Claude Kit

The open-source AI dev toolkit for Claude Code. Ship faster with 27+ commands, 7 modes, and 34+ skills. Free forever.

Ship Faster. For Free.

Claude Kit transforms Claude Code into a production-ready AI development team. Pre-built commands, intelligent modes, and battle-tested skills — all open source.

27+ Commands

From /feature to /ship, automate your entire development workflow with battle-tested commands.

7 Modes

Switch between brainstorm, implementation, review, and more. Each mode optimizes Claude’s behavior for your task.

34+ Skills

Pre-built knowledge for Python, TypeScript, React, FastAPI, testing, security, and more.

5 MCP Servers

Real-time docs, persistent memory, browser testing, and more via Model Context Protocol.

Quick Start

Get up and running in under 2 minutes:

# Clone the repository
git clone https://github.com/duthaho/claudekit.git

# Copy the kit to your project
cp -r claudekit/.claude your-project/

# Start using commands
cd your-project
claude
> /feature "add user authentication"

Why Claude Kit?

The Problem

Working with Claude Code is powerful, but raw Claude has limitations:

Context Spirals — Token budgets run out, context gets lost mid-task
Inconsistent Output — Quality varies between sessions
Manual Workflows — Same prompts copied between projects
No Structure — Every session starts from scratch

The Solution

Claude Kit provides the structure, patterns, and automation that makes Claude Code production-ready:

Structured Workflows

Commands like /feature orchestrate multi-phase development: planning → implementation → testing → review → ship.

Context Control

Modes and skills give Claude the exact context it needs. No more explaining your stack every session.

Consistent Quality

Built-in code review, testing standards, and security checks ensure every output meets your standards.

Fully Customizable

Add your own commands, modes, and skills. Claude Kit is a template, not a black box.

Featured Commands

/feature End-to-end feature development: plan, implement, test, review, ship.

/fix Smart debugging: analyze errors, find root cause, implement fix, add regression test.

/review Comprehensive code review: quality, security, performance, maintainability.

/ship Git automation: commit, create PR, ready for merge.

View all commands →

Modes for Every Task

Mode	Best For	Description
Default	General tasks	Balanced behavior
Brainstorm	Design, ideation	Explores alternatives, asks questions
Token-Efficient	High-volume work	Compressed output, 30-70% savings
Implementation	Coding	Jump straight to code
Review	Quality checks	Critical analysis, finds issues
Deep Research	Investigation	Thorough analysis with citations

Learn about modes →

Ready to Ship Faster?

Installation Guide Step-by-step setup for your project

Command Reference Complete documentation for all 27+ commands

MCP Integrations Extend Claude Kit with real-time docs, memory, and browser testing

Customization Create your own commands, modes, and skills