leoluyi

avoid-ai-writing-zh

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Extends the English-only avoid-ai-writing with an added Traditional-Chinese (Taiwan business usage) layer, so it handles English, Traditional Chinese, and mixed zh/en text. Use when asked to "remove AI-isms," "clean up AI writing," 「去除 AI 味」or「把中文改成人話」, or as a de-AI finishing pass before shipping English/mixed software-development docs — README, CONTRIBUTING, ADR, API docs, code comments. Also runs a detect-only structure-signals audit for a draft that carries no obvious AI-isms yet still reads as AI-written — uniform rhythm, no stance, no concrete examples, 「正確但沒有靈魂」— naming what is absent rather than rewriting for voice. It removes and flags AI patterns but does not create a voice — composing a blog or rewriting a draft into a human voice is blog-writing-zh's job, not this skill's.

avoid-china-writing

Audit and rewrite Traditional Chinese to remove mainland-China (PRC / 大陸) usage and convert it to Taiwan 正體中文 conventions across four axes — 陸用語詞彙 (視頻→影片、軟件→軟體、屏幕→螢幕、網絡→網路), 互聯網／職場黑話 (賦能、抓手、對齊顆粒度、閉環、落地、賽道、內卷), 簡體字殘留 (为／发／网／软／数据混入繁體), and 音譯與專名／語法差異 (奧巴馬→歐巴馬、悉尼→雪梨、硅谷→矽谷、通過→透過). Trigger when the user asks to 去除大陸／陸用語、改成台灣用語、正體中文在地化、抓簡體殘留、把互聯網黑話改成正常中文, or「這段有沒有大陸用詞」. Supports detect / rewrite / edit modes. Do NOT invoke for 去除 AI 味／潤飾語氣 (use avoid-ai-writing-zh), 結構化商業文件簽呈／報告 (use formal-doc-structure), RFP／需求規格書 (use rfp-writing), 白話文翻譯 (use plain-speak), casual chat, creative writing, or code comments. This skill localizes across the strait — an axis orthogonal to AI-ism cleanup.

blog-writing-zh

Write or rewrite Traditional Chinese (Taiwan) blog posts with a genuine human voice, modeled on seven studied blogs (知識倉鼠, 保哥, 高見龍, 90s.pm.investing, AI避坑情報員, Julia Evans, Simon Willison). Use when asked to 寫部落格文章／電子報／blog post, 把筆記改寫成文章, 把 Obsidian 筆記變成 blog, 翻譯改寫外文文章／演講／討論串成中文長文, or "用我的風格寫一篇 X", or 不確定該用什麼風格寫（本 skill 會依讀者與目的推薦配方）. Supports two modes — compose (from a topic or loose material) and rewrite (from an Obsidian note, translation source, or draft) — and three technical-description modes (操作型可重現教學, 概念型心智模型導讀, 推演型原理解說) with actionability and concept-clarity checklists — plus composable voice axes (opening strategy × persona intensity × metaphor density × closing move) with presets, an optional dual-draft mode (write two deliberately divergent drafts, then merge the strengths) for long or high-stakes pieces, a selectable length tier (短打/標準/深文/工具書級), and an automatic post-draft check that suggests splitting into a series (with outline) when one piece can't hold the material. Output is always the ar

Data & Documents Solid

briefing-outline

說明提綱 (briefing outline) writing — distill detailed source material into one high-altitude overview that gives each part its purpose and essence, then points down for the detail. Source count is not the point: it works over several documents or one long report (pointing down to its sections). Use when the user wants to 整理／撰寫一份說明提綱, condense one or more sources into a navigable briefing for a 主管 or 委員會, summarise a long report into a high-altitude overview that points down for detail, or re-sync an existing 提綱 after its sources changed. Do NOT invoke to author a single formal document from scratch — 簽呈/會議紀錄/報告/專案規劃 (use formal-doc-structure), for RFP / 需求規格書 / 招標規格 (use rfp-writing), for lowering one term or passage to a non-technical audience (use plain-speak), or for pure language cleanup (use avoid-ai-writing-zh). This skill sits above the source material and points down into each part.

API & Backend Solid

formal-doc-structure

Draft, revise, or restructure formal internal business documents in Traditional Chinese (Taiwan corporate / financial-institution usage) — 簽呈, 會議紀錄, 評估報告, 專案規劃, 採購與廠商溝通, 對主管簡報, 驗收與交付, 跨單位協調. Picks a reader-driven structure per document type and produces a usable draft, not just advice. Trigger when the user asks to write or fix an internal business document, memo, report, meeting record, plan, or vendor communication. Do NOT invoke for RFP / 招標規格 / 需求規格書 (use rfp-writing), for pure language cleanup with no structural work (use avoid-ai-writing / clean-ai-writing), or for casual chat, creative writing, marketing copy, or code comments.

