputs with MCP patterns.

Quick Start

Pack the current directory with: repomix --style xml --compress

Frequently Asked Questions about repomix

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

FAQPage Schema
How do I prepare a codebase for AI analysis without exceeding token limits?▼

Pack codebases into compressed, AI-analyzable output using repomix to optimize token usage. The tool compresses code, applies include/ignore patterns, and outputs in multiple formats (XML, markdown, JSON, plain) so Claude can analyze large modules efficiently while preserving essential context.

Can I pack a remote repository alongside local directories for code review preparation?▼

Yes. Repomix supports packing both local directories and remote repositories together, enabling you to prepare complete codebases for AI-driven code reviews and refactoring analysis in a single optimized output.

What output formats does repomix use when packing code?▼

Repomix outputs packed codebases in four styles: XML, markdown, JSON, and plain text. Choose the format that best suits your AI analysis workflow and downstream skill generation needs.

How do I generate a skill from a codebase using repomix?▼

Pack your codebase with repomix using targeted file patterns and compression, then use the optimized output to generate reference skills. The tool reduces token overhead so Claude can understand and generate skills from large codebases.

When should I use compression in repomix instead of unpacked output?▼

Use compression when analyzing large modules or preparing codebases for token-constrained AI workflows. Compression reduces output size while retaining structure, making it ideal for understanding new codebases and generating skills efficiently.

Can I selectively include or exclude files when packing a codebase?▼

Yes. Repomix supports includePatterns and ignorePatterns to target specific files during packing, letting you focus AI analysis on relevant code and reduce token usage by excluding build artifacts, tests, or dependencies.

Related Skills

Explore More Software Engineering Skills→
CastrozanCastrozan
3

repomix

Pack codebases into token-aware single files for LLM context.

Community
Intermediate
pradyumnasagarpradyumnasagar
6

agent-handoff

Automate inter-skill data transfer and provenance capture via JSON Material Passports.

Community
Advanced
outfitter-devoutfitter-dev
28

claude-config-management

Configure Claude Desktop and Claude Code settings, MCP servers, and environment variables.

Official
Intermediate
oaustegardoaustegard
137

mapping-codebases

Generate hierarchical navigation maps of codebases using tree-sitter analysis.

Community
Intermediate