Skillget

Waza

skill
Security Audit
Fail
Health Warn
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 766 GitHub stars
Code Fail
  • rm -rf — Recursive force deletion command in skills/check/scripts/check-destructive.sh
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This is a collection of custom slash commands ("skills") designed for Claude Code. It provides structured playbooks to help developers with UI design, code review, systematic debugging, and reading external URLs or PDFs.

Security Assessment
The tool uses shell scripts to automate tasks and includes a helper script designed to fetch content from the web (cleaning URLs into Markdown). The automated scan flagged a recursive force deletion command (`rm -rf`) inside one of its checking scripts. Because this command is located within a destructive-checking utility, it is likely used intentionally to test or block hazardous actions rather than to delete user files maliciously. However, as with any shell execution tool, users should review the underlying scripts before running them to understand exactly what files are being modified or deleted. There are no hardcoded secrets present. Overall risk is rated as Medium due to the execution capabilities and web-fetching features.

Quality Assessment
The project is very actively maintained, with its most recent updates pushed today. It enjoys strong community trust, backed by 766 GitHub stars. There is a minor discrepancy in the repository: the README displays an MIT license badge, but the automated health check failed to locate an actual license file in the repository. This missing file could pose minor legal or usage ambiguies for companies with strict open-source compliance.

Verdict
Use with caution: it is a popular and actively maintained developer toolkit, but you should quickly verify the presence of a license file and inspect the shell scripts for safe execution boundaries before integrating it into your workflow.
SUMMARY

🥷 Claude Code skills for the complete engineer: design, solve, express, grow.

README.md

Waza

Claude Code skills for the complete engineer: design, solve, express, grow.

Stars Version License Twitter

Why

Waza (技) is a Japanese martial arts term for technique: a move practiced until it becomes instinct.

A good engineer does not just write code. They think through requirements, review their own work, debug systematically, design interfaces that feel intentional, and read primary sources. They write clearly, and learn new domains by producing output, not consuming content.

Skills

Each engineering habit gets a Claude Code skill. Type the slash command, Claude follows the playbook.

Skill When What it does
/think Before building anything new Challenges the problem, pressure-tests the design, validates architecture before any code is written.
/design Building frontend interfaces Produces distinctive UI with a committed aesthetic direction, not generic defaults.
/check After a task, before merging Reviews the diff, auto-fixes safe issues, blocks destructive commands via hooks, verifies with evidence.
/hunt Any bug or unexpected behavior Systematic debugging. Root cause confirmed before any fix is applied.
/write Writing or editing prose Rewrites prose to sound natural in Chinese and English. Strips AI writing patterns.
/learn Diving into an unfamiliar domain Six-phase research workflow: collect, digest, outline, fill in, refine, then self-review and publish.
/read Any URL or PDF Fetches content as clean Markdown via proxy cascade script.
/health Auditing Claude Code setup Checks CLAUDE.md, rules, skills, hooks, MCP, and behavior. Flags issues by severity.

Each skill is a folder, not just a markdown file. Skills include reference docs, helper scripts, scoped hooks, and gotchas sections built from real project failures. See Anthropic's skill best practices for the philosophy behind this structure.

English Coaching

English should be every engineer's first language when working with AI. The model thinks in English, the best resources are in English, and writing clearly in English is a skill that compounds over time.

Passive grammar correction on every reply. Claude flags mistakes with the pattern name so you learn why.

😇 I very like this feature → I really like this feature (Unnatural phrasing)

curl -sL https://raw.githubusercontent.com/tw93/Waza/main/templates/english-coaching.md >> ~/.claude/CLAUDE.md

Install

All skills:

npx skills add tw93/Waza -g -y

Single skill:

# example: install the health skill
npx skills add tw93/Waza -a claude-code -s health -y

Replace health with any skill name. Requires Node 18+ and Claude Code.

Background

Tools like Superpowers and gstack are impressive, but they are heavy. Too many skills, too much configuration, too steep a learning curve for engineers who just want to get things done.

Waza is the opposite: eight skills that cover the habits that actually matter. Each one does one thing, has a clear trigger, and stays out of the way. The goal is not completeness. It is the right amount, done well.

Built from patterns accumulated across real projects, then refined with 30 days of usage data (300+ sessions, 7 projects, 500 hours). Each gotcha in a skill traces back to a specific failure: a wrong code path that cost four rounds, a release announced before artifacts were uploaded, a server restarted eight times without reading the error. The /health skill is based on the six-layer framework described in this post.

Support

  • If Waza helped you, star the repo or share it with friends.
  • Have ideas or found bugs? Open an issue or PR.
  • Like Waza? Buy Tw93 a Coke to support the project.
🥤 Supporters

License

MIT License. Feel free to use Waza and contribute.

Reviews (0)

No results found