V3.10.1 Quiet 🔇

Waza V3.10.1

Unblock Windows installs, harden the validator.

Changelog

1. Learn: Fixed the Windows install where the learn skill was silently dropped. Thanks @OiAnthony (#31), @zhangleijuly (#32).
2. Verify: scripts/verify-skills.sh now catches the YAML mistake at commit time and enforces the 🥷 first-line prefix across all skills.
3. Health: Filled in the Gotchas section that the other skills already carry.

更新日志

1. Learn: 修复 Windows 下 learn skill 被静默丢弃的问题。感谢 @OiAnthony (#31)、@zhangleijuly (#32)。
2. Verify: scripts/verify-skills.sh 在提交时就拦住相关 YAML 写法，并要求每个 skill 都带 🥷 首行约定。
3. Health: 补齐其余 skill 已有的 Gotchas 小节。

Update: npx skills add tw93/Waza@latest · ⭐ tw93/Waza

V3.10.0 Polish ✨

Waza V3.10.0

Polish the edges: tighter validation, sharper handoffs, cleaner install.

Changelog

1. Hunt: Added a structured Handoff format for when three hypotheses fail, so debugging sessions surface evidence and unknowns instead of trailing off.
2. Think: Added an official-solution-first check before custom proposals, and decoupled pre-read gates from project-specific conventions so the skill works on any codebase.
3. Design: Catalogued the awesome-design-md brand preset library (66+ brands) and documented how to pull a DESIGN.md seed without overriding Reflex Fonts or Absolute Bans.
4. Learn: Split Phase 1 into explicit Discover / Fetch / File steps so /read is never bypassed on paywalled or JS-heavy sources.
5. Verify: Tightened verify-skills.sh to enforce description parity between each SKILL.md and marketplace.json, catching drift at commit time.
6. Install: Install commands now mkdir -p their target directories before curl, fixing fresh-machine failures (thanks @tang-hi for #30).

更新日志

1. Hunt: 新增三次假设失败后的结构化交接模板，让调试在卡住时把证据和未知项讲清楚，而不是草草收尾。
2. Think: 在提出自定义方案前先检查官方解决方案，并把 pre-read 检查从项目特定约定中解耦，换任何代码库都能用。
3. Design: 纳入 awesome-design-md 品牌预设库（66+ 品牌），并说明如何取其作为 DESIGN.md 种子而不覆盖 Reflex Fonts 与 Absolute Bans 规则。
4. Learn: 把 Phase 1 拆成 Discover / Fetch / File 三步，避免绕过 /read 导致付费墙和 JS 重站点抓不到内容。
5. Verify: verify-skills.sh 新增 SKILL.md 与 marketplace.json description 字段一致性校验，提交时就能拦住漂移。
6. Install: 安装命令先 mkdir -p 目标目录再 curl，修复首次使用时目录不存在的失败（感谢 @tang-hi 的 #30）。

Update: npx skills add tw93/Waza@latest · ⭐ tw93/Waza

V3.9.0 Hone 🪒

Waza V3.9.0

Sharper edges. Same eight tools, honed.

Changelog

1. Write: Full restructure into Pre-flight / Hard Rules / Output; audience and language now gated before edit, emoji stripped from edited text, "never guess the target" rule added.
2. Read: No auto-summary, paywall detection added, never overwrites an existing file (auto-increments -1, -2), and stops after the save report instead of suggesting follow-ups.
3. Health: Collection script absorbs all failure-mode docs, SKILL.md trimmed ~40%, agent prompts tightened, circular-symlink guard added to resolve_symlink.
4. Check: Drift signals and hard stops marked as examples, not exhaustive; "should work now" / "trivial change" phrase trigger restored in Verification.
5. Design: AI Slop Test expanded with concrete reflex patterns (Inter, purple-blue gradient, three-card hero, centered dual-CTA) instead of a single-line check.
6. Hunt: Hard Rules consolidated: "let me just try this" folded into same-symptom stop; grep-before-touching merged into verify-before-claiming.
7. Think: Attack angles explicitly non-exhaustive; "帮我做" and "just do it" unified as approval of the recommended option.
8. Learn: Phase 6 renamed to Self-review and Publish Readiness; stops at user confirmation and never auto-publishes; /write fallback path documented when the skill is missing.
9. Infra: verify-skills.sh gains a broken-reference checker covering references/, agents/, and scripts/; readlink -f replaced with a portable fallback for macOS.

