Claude prompts for data scientist job searches

I am applying for the data scientist role below. Rewrite my resume so it speaks to this posting, using only what is already in my resume. Do not invent methods, tools, datasets or business impact. Where the posting asks for something I have no evidence of (for example causal inference, a specific SQL dialect, or experimentation at scale), put it in a "Gaps" list rather than in the resume. Output three things: a table with the columns requirement, evidence from my resume, rewritten bullet; a revised one-page resume in plain text where each bullet names the method, the data and the outcome; and the Gaps list with an honest one-line answer I could give if asked about each. Keep every job, title and date as it is.

Job description:
[paste job description]

My resume:
[paste your resume]

Write a cover note of at most 120 words for the data scientist role below. Use only facts from my resume and my notes; no invented results, no "passionate", no "perfect fit". Structure: one sentence that shows I understand what this team measures or decides (draw it from the job description), two sentences on one analysis or model I delivered and the decision it changed, with the number if my resume has one, and one sentence with a specific ask. Also give a 50-word version I can send as a LinkedIn message to the hiring manager. Sentence case, no exclamation marks, no bullet points.

Job description:
[paste job description]

My resume:
[paste your resume]

Why this role, in my words:
[two or three lines]

Act as the interviewer for a 45-minute data scientist screen at the company below. Ask one question at a time and wait for my answer. Cover, in order: two SQL questions on a small schema you define first (one with a join and aggregation, one with a window function), two statistics questions in the style of this role (for example interpreting a p-value, choosing a test, the difference between confidence intervals and prediction intervals, or why a metric moved), and one metrics question about the company's product (define a north star metric and its guardrails). After each answer, score it from 1 to 5, give the answer a strong candidate would give, and name the one thing I should have said. Finish with three topics to review tonight and why.

Job description:
[paste job description]

My resume:
[paste your resume]

Run a data science case interview with me for the role below. Choose a scenario that fits the company (for example a drop in a key metric, whether to launch a feature, or how to measure a new pricing page) and describe it in three sentences. Then walk me through it one question at a time and wait for my answers: clarifying the goal and the decision, defining the metric and guardrails, forming hypotheses, choosing between an experiment and observational analysis, sample size and duration, confounders and segmentation, and how I would present the result to a non-technical stakeholder. After each step, tell me what a strong candidate would have mentioned that I did not. End with a one-page summary of the case in my own corrected words, plus two follow-up questions an interviewer might use to push back.

Job description:
[paste job description]

What I know about the product:
[a few lines]

Help me prepare behavioral answers for a data scientist interview using only the situations I describe below. Do not add details; where a story lacks a number, a timeline or an outcome, ask me rather than inventing one. First list the eight questions most likely for this role and company (a stakeholder who disagreed with your analysis, a result that was wrong, ambiguity in the ask, prioritizing between requests, explaining something technical to executives, a project that got canceled, a mistake you owned, influencing a decision without authority). Then match each to one of my stories and write an answer of 150 to 200 words shaped as situation, what I did, the result, what I learned. Flag where I reuse the same story so I can spread them across questions.

Job description:
[paste job description]

My stories, rough notes are fine:
[three to five real situations]

Turn my notes below into a portfolio write-up of 500 to 700 words about a data science project, in the first person and plain language, for a hiring manager who has five minutes. Use only what is in my notes. Where something important is missing (the question, the data size and source, the method, the result with a number, the decision it informed, the caveats), insert a placeholder in square brackets and list all placeholders at the end. Structure: the question and who was asking, the data and what was wrong with it, the approach and the simpler approach I rejected, the result, what I would caveat, and what happened next. Add a suggested title, a two-sentence summary for the top, and three resume bullets that describe this work honestly.

Project notes:
[paste notes, notebook markdown, or a rough description]

I have an offer for a data scientist role. Below are the offer, my current compensation, any competing offers, and what I have found from public salary sources. Help me evaluate it and negotiate honestly. Do not make up market numbers; if you need one I have not given, tell me exactly what to look up. Output: (1) four-year total compensation under a cautious and an optimistic equity assumption, as a table; (2) the two or three components most worth negotiating here and why; (3) a short script for the conversation that names a specific number, gives a reason grounded in my experience, and stays collaborative; (4) questions to ask before accepting: the level, the vesting schedule, the review cycle, how the team is measured, and what the first project is. Keep the whole thing under 500 words.

Offer:
[base, bonus, equity and vesting, signing bonus, location]

My situation:
[current compensation, competing offers, constraints]

Write a 30/60/90-day plan for me as a new data scientist on the team below. Make it realistic for someone who has to learn the data warehouse, the metric definitions and the stakeholders before producing anything trusted. Days 1 to 30: which tables and dashboards to learn, which people to meet, which existing analyses to read, and a small question I could answer to learn the data. Days 31 to 60: one useful deliverable, for example a metric audit, a fixed dashboard or a quick analysis a stakeholder has been waiting for. Days 61 to 90: a measurable project with a success criterion and its risks. For each block, list three to five outcomes rather than activities, and one question to ask my manager in week one to validate the plan. Mark assumptions I should verify. Under 450 words.

Job description:
[paste job description]

What I learned about the team in interviews:
[notes]

Give me an experiment design drill for a data scientist interview at the company below. Present one realistic product change (for example a new onboarding step, a ranking change or a pricing test) in three sentences. Then ask me, one at a time and waiting for each answer: what the primary metric is and why, what the guardrail metrics are, what the unit of randomization is and what could break it, how I would estimate sample size and duration given a minimum detectable effect I choose, what novelty or network effects could bias the result, how I would handle a peeking problem, and what I would recommend if the primary metric is flat but a guardrail moved. After each answer, tell me what I missed and give the version a strong candidate would give. Finish with a short checklist I can reuse for any experiment question.

Job description:
[paste job description]

What I know about the product:
[a few lines]