Skip to content
Back to search

waza

MarketplaceWorks with Claude CodeGitHub

Personal skill collection for Claude Code, Codex, Antigravity, OpenCode, and Pi: think, check, hunt, ui, read, write, learn, and health for agent config and AI maintainability audits.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/tw93-waza/badge.svg)](/listings/tw93-waza)

HTML

<a href="/listings/tw93-waza"><img src="/api/listings/tw93-waza/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**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 Code (update: claude plugin update waza)
/plugin marketplace add tw93/Waza
/plugin install waza@waza

# Codex (update: codex plugin marketplace upgrade waza, then codex plugin add waza@waza)
codex plugin marketplace add tw93/Waza
codex plugin add waza@waza

**Claude Desktop**: download [waza.zip](https://github.com/tw93/Waza/releases/latest/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`.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 115 lines
  1. {
  2. "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  3. "name": "waza",
  4. "description": "Personal skill collection for Claude Code, Codex, Antigravity, OpenCode, and Pi: think, check, hunt, ui, read, write, learn, and health for agent config and AI maintainability audits.",
  5. "owner": {
  6. "name": "Tw93",
  7. "email": "hitw93@gmail.com"
  8. },
  9. "plugins": [
  10. {
  11. "name": "waza",
  12. "description": "Installs the full Waza toolkit. Registers all eight skills under the waza namespace, callable as /waza:think, /waza:check, /waza:hunt, /waza:ui, /waza:read, /waza:write, /waza:learn, and /waza:health. For one skill on Claude Code v2.1.143 or newer, use /plugin install waza-<name>@waza.",
  13. "version": "3.42.0",
  14. "category": "development",
  15. "source": "./",
  16. "homepage": "https://github.com/tw93/Waza"
  17. },
  18. {
  19. "name": "waza-check",
  20. "description": "Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.",
  21. "version": "3.42.0",
  22. "category": "development",
  23. "source": "./skills/check",
  24. "homepage": "https://github.com/tw93/Waza",
  25. "skills": [
  26. "./"
  27. ],
  28. "strict": false
  29. },
  30. {
  31. "name": "waza-health",
  32. "description": "Audits or prunes agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong or guidance needs slimming. Not for application bugs or PR review.",
  33. "version": "3.42.0",
  34. "category": "development",
  35. "source": "./skills/health",
  36. "homepage": "https://github.com/tw93/Waza",
  37. "skills": [
  38. "./"
  39. ],
  40. "strict": false
  41. },
  42. {
  43. "name": "waza-hunt",
  44. "description": "Finds root cause before any fix. Use when something errors, crashes, regresses, or used to work. Not for code review or new features.",
  45. "version": "3.42.0",
  46. "category": "development",
  47. "source": "./skills/hunt",
  48. "homepage": "https://github.com/tw93/Waza",
  49. "skills": [
  50. "./"
  51. ],
  52. "strict": false
  53. },
  54. {
  55. "name": "waza-learn",
  56. "description": "Runs a six-phase research workflow from source bundle to publish-ready output. Use when researching an unfamiliar domain or compiling materials into one reference. Not for quick lookups or single-file reads.",
  57. "version": "3.42.0",
  58. "category": "development",
  59. "source": "./skills/learn",
  60. "homepage": "https://github.com/tw93/Waza",
  61. "skills": [
  62. "./"
  63. ],
  64. "strict": false
  65. },
  66. {
  67. "name": "waza-read",
  68. "description": "Fetches URLs and PDFs, then summarizes or returns clean Markdown; can also search the web through DeepSeek when built-in search is thin. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.",
  69. "version": "3.42.0",
  70. "category": "development",
  71. "source": "./skills/read",
  72. "homepage": "https://github.com/tw93/Waza",
  73. "skills": [
  74. "./"
  75. ],
  76. "strict": false
  77. },
  78. {
  79. "name": "waza-think",
  80. "description": "Turns rough ideas into approved, decision-complete plans before coding. Use when planning architecture, judging whether to build, or writing a handoff. Not for bug fixes or small edits.",
  81. "version": "3.42.0",
  82. "category": "development",
  83. "source": "./skills/think",
  84. "homepage": "https://github.com/tw93/Waza",
  85. "skills": [
  86. "./"
  87. ],
  88. "strict": false
  89. },
  90. {
  91. "name": "waza-ui",
  92. "description": "Produces distinctive production UI and screenshot-grounded visual polish. Use when building or restyling pages, components, or typography. Not for backend logic or data pipelines.",
  93. "version": "3.42.0",
  94. "category": "development",
  95. "source": "./skills/ui",
  96. "homepage": "https://github.com/tw93/Waza",
  97. "skills": [
  98. "./"
  99. ],