更新日志

1. Write: 重构为 Pre-flight / Hard Rules / Output 三段；编辑前强制卡受众和语言，输出去 emoji，新增"不要猜目标文本"规则。
2. Read: 不再自动摘要；新增付费墙识别；文件重名自动追加 -1、-2，不再覆盖；保存后即停，不追加 follow-up 建议。
3. Health: 失败模式文档下沉到采集脚本注释，SKILL.md 精简约 40%，子 Agent 提示词收紧，resolve_symlink 增加循环软链保护。
4. Check: Drift signals 和 Hard Stops 明确标注为举例不穷尽；恢复 Verification 章节的"should work now / trivial change"触发短语清单。
5. Design: AI Slop Test 从一句话扩展为具体反例（Inter、紫蓝渐变、三卡 hero、居中双 CTA），更好识别默认倾向。
6. Hunt: Hard Rules 合并去重："let me just try this" 并入 same-symptom 停手规则；grep before touching 并入 verify before claiming。
7. Think: 攻击角度明确标注为举例不穷尽；"帮我做"和"just do it"统一视为对推荐方案的批准。
8. Learn: Phase 6 改名为 Self-review and Publish Readiness，用户确认即停，不主动发布；补全 /write 缺失时的降级路径。
9. Infra: verify-skills.sh 新增 broken reference 检查（覆盖 references/、agents/、scripts/）；readlink -f 替换为 macOS 可移植实现。

Update: npx skills add tw93/Waza@latest · ⭐ tw93/Waza

V3.8.0 Forge 🔨

Waza V3.8.0

Engineering habits you already know, turned into skills Claude can run.

Changelog

1. Think: Attack table with four angles (dependency failure, scale explosion, rollback cost, premise collapse) replaces the single-line "attack it first" instruction.
2. Hunt: Progress Signals table added so the model can confirm it is on the right track, not just catch when it goes wrong.
3. Check: Scope drift now has five concrete criteria; specialist finding merge rules handle cross-reviewer severity disagreements explicitly.
4. Design: Mid-Build Checkpoint added every third component to catch aesthetic drift before handoff.
5. Learn: Phase 4 stall signals detect incomplete mental models; Hard Rules extracted into a dedicated section.
6. Write: "Meaning first, style second" rule prevents rewrites that sound better but change the author's intent.
7. Read / Health: All-methods-failed exit path in Read; concrete MCP detection template in Health.
8. Extras: Unified skill versions to 3.8.0, CI workflow added, English Coaching released as a standalone extra.

更新日志

1. Think: 用四维攻击表（依赖断裂、规模爆炸、回滚代价、前提失效）替换原来一句话的"先攻击方案"。
2. Hunt: 新增正向信号表，模型可以确认诊断方向正确，不只是检测何时走偏。
3. Check: Scope drift 新增五条判断标准；专家审查合并规则明确了 severity 不一致时的处理方式。
4. Design: 新增中间检查点，每写完三个组件核查一次美学方向是否漂移。
5. Learn: Phase 4 新增卡壳信号识别心智模型不完整的段落；Hard Rules 提取为独立段落。
6. Write: 新增"语义优先于风格"规则，防止为去 AI 味改坏作者原意。
7. Read / Health: Read 补全所有方式失败时的退出路径；Health MCP 检测改为具体模板。
8. 附加: 统一技能版本到 3.8.0，新增 CI，English Coaching 作为独立附加功能发布。

Update: npx skills add tw93/Waza@latest · ⭐ tw93/Waza

V3.7.0 Kora 🎨

English Changelog

• Design: Major upgrade incorporating Impeccable, GetDesign, and Kora reference material; sharpens aesthetic direction and removes generic defaults.
• Design: Refined craft details and skill contracts based on real-world usage review; tighter guidance on tier detection and output format.
• Health: Added Part C context-effectiveness audit to the inspector-context agent for deeper conversation-quality analysis.
• Health: Replaced head -c byte-slicing with line-safe JSONL sampling; tightened correction-signal detection to cut false positives.
• Write: Distilled top friction patterns from 30-day usage; added concrete counter-examples for bridge-sentence and TL;DR rules.
• Statusline: Added rate-limits cache fallback so token counters survive account switches; fixed cache-write guard to prevent stale data overwrites.
• Verification: Introduced Makefile with smoke tests for statusline and health, replacing scattered inline shell checks.

