STAR Interview Answer Bank Generator
Give Claude the target job description plus 5 real work incidents of yours, and it produces 5 STAR-format interview answers you can rehearse the night before the interview.
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>
Swap the variables inside the [ ] brackets for your own content, then paste into Claude.
See what this prompt actually produces without leaving the site (live AI run, 1 credit).
An essential prep step for the night before an interview. Interviewers ask 'tell me about a time you did X' — the STAR format is the answer template, so you don't have to improvise. Preparing 5 different themes (leadership, conflict, failure, innovation, cross-team work) covers about 80% of behavioral interview questions. The Result section must include a number — if you don't have one, dig through your records until you find it.
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。
A description of the intended result. Check this entry's testing notes and try the prompt with your own inputs.
[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>
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."