article-writing
依範例或品牌語氣寫長篇文章，用證據開頭、刪掉 AI 腔套話
中文翻譯
--- name: article-writing description: 依使用者提供的範例或品牌指引，以有辨識度的語氣撰寫文章、指南、部落格、教學、電子報和其他長篇內容。使用者需要超過一段、經過潤飾的書面內容時使用，尤其是語氣一致性、結構和可信度很重要的時候。 metadata: origin: ECC --- # 文章寫作 寫出聽起來像真人、有自己觀點的長篇內容，而不是 LLM 把自己磨成一坨糊。 ## 何時啟用 - 起草部落格文章、隨筆、發表文、指南、教學或電子報 - 把筆記、逐字稿或研究整理成潤飾過的文章 - 從範例比對既有的創辦人、營運者或品牌語氣 - 收緊已經寫好的長篇文案的結構、節奏和佐證 ## 核心規則 1. 從具體的東西開頭：成品、範例、輸出、軼事、數字、截圖或程式碼。 2. 先給範例，再解釋，不要反過來。 3. 句子要精簡，除非原本的語氣就是刻意鋪陳。 4. 用證據，不用形容詞。 5. 絕對不要捏造事實、可信度或客戶證據。 ## 語氣處理 如果使用者想要特定的語氣，先執行 `brand-voice`，並重複使用它產出的 `VOICE PROFILE`。 除非使用者明確要求，否則不要在這裡重複做第二輪風格分析。 如果沒有提供語氣參考，預設用犀利的實務者語氣：具體、不煽情、有用。 ## 禁用的寫法 下面任何一種，都要刪掉重寫： - "In today's rapidly evolving landscape" - "game-changer"、"cutting-edge"、"revolutionary" - "here's why this matters" 這種單獨當橋段用的句子 - 假的脆弱坦白橋段 - 只為了衝互動而加的結尾問題 - 對論點沒有推進的自傳式灌水 - 拖延重點的、一般 AI 式的清喉嚨開場 ## 寫作流程 1. 釐清讀者和目的。 2. 建立紮實的大綱，每個段落只負責一件事。 3. 每個段落都從證據、成品、衝突或範例開始。 4. 只在下一句值得佔篇幅的地方才展開。 5. 刪掉任何聽起來像套公式、過度解釋或自我感覺良好的內容。 ## 結構指引 ### 技術指南 - 開頭先說讀者會得到什麼 - 主要段落要放程式碼、指令、截圖或具體的輸出 - 用可執行的重點收尾，不要軟綿綿的回顧 ### 隨筆 / 評論 - 從張力、矛盾或具體的觀察開始 - 每個段落只維持一條論述主線 - 讓意見接受證據的檢驗 ### 電子報 - 讓第一個畫面就在做實事 - 不要把日記式的填充內容放在最前面 - 只有在能改善掃讀性的時候才用段落標籤 ## 品質關卡 交付之前： - 事實性的主張都有提供的來源支撐 - 一般 AI 式的轉場都不見了 - 語氣符合提供的範例或約定的 `VOICE PROFILE` - 每個段落都帶來新的東西 - 格式符合預定的媒介
英文原文
--- name: article-writing description: Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter. metadata: origin: ECC --- # Article Writing Write long-form content that sounds like an actual person with a point of view, not an LLM smoothing itself into paste. ## When to Activate - drafting blog posts, essays, launch posts, guides, tutorials, or newsletter issues - turning notes, transcripts, or research into polished articles - matching an existing founder, operator, or brand voice from examples - tightening structure, pacing, and evidence in already-written long-form copy ## Core Rules 1. Lead with the concrete thing: artifact, example, output, anecdote, number, screenshot, or code. 2. Explain after the example, not before. 3. Keep sentences tight unless the source voice is intentionally expansive. 4. Use proof instead of adjectives. 5. Never invent facts, credibility, or customer evidence. ## Voice Handling If the user wants a specific voice, run `brand-voice` first and reuse its `VOICE PROFILE`. Do not duplicate a second style-analysis pass here unless the user explicitly asks for one. If no voice references are given, default to a sharp operator voice: concrete, unsentimental, useful. ## Banned Patterns Delete and rewrite any of these: - "In today's rapidly evolving landscape" - "game-changer", "cutting-edge", "revolutionary" - "here's why this matters" as a standalone bridge - fake vulnerability arcs - a closing question added only to juice engagement - biography padding that does not move the argument - generic AI throat-clearing that delays the point ## Writing Process 1. Clarify the audience and purpose. 2. Build a hard outline with one job per section. 3. Start sections with proof, artifact, conflict, or example. 4. Expand only where the next sentence earns space. 5. Cut anything that sounds templated, overexplained, or self-congratulatory. ## Structure Guidance ### Technical Guides - open with what the reader gets - use code, commands, screenshots, or concrete output in major sections - end with actionable takeaways, not a soft recap ### Essays / Opinion - start with tension, contradiction, or a specific observation - keep one argument thread per section - make opinions answer to evidence ### Newsletters - keep the first screen doing real work - do not front-load diary filler - use section labels only when they improve scanability ## Quality Gate Before delivering: - factual claims are backed by provided sources - generic AI transitions are gone - the voice matches the supplied examples or the agreed `VOICE PROFILE` - every section adds something new - formatting matches the intended medium