中文更新日志

• 设计技能: 全面升级，融入 Impeccable、GetDesign 和 Kora 参考素材，审美方向更清晰，彻底去掉通用默认风格。
• 设计技能: 根据实际使用反馈精炼工艺细节和技能契约，层级检测和输出格式指导更严谨。
• Health: inspector-context agent 新增 Part C 上下文效果审计，对话质量分析更深入。
• Health: 用逐行安全的 JSONL 采样替换 head -c 字节截断；收紧 correction 信号检测，减少误报。
• 写作技能: 提炼 30 天使用中的高频摩擦点，为桥接句和 TL;DR 规则补充具体反例。
• Statusline: 新增 rate-limits 缓存回退，切换账号后 token 计数不再丢失；修复缓存写入条件，防止陈旧数据覆写。
• 验证: 新增 Makefile，包含 statusline 和 health 的 smoke test，取代分散的内联 shell 检查。

---

Update: npx skills add tw93/Waza@latest · ⭐ tw93/Waza

V3.4.0 Distill 🧪

Changelog

1. Write: Editing pass now catches paragraph-end summary sentences first and stops over-correcting the author's natural voice.
2. Learn: When two sources contradict on a fact, both positions are now recorded rather than one being silently picked.
3. Hunt: Visual and rendering bugs now follow a static-analysis-first protocol: inspect paint layers in DevTools before adding logs.
4. Check: PR comment guidance now requires natural paragraphs and thanks the contributor first, not bullet-point reports.
5. Read: Fetch cascade retries each proxy once before falling back; GitHub file URLs now route to raw.githubusercontent.com or gh api instead of the proxy.

---

更新日志

1. Write: 改稿优先清除段末总结句，不再过度去口语化，英文清单补 emoji 删除。
2. Learn: 来源互相矛盾时，现在记录双方立场和依据，不再默默选一个。
3. Hunt: 视觉/渲染 bug 现在先走静态分析流程，在 DevTools 检查绘制层，再加日志。
4. Check: PR 评论规范改为自然段落，先感谢贡献者，不用列表汇报格式。
5. Read: 抓取级联现在对每个代理各重试一次；GitHub 文件链接改为走 raw.githubusercontent.com 或 gh api。

---

https://github.com/tw93/Waza

V3.3.0 Resonance 🎵

Changelog

1. /read and /learn: now support web search plugins (e.g., PipeLLM) for better source discovery and JavaScript-rendered pages.
2. /think: added TDD protocol enforcing red-green-refactor cycles after design approval.
3. Agent discovery: added .agents/skills/ symlinks for agents that auto-discover skills from that path.

更新日志

1. /read 和 /learn: 现在支持网页搜索插件（如 PipeLLM），提升来源发现和 JavaScript 渲染页面支持。
2. /think: 新增 TDD 协议，设计通过后强制执行红-绿-重构循环。
3. Agent 发现: 新增 .agents/skills/ 符号链接，支持从该路径自动发现技能的 agent。

Update: npx skills add tw93/Waza@latest · ⭐ https://github.com/tw93/Waza

V3.2.0 Clarity ✨

English Changelog

• Skill philosophy: replaced prescriptive step-by-step instructions in health, check, think, and hunt with goal statements, letting the model choose the best approach as capabilities improve.
• Health refactor: extracted the 180-line data-collection bash script into scripts/collect-data.sh, reducing health SKILL.md by 60%.
• Check refactor: removed hardcoded git and gh commands; trimmed GitHub Operations to constraint-only rules.
• Read: defuddle.md is now the primary fetch proxy; r.jina.ai falls back if it fails.
• Statusline: setup script now detects an existing statusline and prompts before overwriting (default Y).
• Rename: health agents renamed to inspector-context/inspector-control to match the reviewer-* pattern; verify.sh renamed to run-tests.sh; english-coaching.md renamed to coaching-en.md.

