tw93/waza

★ 4,734ShellAudience · developerComplexity · 2/5LicenseSetup · easy

Mindmap

mindmap
  root((waza))
    Skills
      think planning
      design UI
      check review
      hunt debug
    More skills
      write prose
      learn research
      read web content
      health config audit
    Workflow patterns
      Plan then build
      Build then check
      Debug with hunt
    Distribution
      npx install
      Claude Desktop ZIP

mindmap root((waza)) Skills think planning design UI check review hunt debug More skills write prose learn research read web content health config audit Workflow patterns Plan then build Build then check Debug with hunt Distribution npx install Claude Desktop ZIP

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Run /think before a feature to get AI-challenged requirements and a decision-ready implementation plan.

USE CASE 2

Use /check on your diff before merging to get a focused AI code review of only your changes.

USE CASE 3

Use /hunt when stuck on a bug to get a systematic root-cause walkthrough before touching any code.

USE CASE 4

Run /design during frontend work to get a committed visual direction generated inside your editor.

Tech stack

ShellNode.js

Getting it running

Difficulty · easy Time to first run · 5min

Requires Claude Code or Codex to be installed, skills install globally via one npx command.

Use freely for any purpose including commercial use under the MIT license.

In plain English

Waza is a collection of eight skills for Claude Code (Anthropic's AI coding assistant) that encode common software engineering habits as slash commands you can invoke during your work. The name comes from a Japanese martial arts term for a practiced technique: something drilled until it becomes instinct. The idea is that good engineering involves more than writing code, and that an AI assistant can handle each part of the workflow if given the right structure. The eight skills each target a different moment in the development process. Before building something new, /think challenges the requirements and produces a decision-ready plan. During frontend work, /design generates UI with a committed visual direction. After finishing a task, /check reviews the diff and verifies the work before merging or releasing. When debugging, /hunt walks through the problem systematically and confirms the root cause before touching anything. Other skills cover writing clear prose (/write), researching an unfamiliar topic (/learn), fetching and cleaning web content or PDFs (/read), and auditing your Claude Code configuration (/health). Skills can be chained together manually. A typical flow might run /think to plan, then implement the feature, then /check before merging. The README provides several common workflow patterns for design, debugging, research, and shipping fixes. Installation is one command via npx for Claude Code or Codex. A Claude Desktop ZIP package is also available. The skills install globally so they are available in any project. Waza is part of a three-project set from the same author: Kaku for code generation and Kami for document output. Two optional extras are also included: a statusline showing context window and quota usage, and an English coaching rule that quietly corrects grammar mistakes in your prompts. The project is MIT licensed.

Copy-paste prompts

Prompt 1

How do I chain Waza skills, run /think to plan, implement the feature, then /check before merging?

Prompt 2

Show me how Waza's /hunt skill walks through debugging a failing test in my TypeScript project step by step.

Prompt 3

I want to build a custom Waza-style skill that reviews my commit messages, how do I structure the skill file?

Prompt 4

What does Waza's /health command check in my Claude Code setup, and how do I fix common issues it finds?

Open on GitHub → Explain another repo

← tw93 on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.