Data & Documents Solid

infographic-design

Design polished, professional explanatory graphics as SVG or single-file HTML. Use when the user asks for an infographic, 資訊圖表, 懶人包, 圖解, a one-pager, a visual summary, or a timeline/comparison/process ("how it works") graphic — even without the word "infographic" — and to review an existing one ("幫我看這張圖表哪裡可以改"). Use for a learning recap when a teaching dialogue ends ("學習總結成一張圖", "visual recap of what you taught me"); that route needs no further prompting. Also use when another skill needs a figure designed for a document it is producing. Do NOT invoke for a single standalone chart embedded in analysis output, for dashboards / BI tooling, for slide decks (use a pptx workflow), for explaining a term in plain language (use plain-speak), or for data-dense charts where the numbers are themselves the subject or precise scales matter (annual-results decks, survey findings, statistical graphics) — hand those to a data-visualization workflow. An explicit ask for an infographic / 資訊圖表 / 懶人包 / one-pager always qualifie

knowledge-doc-writing

把自學或研究一個技術主題的成果，整理成一份包含四個清楚分離 Diátaxis 區塊的知識文件——tutorial（帶著上手）、 how-to（照著完成任務）、reference（查參數與結構）、explanation（What/Why 論述與取捨決策）；用 compass 兩問把每段素材路由到對應區塊，素材撐得起才寫，撐不起的型（研究過但未實作常缺 tutorial/how-to）明列為缺口，不捏造、不搭空殼（繁體中文為主、術語保留英文）。觸發：使用者要把對話紀錄、官方文件或原始資料、或從零研究的主題（強制查一手來源並標 as-of 時效）消化成可長期參考的技術文件；或改寫一份既有技術文件——依意圖分流：更新時效／��入新素材→定點修補保留原形，重整／重構→依 compass 重建四型區塊。可接在 learn-loop 之後： learn 管互動學習迴圈與親手 distillation（鐵律：distillation 是學習本身，不代寫），本 skill 只接手 distill 完成後重新組織、補讀者上下文、套完稿檢查。不要用於：公司內部簽呈／會議紀錄／評估報告等行政文件（用 formal-doc-structure，即使輸入是既有文件也不因此轉入本 skill）、RFP／招標規格（用 rfp-writing）、部落格文章（用 blog-writing-zh）、只做語言層去 AI 味不動結構（用 avoid-ai-writing-zh）、只要口頭白話解釋不產文件（用 plain-speak）、learn 的互動學習迴圈本身（用 learn-loop）。

plain-speak

Translate technical jargon, code concepts, or dense engineering text into plain language a non-technical colleague or manager can follow. Use when the user asks to "explain in plain language", "白話文", "翻成人話", "用白話解釋", "explain like I'm a PM", "make this non-technical", "simplify this term", "what does this term mean", or pastes technical text and asks for a business-audience version, or asks you to review/check whether an existing plain-language draft lands for a non-technical reader ("這樣夠白話嗎", "幫我看非技術主管看不看得懂", "is this clear enough for a PM"). Reply in the language the user wrote in. Do NOT invoke for removing AI-isms / 潤飾語氣 from existing prose (use avoid-ai-writing-zh), for structuring a whole formal business document — 簽呈/會議紀錄/報告 (use formal-doc-structure), or for RFP / 需求規格書 / 招標規格 (use rfp-writing). This skill lowers the audience, not the voice, the structure, or the document type.

rfp-writing

Write or review technical RFP documents from the issuer's perspective in Traditional Chinese (需求規格書 / 需求規劃書 / 招標規格), enforcing structural rules for redundancy elimination, appendix bloat, thin-section consolidation, and formal plain-language style. Trigger only when the user explicitly asks for an RFP; do not invoke for migration plans, runbooks, ADR/ARB, design docs, meeting minutes, vendor-side bid proposals (投標提案 / RFP responses), or general formal Chinese writing — those conventions conflict with RFP rules.

AI & Automation Listed

learn-loop

Leo 的結構化學習迴圈（先教後考 + 來源查證），把一個新概念精煉成 Obsidian vault 的知識結晶。僅在 Leo 明確叫用（Claude Code `/learn-loop`、Codex `$learn-loop`，或明說「跑 learn-loop 流程學 X」）時啟動；不要因為對話中提到想了解某事就自動觸發 —— 這是刻意的、會佔用整段對話的六步互動流程。