Agent skills that write Traditional Chinese like a real person寫出像真人正體中文的 agent 技能

Catches the tells that make English and Traditional Chinese read as machine-written, then rewrites them into human prose揪出讓中英文讀起來像機器寫的破綻，改回像人講話的樣子

Strips mainland-China wording, jargon, and leaked Simplified from Traditional Chinese and rewrites it into natural Taiwan usage without over-correcting real terms把混進來的陸用語、簡體字和互聯網黑話，改回台灣讀者習慣的正體中文，又不誤傷真正的術語

Turn a technical term, snippet, or dense paragraph into one line your PM, exec, or customer can actually repeat back把術語、程式碼、工程長文翻成非技術主管聽得懂、還能複述的一句話

Turn notes, a talk, or a bare topic into a Taiwan-Chinese blog post that reads like a real person wrote it把筆記、演講或一個題目，寫成有立場、有親身經歷、讀起來像真人的繁中部落格文

Distill one long report or many docs into a high-altitude 說明提綱 a manager can grasp, then drill into把厚重的來源文件收斂成一份高空俯瞰的說明提綱，讓主管一眼掌握全貌、需要時再往下鑽

Turns a rough ask into a ready-to-circulate 簽呈, 會議紀錄, or 評估報告 with the structure its reader actually needs把粗略需求變成可直接送簽的簽呈、會議紀錄或評估報告，結構跟著讀者的決策需求走

Draft and review technical RFPs from the issuer's side, cutting redundant sections, appendix bloat, and AI filler站在招標方立場撰寫與審查技術 RFP，砍掉重複章節、附錄灌水與 AI 填充語

Advise on a presentation one node at a time — positioning, structure, headlines, storyline, opening, closing, delivery, layout — with current cross-session state and each node's artifact on disk so the next one picks up where it left off像顧問一樣一次做一個節點：溝通定位、骨架定形、主張式標題、敘事編排、破題定錨、收束提請、口說轉譯、逐頁診斷，保留跨 session 狀態與每個節點的檔案產出，下一個節點直接接手

Turn a topic or source bundle into a complete slide-by-slide Markdown deck with an argument, assertion-style titles, full on-slide copy, evidence notes, and speaker notes把主題或素材寫成完整的逐頁簡報 Markdown，包含論證、主張式標題、投影片內文、來源註記與講者備註

Design-system-grade explanatory graphics — timelines, comparisons, process diagrams — as clean, self-contained SVG or a single HTML file. Language-agnostic; built to be saved and reshared設計系統級的說明圖表（時間軸、比較、流程圖），輸出成乾淨、可獨立開啟的 SVG 或單一 HTML 檔案。跨語言通用，為收藏轉發而生

Engineering-grade knowledge docs on the Diátaxis model — tutorial, how-to, reference, explanation — writing only what the material supports and flagging the gaps honestly. A discipline that travels across domains以 Diátaxis 模型寫工程等級的知識文件（tutorial、how-to、reference、explanation），素材撐得起才寫，缺口據實標出。這套紀律跨領域通用

Create structured visual work from requirements or restyle existing work while preserving requested content從需求建立結構化視覺化作品，或保留指定內容重新設計既有作品

Removes prose about the artifact, reading path, page role, and commissioning context while preserving evidence and real instructions移除文件自述、閱讀導引、頁面角色與委託脈絡，同時保留來源引用與實際操作指示

Review rendered visual artifacts against one fail-closed delivery standard以單一且無法驗證就不放行的標準，檢查視覺成品的實際呈現

Turn any topic into a one-screen HTML picture explainer: big visuals, very few words, no jargon把任何主題變成一頁式 HTML 圖解：畫面大、字少、零術語

Get taught and quizzed on a concept, then write the note yourself while it verifies sources and files it into your Obsidian vault先教後考，筆記你親手寫，它負責查證來源、挑洞、歸檔進 Obsidian

Search, create, and link notes in an Obsidian vault that stays on PARA / Johnny-Decimal structure and wikilinks在 Obsidian 筆記庫搜尋、新增與串連筆記，維持 PARA 結構

Think through a question neither of you can answer yet — widen the options, label what's found vs guessed, attack the load-bearing assumptions, and leave a record that says what would overturn it陪你想一個雙方都還沒有答案的問題：先展開選項，標出哪句是查到的、哪句是猜的，再拆掉承重假設，留下一份寫明「什麼會推翻它」的紀錄

Pull a deleted Claude Desktop/claude.ai conversation and its artifacts back out of the Chromium cache before it's evicted在 Chromium 快取被清掉之前，把刪除的 Claude Desktop／claude.ai 對話與產出檔案救回來

Turn a rough plan into a bounded goal with machine-checkable done conditions, before an autonomous run burns tokens on a vague target在 agent 自己跑起來之前，把粗略的計畫變成有邊界、完成條件機器可驗的 goal，別讓它對著模糊目標燒 token

Interview a fuzzy task into a six-element goal prompt an agent can run for hours without drifting or wrapping up early把講不清楚的任務訪談成六元素 goal prompt，讓 agent 自己跑好幾個小時也不偏離、不提早收工

Hand over the whole job: orchestrate subagents, self-repair on a budget, pass a verification gate, then commit, push and open a PR without checking back整份工作交出去：以 subagent 為主力執行、故障自修有次數上限、過驗證閘門後 commit、push、開 PR，全程不回頭問

Lay every case out in full before evaluating any of them, split the problem into decisions only you can make, then wait — recommendation comes last先把每個情況完整攤開再評估，把問題拆成只有你能拍板的決策，然後停住等你回答，建議放到最後

Re-ask whatever is pending as tappable choices, then keep every direction decision clickable for the rest of the session把懸而未決的問題改成可點選的選項重問一次，之後整段對話遇到方向決策都給你點

Mine your rejections of AI output and distil the standard behind them into a reusable 1-5 rubric, in Markdown and in JSON for an evaluator agent從你退掉、重寫 AI 產出的實例裡挖出背後的標準，蒸餾成可重複使用的 1-5 分 rubric，同時給 Markdown 和 evaluator 用的 JSON

Take a rough brief through documented grilling to one developer spec, one runnable sample, and end-to-end proof把初始需求逐題問清楚，收斂成一份開發者技術規格、一套可執行 sample 與 end-to-end 證據