Một mục tích hợp AI trong kho dữ liệu GitHub của TopGit: tw93/Waza, 7.6k sao, nhóm AI Tools, Python. 🥷 Engineering habits you already know, turned into skills AI assistants like Claude Code, Codex and Cursor can run.
Tóm tắt dựng từ metadata GitHub của chính dự án — chưa có bài review TopGit. Trang sẽ tự động cập nhật khi bài review đầy đủ được xuất bản.
VÌ SAO CHƯA CÓ REVIEW
TopGit viết bài đầy đủ cho repo có nhiều sao nhất và được yêu cầu nhiều nhất. Trang này là snapshot trong thời gian chờ — xem README gốc ở tab READ ME.
Tw93's engineering habits, turned into your skills.
English · 中文 · 繁體 · 日本語 · 한국어 · Deutsch · Français
Skills
Each engineering habit gets an installed skill, a folder with reference docs, helper scripts, and gotchas from real failures. 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.
/ui
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 against project constraints, verifies the result, and handles approved release and maintainer actions.
/hunt
Any bug, regression, or unexpected behavior
Systematic debugging. Root cause confirmed before any fix is applied, especially when something used to work.
/write
Writing or editing prose
Rewrites prose to sound natural in Chinese and English. Cuts stiff, formulaic phrasing.
/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
Returns a concise summary, or clean Markdown for conversion, quotes, citations, saving, or further research.
/health
Auditing agent setup
Checks Codex, Claude Code, project instructions, verifier output, and AI maintainability with a budget-aware summary pass before deep inspection.
Install
Claude Code, Codex, Cursor, and other agents
npx skills add tw93/Waza -a claude-code codex cursor -g -y
One copy lands in ~/.agents/skills, the shared skills directory. Claude Code is symlinked in; Codex, Cursor, Gemini CLI, Copilot, Amp, Kimi Code CLI, and every other agent that reads that directory picks the eight skills up as /check, /think, and so on. Agents with a private skills directory take their id after -a (for example antigravity-cli or qwen-code). Update with npx skills update -g -y. You can also tell your agent to install it:
Install Waza for me by reading https://github.com/tw93/Waza/blob/main/llms.txt
Host plugin, if you prefer the host's own update command (skills are namespaced, /waza:check)
Claude Desktop: download waza.zip, open Customize > Skills > "+" > Create skill, and upload the ZIP. To update, click "..." on the skill card, choose Replace, and upload the latest ZIP.
Pi: pi install npm:@tw93/waza, update with pi update npm:@tw93/waza.
Chaining Skills
You decide how skills chain together. Each skill stops at the requested outcome; an explicitly authorized workflow continues without asking you to approve every transition.
Common workflows:
Plan a feature: /think to settle the plan, implement after approval, then /check before merging
Ship a fix: /hunt to find the root cause, fix it, then /check to review the changes and, when needed, handle release, publish, push, and issue follow-through
Research and write: /read to fetch sources, /learn to synthesize, /write to polish
The stages a task moves through, and the rules each one holds, are in the AI coding rules.
Project Context
Waza ships only generic engineering habits. /check becomes project-aware at runtime by reading the target repository's public context (READMEs, package manifests, Makefiles, CI workflows) and your task constraints, never private paths, credentials, or tokens. See skills/check/references/project-context.md for the review context template.
Extras
Curl URLs use the latest GitHub release asset. Set WAZA_REF=main before the command if you want bleeding-edge scripts.
Statusline
A minimal statusline for Claude Code: context window, 5-hour quota, and 7-day quota. Color-coded by usage, no progress bars, no noise.
(
set -e
WAZA_STATUSLINE_SCRIPT="$(mktemp -t waza-statusline.XXXXXX)"
trap 'rm -f "$WAZA_STATUSLINE_SCRIPT"' EXIT
curl -fL https://github.com/tw93/Waza/releases/latest/download/setup-statusline.sh -o "$WAZA_STATUSLINE_SCRIPT"
# review it first: less "$WAZA_STATUSLINE_SCRIPT"
bash "$WAZA_STATUSLINE_SCRIPT"
)
Codex has native statusline items. Add to ~/.codex/config.toml:
Codex shows remaining quota; the Claude Code statusline above shows used percentage (upstream does not yet expose five-hour-used / weekly-used).