  100. "strict": false
  101. },
  102. {
  103. "name": "waza-write",
  104. "description": "Rewrites and polishes Chinese or English prose, technical instructions, and product copy. Use when drafting, editing, localizing, or cutting AI tone. Not for code comments or commit messages.",
  105. "version": "3.42.0",
  106. "category": "development",
  107. "source": "./skills/write",
  108. "homepage": "https://github.com/tw93/Waza",
  109. "skills": [
  110. "./"
  111. ],
  112. "strict": false
  113. }
  114. ]
  115. }
README.md · README · 180 lines
  1. <div align="center">
  2. <img src="https://raw.githubusercontent.com/tw93/Waza/main/assets/logo.svg" width="120" />
  3. <h1>Waza</h1>
  4. <p><b>Tw93's engineering habits, turned into your skills.</b></p>
  5. <p>English · <a href="README_CN.md">中文</a> · <a href="README_TW.md">繁體</a> · <a href="README_JA.md">日本語</a> · <a href="README_KR.md">한국어</a> · <a href="README_DE.md">Deutsch</a> · <a href="README_FR.md">Français</a></p>
  6. <a href="https://github.com/tw93/Waza/actions/workflows/test.yml"><img src="https://img.shields.io/github/actions/workflow/status/tw93/Waza/test.yml?branch=main&style=flat-square&label=tests" alt="Tests"></a>
  7. <a href="https://github.com/tw93/Waza/stargazers"><img src="https://img.shields.io/github/stars/tw93/Waza?style=flat-square" alt="Stars"></a>
  8. <a href="https://github.com/tw93/Waza/releases"><img src="https://img.shields.io/github/v/tag/tw93/Waza?label=version&style=flat-square" alt="Version"></a>
  9. <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue.svg?style=flat-square" alt="License"></a>
  10. <a href="https://x.com/HiTw93"><img src="https://img.shields.io/badge/follow-Tw93-red?style=flat-square&logo=x" alt="Twitter"></a>
  11. </div>
  12. <br/>
  13. <div align="center">
  14. <img src="assets/waza_skills.svg" width="1000" />
  15. </div>
  16. ## Skills
  17. 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.
  18. | Skill | When | What it does |
  19. | :--- | :--- | :--- |
  20. | [`/think`](skills/think/SKILL.md) | Before building anything new | Challenges the problem, pressure-tests the design, and produces a decision-complete plan another agent can implement. |
  21. | [`/ui`](skills/ui/SKILL.md) | Building frontend interfaces | Produces distinctive UI, including screenshot-driven aesthetic iteration, with a committed direction rather than generic defaults. |
  22. | [`/check`](skills/check/SKILL.md) | After a task, before merging or release | Reviews the diff against project constraints, verifies the result, and handles approved release and maintainer actions. |
  23. | [`/hunt`](skills/hunt/SKILL.md) | Any bug, regression, or unexpected behavior | Systematic debugging. Root cause confirmed before any fix is applied, especially when something used to work. |
  24. | [`/write`](skills/write/SKILL.md) | Writing or editing prose | Rewrites prose to sound natural in Chinese and English. Cuts stiff, formulaic phrasing. |
  25. | [`/learn`](skills/learn/SKILL.md) | Diving into an unfamiliar domain | Six-phase research workflow: collect, digest, outline, fill in, refine, then self-review and publish. |
  26. | [`/read`](skills/read/SKILL.md) | Any URL or PDF | Returns a concise summary, or clean Markdown for conversion, quotes, citations, saving, or further research. |
  27. | [`/health`](skills/health/SKILL.md) | Auditing agent setup | Checks Codex, Claude Code, project instructions, verifier output, and AI maintainability with a budget-aware summary pass before deep inspection. |
  28. ## Install
  29. **Claude Code, Codex, Cursor, and other agents**
  30. ```bash
  31. npx skills add tw93/Waza -a claude-code codex cursor -g -y
  32. ```
  33. 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:
  34. > Install Waza for me by reading https://github.com/tw93/Waza/blob/main/llms.txt
  35. **Host plugin**, if you prefer the host's own update command (skills are namespaced, `/waza:check`)
  36. ```bash
  37. # Claude Code (update: claude plugin update waza)
  38. /plugin marketplace add tw93/Waza
  39. /plugin install waza@waza
  40. # Codex (update: codex plugin marketplace upgrade waza, then codex plugin add waza@waza)
  41. codex plugin marketplace add tw93/Waza
  42. codex plugin add waza@waza
  43. ```
  44. **Claude Desktop**: download [waza.zip](https://github.com/tw93/Waza/releases/latest/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.
  45. **Pi**: `pi install npm:@tw93/waza`, update with `pi update npm:@tw93/waza`.
  46. ## Chaining Skills
  47. 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.
  48. **Common workflows:**
  49. - **Plan a feature**: `/think` to settle the plan, implement after approval, then `/check` before merging
  50. - **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
