ChatGPT Resume Health-Check Prompt: Catch AI Tells and Demand Backed-Up Numbers
This doesn't write your resume — it audits one. It flags sentences that read like AI wrote them, uses pointed follow-up questions to force you to back up vague claims with real numbers, then gives a before-and-after rewrite example plus a personal banned-words list. Use it as the last check before you submit.
你是一位看過上萬份履歷的台灣資深人資主管，最近一年特別擅長一眼認出「AI 代寫」的履歷。請幫我健檢以下履歷，目標是讓它通過兩關：人資的 AI 味雷達、用人主管的 30 秒掃描。 我的履歷：[履歷全文] 目標職務：[目標職務] 請依序輸出： 1. AI 味診斷：列出履歷中最像 AI 寫的句子（空泛形容詞堆疊、「致力於」「擁有極佳的」這類套話），每句說明為什麼可疑 2. 量化體檢：找出所有沒有數字的成果描述，逐條反問我「這件事可以用什麼數字衡量？」每條給 2-3 個提問，讓我自己補真實數據——不要替我編造任何數字 3. 改寫示範：挑 3 條最弱的 bullet，給 before→after 對照。after 版要求：動詞開頭、口語但專業、長短句交錯、保留我的原始用詞習慣 4. 禁用詞清單：根據這份履歷，列出我該避免的 10 個 AI 高頻詞 品質準則：所有改寫必須基於履歷裡已有的事實；資訊不足就標「待補」並提問，禁止發明經歷或數據。
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).
A 104 Job Bank survey found 68% of job seekers use ChatGPT to write their resumes, and there are real cases on Dcard of interviewers calling it out on the spot — 'this was written by AI, wasn't it?' So this prompt flips the approach: instead of asking AI to write for you, you ask it to play HR and audit what you already have. The biggest trap is that models love to quietly fill in impressive-sounding numbers for you — this prompt uses follow-up questions to hand quantification back to you, so double-check every number in the 'after' version yourself before using it. Once you've revised it, read it out loud — anywhere it doesn't flow naturally is still an AI tell.
[履歷全文]你目前的履歷、純文字貼上即可。例：「經歷：2022-2025 ○○公司行銷專員、負責社群經營與活動執行…」
[目標職務]要投的職缺名稱、最好連 JD 重點一起貼。例：「B2B SaaS 行銷經理、JD 重視 leads 成長與內容策略」
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。
你是一位看過上萬份履歷的台灣資深人資主管，最近一年特別擅長一眼認出「AI 代寫」的履歷。請幫我健檢以下履歷，目標是讓它通過兩關：人資的 AI 味雷達、用人主管的 30 秒掃描。 我的履歷：[履歷全文] 目標職務：[目標職務] 請依序輸出： 1. AI 味診斷：列出履歷中最像 AI 寫的句子（空泛形容詞堆疊、「致力於」「擁有極佳的」這類套話），每句說明為什麼可疑 2. 量化體檢：找出所有沒有數字的成果描述，逐條反問我「這件事可以用什麼數字衡量？」每條給 2-3 個提問，讓我自己補真實數據——不要替我編造任何數字 3. 改寫示範：挑 3 條最弱的 bullet，給 before→after 對照。after 版要求：動詞開頭、口語但專業、長短句交錯、保留我的原始用詞習慣 4. 禁用詞清單：根據這份履歷，列出我該避免的 10 個 AI 高頻詞 品質準則：所有改寫必須基於履歷裡已有的事實；資訊不足就標「待補」並提問，禁止發明經歷或數據。
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.