Documentation/Jutsu/Crystal
🎯

Crystal

v1.9.0

Crystal language development skills and best practices.

jutsuskillhookcrystallanguage

Installation

Install han binary (required for hooks to work):

curl -fsSL https://han.guru/install.sh | bash

Then install this plugin:

han plugin install jutsu-crystal

Overview

Crystal language development skills and best practices.

Skills

This plugin provides the following skills:

  • Engineer

Usage

Once enabled, Claude will automatically apply these skills when working with relevant code. The plugin provides context and expertise that Claude uses to:

  • Write idiomatic code following best practices
  • Suggest appropriate patterns and architectures
  • Catch common mistakes and anti-patterns
  • Provide framework-specific guidance

Installation

Install with npx (no installation required):

han plugin install jutsu-crystal

License

Licensed under MIT - see repository for details.

Skills

📖

crystal-concurrency

Use when implementing concurrent programming in Crystal using fibers, channels, and parallel execution patterns for high-performance, non-blocking applications.

📖

crystal-engineer

Use when working with Crystal language development including WebSocket communication, TLS/SSL configuration, HTTP frameworks, ORM operations, and high-performance concurrent systems.

📖

crystal-macros

Use when implementing compile-time metaprogramming in Crystal using macros for code generation, DSLs, compile-time computation, and abstract syntax tree manipulation.

Hooks

⚠

Token Usage Notice

Hooks run automatically during Claude Code sessions and their output is sent to the model for processing. This may increase token usage and associated costs. Consider disabling hooks you don't need via han-config.yml.

🛑

Stop

Runs when the main Claude Code agent has finished responding. Can verify task completion, check quality gates, or ensure documentation requirements are met before the session ends.

🛑

SubagentStop

Runs when a Claude Code subagent (Task tool call) has finished responding. Can validate subagent outputs, enforce quality standards, or trigger additional workflows after delegated tasks complete.