中文更新日志

• 技能哲学: 将 health、check、think、hunt 中逐步指令替换为目标陈述，让模型随能力提升自主选择最佳方式。
• Health 重构: 将 180 行数据采集 bash 脚本提取为 scripts/collect-data.sh，health SKILL.md 体积缩减 60%。
• Check 重构: 移除硬编码的 git 和 gh 命令；GitHub Operations 精简为纯约束规则。
• Read: defuddle.md 升为首选抓取代理，r.jina.ai 作为备用。
• Statusline: 安装脚本现在检测已有 statusline 并在覆盖前提示确认（默认 Y）。
• 重命名: health agents 改为 inspector-context/inspector-control，与 reviewer-* 命名风格一致；verify.sh 改为 run-tests.sh；english-coaching.md 改为 coaching-en.md。

Update: npx skills add tw93/Waza@latest  ·  ⭐ github.com/tw93/Waza

V3.0.0 Forge 💂‍♀️

English Changelog

• Version Unification: all 8 skills moved to a single version 3.0.0 for collection-level consistency.
• Rationalization Watch: /hunt now includes a named table of 5 diagnostic-failure phrases ("I'll just try this one thing", "I'm confident it's X", etc.) with rebuttals that redirect back to evidence-based diagnosis.
• Condition-Based Waiting: /hunt Known Failure Shapes gains a new row for replacing fixed sleeps with condition polling (file exists, port responds, process exits).
• Verification Anti-Patterns: /check Verification section now lists 5 specific rationalization phrases ("should work now", "probably fixed", "I'm confident", etc.) as hard stops before claiming done.
• No-Placeholder Rule: /think Phase 3 now explicitly forbids TBD, TODO, "implement later", and similar placeholders in approved plans.

中文更新日志

• 版本统一: 全部 8 个 skill 统一升至 3.0.0，告别各自为政的版本号。
• 自我合理化警示表: /hunt 新增 5 条诊断失败的惯用借口（"就试这一个小改动"、"我有把握是 X"等），每条附上应对规则，防止在没有假设的情况下随机修改代码。
• 条件等待模式: /hunt 已知故障形态表新增"条件等待"行，替代固定时间 sleep，改为轮询状态（文件存在、端口响应、进程退出）。
• 验证反模式清单: /check 验证节点列出 5 个合理化短语（"应该好了"、"感觉没问题"等），出现任何一个即强制先跑验证命令再声明完成。
• 禁止占位符: /think Phase 3 明确禁止在已批准的计划中出现 TBD、TODO、"以后实现"等占位符。

---

Update: npx skills add tw93/Waza@latest · ⭐ Star on GitHub

V2.0.0 Waza 🎯

Why Waza

This started as claude-health: a single skill to audit Claude Code configuration. It worked well, and I kept adding more skills for the habits I use every day — debugging, design, writing, research, code review.

At some point I looked at tools like Superpowers and gstack. They are impressive, but they are heavy. Too many skills, too much setup, built for power users. Not the right fit for a younger engineer who just wants a clean, focused workflow.

So instead of growing claude-health into another heavy toolkit, I gave it a new name: Waza (技), the Japanese term for a technique practiced until it becomes instinct. Eight focused skills. Each one does one thing well. Nothing unnecessary.

---

English Changelog

• Rename: claude-health is now Waza, a full skill collection for the complete engineer.
• Skills: eight skills covering the core engineering workflow: /think, /design, /check, /hunt, /write, /learn, /read, /health.
• English Coaching: passive grammar correction shipped as a template, not a skill. One curl command adds it to any Claude Code setup.
• Progressive disclosure: large reference content extracted to supporting files for /english, /design, /read — SKILL.md stays thin and fast to load.
• AI usability: explicit AskUserQuestion gates, concrete verification commands, fixed placeholder text, and correct allowed-tools declarations across all skills.
• Descriptions: all descriptions trimmed to trigger-focused format, reducing constant context overhead.

中文更新日志

• 重命名: claude-health 正式升级为 Waza，覆盖完整工程工作流的 skill 合集。
• Skills: 八个技能覆盖核心工程习惯：/think、/design、/check、/hunt、/write、/learn、/read、/health。
• English Coaching: 被动英文纠错以模板形式发布，不再是 skill。一行 curl 命令即可添加到任意 Claude Code 配置。
• 渐进式加载: /design、/read 等 skill 的大型参考内容拆分到 references/ 子目录，SKILL.md 保持精简。
• AI 可用性: 所有 skill 补充了明确的 AskUserQuestion 节点、具体的验证命令、修正了占位符文本和 allowed-tools 声明。
• 描述精简: 所有描述改为触发条件格式，减少常驻上下文开销。

---

Update: npx skills add tw93/Waza@latest -g -y · ⭐ Star on GitHub