給目標職缺 JD + 你的 5 個實際工作事件，Claude 產出 5 組 STAR 格式的面試回答 — 面試前一晚準備、腦袋裡預演。
You are an executive interview coach specializing in [role_type] interviews. For each of the candidate's 5 actual work situations below, produce a STAR-format answer (Situation, Task, Action, Result) tailored specifically for the JD provided. Rules: (1) Situation — 2 sentences setting up context with enough detail to feel real, (2) Task — 1 sentence naming the specific responsibility on candidate's shoulders, (3) Action — 3 sentences describing what candidate specifically did (not "we", always "I"), (4) Result — 2 sentences with at least one number (metric, percentage, dollar amount, headcount), (5) Tie-back — 1 sentence connecting this to what the JD says they're looking for. Total length: ~150 words per answer. Do not fabricate metrics — if candidate provided "improved X by a lot", keep it qualitative and ask candidate to add numbers later. Output 5 answers with clear headers. <jd> [jd] </jd> <candidate_situations> [candidate_situations] </candidate_situations>
把方括號 [ ] 內的變數換成你的內容，丟進 Claude。
不用離開網站，直接看這組 prompt 跑出來長怎樣（AI 即時生成，扣 1 點）。
面試前一晚的必備準備。HR 會問「告訴我一次你 X 的經驗」 — STAR 格式是答題模板、不用即興。預先準備 5 個不同主題（領導、衝突、失敗、創新、跨團隊）可以涵蓋 80% 的行為面試題。Result 階段一定要有數字 — 沒數字就去挖原始資料找。
產出 5 組 150 字 STAR 答案、每組都連結到 JD 的特定需求、Action 段全用「我」不用「我們」、Result 有具體數字、Tie-back 收尾把經歷包裝給那家公司想聽的樣子。背熟後面試回答流暢。
以上為此 Prompt 丟進 Claude 後可得到的描述性成果，實際畫面會因填入的變數而有差異。
[role_type]職缺類型。例："senior product manager"、"VP of engineering"、"marketing director"
[jd]目標職缺 JD（直接從招募平台貼）
[candidate_situations]你的 5 個實際工作事件各 100 字摘要（不用很完整，重點是「我做了什麼、結果怎樣」）
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。
You are an executive interview coach specializing in [role_type] interviews. For each of the candidate's 5 actual work situations below, produce a STAR-format answer (Situation, Task, Action, Result) tailored specifically for the JD provided. Rules: (1) Situation — 2 sentences setting up context with enough detail to feel real, (2) Task — 1 sentence naming the specific responsibility on candidate's shoulders, (3) Action — 3 sentences describing what candidate specifically did (not "we", always "I"), (4) Result — 2 sentences with at least one number (metric, percentage, dollar amount, headcount), (5) Tie-back — 1 sentence connecting this to what the JD says they're looking for. Total length: ~150 words per answer. Do not fabricate metrics — if candidate provided "improved X by a lot", keep it qualitative and ask candidate to add numbers later. Output 5 answers with clear headers. <jd> [jd] </jd> <candidate_situations> [candidate_situations] </candidate_situations>
這組 prompt 專為 Claude 設計。把 prompt 內 3 個方括號 [變數] 換成你自己的內容，貼進 Claude 執行即可。難度中等，照變數說明填好後即可上手。
完整 prompt 免費開放閱讀，不用註冊；登入後可一鍵複製、收藏與留言。
prompt 文字本身你可自由使用與修改。但 AI 生成物（圖／音樂／影片／文字）的商用授權，取決於你在 Claude 使用的方案與其官方服務條款，請以該工具的授權規範為準。
Studio engineer 視角拆解 Suno 致命弱點（油炸 vocals、高頻 artifact）+ 4 步驟 DAW workflow + Suno Studio 修音 prompt
提案產生器 / 會議處理器 / 內容再利用 / 週五回顧 / 收工 reset — 試了 40 個只有這 5 個沒被丟掉、各省 30+ 分鐘 / 次。
適合：部落格、Medium、Notion 公開頁、Substack — 任何支援 iframe / HTML 嵌入的地方。對方點「看完整」會回到本站、是 prompt 庫的免費 backlink。
<iframe src="https://prompt.luvai.net/embed/claude-star-interview-answers" width="100%" height="380" frameborder="0" style="border:1px solid #e0dcd0;border-radius:4px;" loading="lazy" title="PromptCraft Embed"></iframe>
六個月在 Claude / GPT-4 / Gemini 上用人工 rater A/B 測 200+ prompt 後寫的。包含 persona+constraint stacking / anti-example / role reversal QA / cognitive scaffold / emotional priming / uncertainty CoT / steelman first。
一年的 role-play system prompt + 14-step framework 後總結：真正改變品質的是 5 個單行 prompt。沒有 role、沒有 markdown、沒有「you are an expert」。