Waza

Install

npx skills add tw93/Waza -a claude-code codex cursor -g -y

This is third-party code. Review the repository files before installing.

What it does

Waza packs an experienced engineer's habits into eight small skills with clear triggers. /think stress-tests a problem and produces a plan another agent can implement. /hunt finds a bug's root cause before any fix, and /check reviews the diff against project rules and follows through on releases. /ui builds interfaces with a committed direction, /write cleans up English and Chinese prose, /learn and /read drive research and source summaries, and /health audits agent config and project instructions.

Who it is for. For developers who want a compact set of working habits for their agent without a heavy framework.

Example request

/hunt the build broke after the dependency update, find the cause

Limitations

/write handles English and Chinese only. Some SKILL.md triggers are in Chinese. Optional rules and the statusline install through separate shell scripts that the author suggests reviewing first.

How to disable. Run npx skills remove tw93/Waza -g. For the plugin, uninstall waza via /plugin; in Claude Desktop delete the skill under Customize, Skills.

Security check

• Skills run git commands and helper scripts
• /check can commit, push and publish releases after explicit approval

README in short

The README lists eight skills with when to use each and what it produces. Install via npx skills into ~/.agents/skills, as a Claude Code or Codex plugin, as a ZIP for Claude Desktop or a Pi package. It also covers a Claude Code statusline with context and quota usage and three optional rules. The author explains keeping the set deliberately small. MIT licensed.

SKILL.md

---
name: check
description: "Reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use when users ask in any language for code review, issue or PR triage, release gates, publishing follow-through, or project audits. Not for debugging root causes or prose review."
dispatch_intent: "Code review, before merge, release gates, generated artifacts, safety sinks, publish/push/reaction follow-through, triage issues/PRs, project-wide code-quality audit scorecard"
---

# Check: Review Before You Ship

> Note: `/review` is a built-in Anthropic plugin command for PR review. Waza uses `/check` (or the alias `code-review`) instead. Do not re-trigger `/review` from within this skill.

Read the diff and find the problems. Review, audit, triage, and readiness requests are report-only; apply fixes only when the current turn explicitly asks to fix, change, implement, or optimize. Done means the requested review surface is covered and every verification claim comes from this session.

## Outcome Contract

- Outcome: a review, release decision, or maintainer action grounded in the current diff, project context, and live evidence.
- Done when: findings, fixes, shipped state, or blockers are stated with the commands, artifacts, or remote state that prove them.
- Evidence: worktree status, diff, public project docs, manifests, CI, package contents, release or registry state, and current command output.

## Worktree Safety Preflight

Before any review, triage, ship, release, or PR operation, read the current worktree with:

```bash
git status --short --branch -uall
```

Treat modified, staged, and untracked files as user work. You may read them and include them in the review surface, but you must not move, hide, overwrite, clean, or discard them without explicit user approval in the current turn.

Related