Meeting Transcript Cleanup: Decisions, Action Items, Absentee Summary
Use this right after any speech-to-text tool: paste the transcript and get a formal record, a list of decisions, an action-item table with "Owner/Deadline/Dependencies," and a 3-line summary for people who missed the meeting. It handles transcription typos and mixed Chinese-English text, flags any deadline that wasn't actually stated as "to be confirmed," and doesn't make things up.
你是專業會議紀錄師，擅長把 AI 轉出來的逐字稿（常有辨識錯字、中英夾雜、閒聊）整理成可以直接發出去的正式紀錄。 會議資訊：[會議名稱與日期] 逐字稿：[逐字稿全文] 請輸出以下四個區塊： ## 會議紀錄 會議目的一句話＋3-6 條重點討論脈絡（誰主張什麼、最後怎麼收斂） ## 決議事項 條列、每條註明「拍板者」 ## 待辦事項 表格：負責人｜事項｜期限｜依賴項。負責人或期限在逐字稿裡沒講到的、填「待確認」、並在表格下方列出「會後需要追認的問題」 ## 給缺席者的 3 行摘要 三句話讓沒參加的人知道：結論是什麼、跟他有關的是什麼、需要他做什麼 品質準則：閒聊和重複發言直接略過、不要逐句摘要；專有名詞或人名疑似語音辨識錯誤時，保留原文並在後面加（？）標註；中英夾雜的發言統一整理成通順中文、保留必要的英文術語；禁止替任何人補上他沒說過的承諾或期限。
Swap the variables inside the [ ] brackets for your own content, then paste into ChatGPT / Claude / Gemini.
See what this prompt actually produces without leaving the site (live AI run, 1 credit).
Transcription tools can already convert speech to text, but someone still has to bridge the gap from "raw transcript" to "record you can actually send out" — this prompt is that bridging layer, and it works with output from NotebookLM, CLOVA Note, or any speech-to-text tool. The "3-line summary for absentees" section is the most appreciated part in practice — perfect for pasting straight into a group chat. If the transcript is too long, paste it in sections, telling it upfront "there's more coming, hold off on output" for the first half. The most important safeguard is banning it from filling in deadlines: the model loves to invent a plausible date for an action item that never had one stated, and sending that kind of record out causes real problems.
[會議名稱與日期]例：「Q3 產品線檢討會、2026/6/10、與會：產品部＋業務部」
[逐字稿全文]錄音轉文字工具的輸出直接貼上、不用先整理
填下面的欄位，上方 prompt 會即時替換 [方括號] 內容。填好後按「複製組好的 prompt」直接丟進工具。
你是專業會議紀錄師，擅長把 AI 轉出來的逐字稿（常有辨識錯字、中英夾雜、閒聊）整理成可以直接發出去的正式紀錄。 會議資訊：[會議名稱與日期] 逐字稿：[逐字稿全文] 請輸出以下四個區塊： ## 會議紀錄 會議目的一句話＋3-6 條重點討論脈絡（誰主張什麼、最後怎麼收斂） ## 決議事項 條列、每條註明「拍板者」 ## 待辦事項 表格：負責人｜事項｜期限｜依賴項。負責人或期限在逐字稿裡沒講到的、填「待確認」、並在表格下方列出「會後需要追認的問題」 ## 給缺席者的 3 行摘要 三句話讓沒參加的人知道：結論是什麼、跟他有關的是什麼、需要他做什麼 品質準則：閒聊和重複發言直接略過、不要逐句摘要；專有名詞或人名疑似語音辨識錯誤時，保留原文並在後面加（？）標註；中英夾雜的發言統一整理成通順中文、保留必要的英文術語；禁止替任何人補上他沒說過的承諾或期限。
Suno Engineer's Mindset: 4 Steps to a Song That Doesn't Sound Like AI
A studio engineer's breakdown of Suno's fatal weaknesses (fried vocals, high-frequency artifacts), plus a 4-step DAW workflow and a Suno Studio cleanup prompt.
5 Claude Weekly Workflows That Stuck After 6 Months
Proposal generator / meeting processor / content repurposer / Friday review / shutdown reset — out of 40 I tried, only these 5 survived, each saving 30+ minutes per run.
7 Cross-Model A/B-Tested Prompt Techniques (Not Vibes)
Written after six months of A/B testing 200+ prompts on Claude, GPT-4, and Gemini with human raters. Covers persona + constraint stacking, anti-examples, role-reversal QA, cognitive scaffolds, emotional priming, uncertainty CoT, and steelman-first.
5 trust-checking one-liner prompts (no role-play)
After a year of role-play system prompts and 14-step frameworks, here's the takeaway: the thing that actually moved the needle on quality was 5 one-line prompts. No roles, no markdown, no "you are an expert."