Optional Rules
Optional rules apply beyond skill invocations when installed into your agent's persistent instructions. Installing Waza skills alone does not enable them. Copy the ones you want (swap claude-code for codex or antigravity-cli on those agents):
(
set -e
WAZA_RULE_SCRIPT="$(mktemp -t waza-rule.XXXXXX)"
trap 'rm -f "$WAZA_RULE_SCRIPT"' EXIT
curl -fL https://github.com/tw93/Waza/releases/latest/download/setup-rule.sh -o "$WAZA_RULE_SCRIPT"
# review it first: less "$WAZA_RULE_SCRIPT"
# English coaching: appends a short 😇 correction when your prompt has an English mistake
bash "$WAZA_RULE_SCRIPT" english claude-code
# Anti-patterns: always-on cross-skill guardrails (read before acting, no scope creep, no unsolicited summaries)
bash "$WAZA_RULE_SCRIPT" anti-patterns claude-code
# Routing hint: tells non-Claude hosts to prefer Waza skills when a request matches their triggers
bash "$WAZA_RULE_SCRIPT" waza-routing claude-code
# Clear everyday replies: consistent terms, explicit conditions, preserved uncertainty
bash "$WAZA_RULE_SCRIPT" clarity claude-code
# Chinese writing: applies these habits to Chinese replies and prose
bash "$WAZA_RULE_SCRIPT" chinese claude-code
)
Clarity uses clear-writing principles from ASD-STE100 without imposing controlled-English grammar or changing your voice. Re-run its command to update the installed rule, then start a new session. Codex installs a marked block in ~/.codex/AGENTS.md; Claude Code and Antigravity install a rule file. For other tools, copy the rule into their persistent custom instructions.
Why
Waza (技, わざ) is a Japanese martial arts term for technique: a move practiced until it becomes instinct. A good engineer does more than write code. They pressure-test requirements, debug to root cause, review their own diffs, and read primary sources. AI has the raw output for all of it, but without structure that output drifts into generic, imprecise work. Each Waza skill states the outcome, the red lines, and how the result gets verified, then steps back and lets the model choose the path. As models improve, that restraint pays compound interest.
Tools like Superpowers and gstack are powerful but heavy: too many skills, too much configuration. Waza stays small, eight skills for the habits that actually matter, each with one job and a clear trigger. The skills were built from real projects and refined through 300+ sessions across 7 projects, and every gotcha traces to a real failure. The /health skill grew from the six-layer Claude Code framework in this post.
Part of a trilogy: Kaku (書く) writes code, Waza (技) drills habits, Kami (紙) ships documents. Think of them as a family: Kaku is the dad, Waza the big sister, Kami the little sister.
For the statusline, also remove the statusLine entry from ~/.claude/settings.json. For Claude Desktop, delete Waza from Customize > Skills. For Codex rule installs, remove the marked Waza blocks from ~/.codex/AGENTS.md. For Antigravity, remove the selected rule file from ~/.gemini/antigravity-cli/rules/. Remove copied rules from other tools' custom instructions. Start a new session after removing a rule.
Support
The most direct way to support me is getting Mole for Mac, my paid Mac cleanup app
If Waza helped you, give it a star, share it, or open an issue or PR after reading SCOPE.md
I have two cats, TangYuan and Coke, and if Waza has been helpful to you, you can feed them canned food 🥩
These lovely people already did 🐱
License
MIT License. Please feel free to use and contribute to the development.
Trang TopGit này là một snapshot — tab "Readme" hiển thị nguyên văn README của repo (đã bỏ link, giữ ảnh). Repo GitHub ở github.com/tw93/Waza là nguồn chính thức.
tw93/Waza có những chủ đề gì?
GitHub topics của tw93/Waza: "agent-skills", "ai-agents", "claude", "claude-code", "codex", "cursor", "design", "engineer", "skills", "superpowers". TopGit xếp repo vào nhóm AI Tools.
tw93/Waza có phải mã nguồn mở không?
Có — tw93/Waza phát hành theo license MIT, nghĩa là mã nguồn mở để đọc, fork và (tùy license) tái sử dụng. Mã: github.com/tw93/Waza.
tw93/Waza có website riêng không?
TopGit chưa ghi nhận URL trang chủ cho tw93/Waza. Phần README ở tab phía trên thường có link demo, hoặc xem mô tả GitHub của repo.
tw93/Waza còn đang phát triển không?
Commit gần nhất trên tw93/Waza là 3 tháng trước (theo timestamp GitHub). Repo có 437 fork — một chỉ báo về mức độ quan tâm của cộng đồng.
tw93/Waza dùng license gì?
tw93/Waza phát hành theo license MIT. Nên mở file LICENSE trên GitHub để xác nhận — license metadata đôi khi lệch với thực tế dự án.
Đọc đầy đủ README ở tab phía trên.
Chưa chắc Waza có hợp với bạn?
Để ChatGPT, Claude hoặc Perplexity tìm hiểu giúp — bấm bên dưới và xem AI nói gì về Waza.