by tw93
π₯· Engineering habits you already know, turned into skills Claude can run.
# Add to your Claude Code skills
git clone https://github.com/tw93/WazaLast scanned: 4/21/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-04-21T06:03:05.858Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}Waza (ζ, γγ) 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.
AI is more capable than most engineers at raw output. But without structure, that capability drifts into generic, imprecise work. Waza channels it into precision: eight skills that set clear goals and constraints, then let the model do what it does best.
Part of a trilogy: Kaku (ζΈγ) writes code, Waza (ζ) drills habits, Kami (η΄) ships documents. Think of them as a family: Kaku is the dad, Waza the big sister, Kami the little sister.
Each engineering habit gets an installed skill. In Claude Code, type the slash command. In Codex, invoke the installed skill by name and follow the same playbook.
| Skill | When | What it does |
| :--- | :--- | :--- |
| /think | Before building anything new | Challenges the problem, pressure-tests the design, and produces a decision-complete plan another agent can implement. |
| /design | Building frontend interfaces | Produces distinctive UI, including screenshot-driven aesthetic iteration, with a committed direction rather than generic defaults. |
| /check | After a task, before merging or release | Reviews the diff, extracts project-specific constraints, handles approved release/publish/push/reaction follow-through, and verifies with evidence. |
| /hunt | Any bug, regression, or unexpected behavior | Systematic debugging. Root cause confirmed before any fix is applied, especially when something used to work. |
| | Writing or editing prose | Rewrites prose to sound natural in Chinese and English. Cuts stiff, formulaic phrasing. |
| | Diving into an unfamiliar domain | Six-phase research workflow: collect, digest, outline, fill in, refine, then self-review and publish. |
| | Any URL or PDF | Fetches content as clean Markdown with platform-specific routing. Special handling for GitHub, PDFs, WeChat, and Feishu. Privacy-first: defaults to a local extractor; opts into defuddle.md / r.jina.ai for JS-heavy pages. |
| | Auditing Agent Health | Checks Codex, Claude Code, project instructions, verifier output, and AI maintainability with a budget-aware summary pass before deep inspection. |
No comments yet. Be the first to share your thoughts!
--use-proxyEach skill is a folder with reference docs, helper scripts, and gotchas from real failures.
Most users should install Waza globally, so the same skills are available in every project.
Claude Code
npx skills add tw93/Waza -a claude-code -g -y
This installs /think, /design, /check, /hunt, /write, /learn, /read, and /health. Install just one with npx skills add tw93/Waza --skill think -a claude-code -g -y.
Codex
npx skills add tw93/Waza -a codex -g -y
Install just one with npx skills add tw93/Waza --skill think -a codex -g -y. Codex sessions can invoke installed skills by name or link to the installed SKILL.md path shown by npx skills path tw93/Waza.
Claude Code plugin marketplace
/plugin marketplace add tw93/Waza
/plugin install waza@waza
Use the bundle for now. Per-skill marketplace entries like waza-think@waza are temporarily affected by a Claude Code v2.1.136+ path-validation regression; until upstream fixes it, install one skill with the npx skills add ... --skill path above.
Claude Desktop
Download waza.zip, open Customize > Skills > "+" > Create skill, and upload the ZIP.
Update
npx skills update -g -y
Marketplace installs use claude plugin update <skill>. Claude Desktop users can replace the old skill with the latest waza.zip.
Compatibility
/health now supports Agent Health for both Claude Code and Codex. It understands AGENTS.md, CLAUDE.md, Copilot/Gemini instruction files, Codex config summaries, Claude hooks/MCP when present, verifier logs, and AI maintainability signals. It defaults to summary mode and only deepens when you ask for a deep/full audit or when the summary pass cannot classify the risk.
Waza keeps the generic programmer habits inside the public skill. /check becomes project-aware by reading the target repository's public context and the user's task constraints.
See skills/check/references/project-context.md for the review context template.
Skills are designed to be chained together, but transitions are manual. Each skill stops after completing its task and waits for you to decide the next step.
Common workflows:
/think β approve β say "implement X" β /check β merge/hunt β fix β /check β release/publish/push/issue follow-through/read (fetch sources) β /learn (synthesize) β /write (polish)/hunt (find root cause) β fix β /check (review changes)Each arrow represents a manual user action. Skills don't automatically trigger each other.
A minimal statusline for Claude Code: context window, 5-hour quota, and 7-day quota.
Color coding: green below 70%, yellow at 70-85%, red above 85% for context; blue, magenta, red for quota thresholds. No progress bars, no noise.
curl -sL https://raw.githubusercontent.com/tw93/Waza/v3.24.0/scripts/setup-statusline.sh | bash
Codex
Codex has native statusline items. Add to ~/.codex/config.toml:
[tui]
status_line = ["model-with-reasoning", "current-dir", "context-used", "five-hour-limit", "weekly-limit"]
status_line_use_colors = true
Note: Codex shows remaining quota, while the Claude Code statusline above shows used percentage. Upstream does not yet offer used-percentage items (e.g. five-hour-used / weekly-used).
Optional rule for English practice. When your prompt contains an English mistake, the agent appends a short π correction; Chinese-only prompts stay untouched.
# Claude Code
curl -sL https://raw.githubusercontent.com/tw93/Waza/v3.24.0/scripts/setup-rule.sh | bash -s -- english claude-code
# Codex
curl -sL https://raw.githubusercontent.com/tw93/Waza/v3.24.0/scripts/setup-rule.sh | bash -s -- english codex
Optional always-on guardrails for cross-skill behaviors: stop acting before reading, no hallucinated paths, no scope creep, no unsolicited summaries. Skill-agnostic, applies in every session.
curl -sL https://raw.githubusercontent.com/tw93/Waza/v3.24.0/scripts/setup-rule.sh | bash -s -- anti-patterns claude-code
Use codex instead of claude-code for Codex. Curl URLs are pinned to the current release tag for reproducibility; swap v3.24.0 for main if you want bleeding-edge scripts.
npx skills remove tw93/Waza -g
rm -f ~/.claude/statusline.sh
rm -f ~/.claude/rules/english.md
rm -f ~/.claude/rules/anti-patterns.md
For Claude Desktop, delete Waza from Customize > Skills. For Codex rule installs, remove the marked Waza block from ~/.codex/AGENTS.md.
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.
There's also a subtler problem. Every rule the author writes becomes a ceiling. The model can only do what the instructions say and can't go further. Waza goes the other direction. Each skill sets a clear goal and the constraints that matter, then steps back. As models improve, that restraint pays compound interest.
Eight