  51. - **Research and write**: `/read` to fetch sources, `/learn` to synthesize, `/write` to polish
  52. The stages a task moves through, and the rules each one holds, are in the [AI coding rules](https://github.com/tw93/Waza/blob/main/docs/ai-coding-rules.md).
  53. ## Project Context
  54. 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`](skills/check/references/project-context.md) for the review context template.
  55. ## Extras
  56. Curl URLs use the latest GitHub release asset. Set `WAZA_REF=main` before the command if you want bleeding-edge scripts.
  57. ### Statusline
  58. A minimal statusline for Claude Code: context window, 5-hour quota, and 7-day quota. Color-coded by usage, no progress bars, no noise.
  59. <div align="center">
  60. <img src="https://raw.githubusercontent.com/tw93/Waza/main/assets/statusline.png" width="1000" />
  61. </div>
  62. ```bash
  63. (
  64. set -e
  65. WAZA_STATUSLINE_SCRIPT="$(mktemp -t waza-statusline.XXXXXX)"
  66. trap 'rm -f "$WAZA_STATUSLINE_SCRIPT"' EXIT
  67. curl -fL https://github.com/tw93/Waza/releases/latest/download/setup-statusline.sh -o "$WAZA_STATUSLINE_SCRIPT"
  68. # review it first: less "$WAZA_STATUSLINE_SCRIPT"
  69. bash "$WAZA_STATUSLINE_SCRIPT"
  70. )
  71. ```
  72. **Codex** has native statusline items. Add to `~/.codex/config.toml`:
  73. ```toml
  74. [tui]
  75. status_line = ["model-with-reasoning", "current-dir", "context-used", "five-hour-limit", "weekly-limit"]
  76. status_line_use_colors = true
  77. ```
  78. Codex shows remaining quota; the Claude Code statusline above shows used percentage (upstream does not yet expose `five-hour-used` / `weekly-used`).
  79. ### Optional Rules
  80. 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):
  81. ```bash
  82. (
  83. set -e
  84. WAZA_RULE_SCRIPT="$(mktemp -t waza-rule.XXXXXX)"
  85. trap 'rm -f "$WAZA_RULE_SCRIPT"' EXIT
  86. curl -fL https://github.com/tw93/Waza/releases/latest/download/setup-rule.sh -o "$WAZA_RULE_SCRIPT"
  87. # review it first: less "$WAZA_RULE_SCRIPT"
  88. # English coaching: appends a short 😇 correction when your prompt has an English mistake
  89. bash "$WAZA_RULE_SCRIPT" english claude-code
  90. # Anti-patterns: always-on cross-skill guardrails (read before acting, no scope creep, no unsolicited summaries)
  91. bash "$WAZA_RULE_SCRIPT" anti-patterns claude-code
  92. # Routing hint: tells non-Claude hosts to prefer Waza skills when a request matches their triggers
  93. bash "$WAZA_RULE_SCRIPT" waza-routing claude-code
  94. # Clear everyday replies: consistent terms, explicit conditions, preserved uncertainty
  95. bash "$WAZA_RULE_SCRIPT" clarity claude-code
  96. # Chinese writing: applies these habits to Chinese replies and prose
  97. bash "$WAZA_RULE_SCRIPT" chinese claude-code
  98. )
  99. ```
  100. <div align="center">
  101. <img src="https://raw.githubusercontent.com/tw93/Waza/main/assets/english-coaching.png" width="1000" />
  102. </div>
  103. [Clarity](rules/clarity.md) 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.
  104. ## Why
  105. 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.
  106. 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](https://tw93.fun/en/2026-03-12/claude.html).
  107. Part of a trilogy: [Kaku](https://github.com/tw93/Kaku) (書く) writes code, [Waza](https://github.com/tw93/Waza) (技) drills habits, [Kami](https://github.com/tw93/Kami) (紙) ships documents. Think of them as a family: Kaku is the dad, Waza the big sister, Kami the little sister.
  108. ## Uninstall
  109. ```bash
  110. npx skills remove tw93/Waza -g
  111. rm -f ~/.claude/statusline.sh
  112. rm -f ~/.claude/rules/english.md
  113. rm -f ~/.claude/rules/anti-patterns.md
  114. rm -f ~/.claude/rules/waza-routing.md
  115. rm -f ~/.claude/rules/clarity.md
  116. ```
  117. 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.
  118. ## Support
  119. - The most direct way to support me is getting [Mole for Mac](https://mole.fit), my paid Mac cleanup app
  120. - If Waza helped you, give it a star, [share it](https://x.com/intent/tweet?url=https://github.com/tw93/Waza&text=Waza%20-%20Tw93%27s%20engineering%20habits%2C%20turned%20into%20your%20skills.), or open an issue or PR after reading [SCOPE.md](https://github.com/tw93/Waza/blob/main/SCOPE.md)
  121. - I have two cats, TangYuan and Coke, and if Waza has been helpful to you, you can feed them <a href="https://cats.tw93.fun?name=Waza" target="_blank">canned food 🥩</a>
  122. These lovely people already did 🐱
  123. <div align="center">
  124. <a href="https://cats.tw93.fun?name=Waza"><img src="https://raw.githubusercontent.com/tw93/sponsors/main/assets/sponsors.svg" width="1000" loading="lazy" /></a>
  125. </div>
  126. ## License
  127. MIT License. Please feel free to use and contribute to the development.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.