Your cart is empty
Add prompt packs to continue
This definitive collection for Data Analysts has been designed as the master resource for professionals seeking to master the entire data lifecycle, from raw ingestion to strategic value delivery. Each section addresses real technical challenges in today's market, providing precise frameworks to optimize highly complex SQL queries, design robust data architectures under the Kimball methodology, and run advanced statistical analyzes with Python. By integrating this repository of prompts into their workflow, the analyst not only automates repetitive cleaning and ETL tasks, but also increases their storytelling capacity, translating complex metrics into actionable business decisions. It is the essential tool to ensure technical accuracy in production environments and excel in senior selection processes through expert resolution of case studies and architectural challenges.
100 resources included
He acts as a Senior Data Analyst and Growth Retention Specialist with more than 15 years of experience in user behavior analysis. Your mission is to design a comprehensive and technical "Customer Journey Mapping" for the product/service [Product Name] operating in the [Sector/Industry] market. The central objective of this mapping is to dissect each user interaction to identify conversion leaks and critical retention opportunities that directly impact CLV (Customer Lifetime Value) and MRR (Monthly Recurring Revenue). To begin, structure the analysis under the AARRR (Pirate Metrics) framework, but with a surgical focus on post-acquisition retention. For each stage (Awareness, Acquisition, Activation, Retention, Referral and Revenue), you must define: 1. Digital and analog Touchpoints. 2. Measurable User Actions. 3. Specific success metrics (KPIs such as Time to Value, Stickiness Ratio, or Feature Adoption Rate). 4. Pain points or frictions identified in the data [Analytical Tools used, e.g. Mixpanel, Amplitude, GA4]. Delve into the cohort analysis for this mapping. I need you to identify the behaviors predictive of churn (Churn Signals). Analyze how users who interact with the [Key Feature] functionality in its first [X] days have a [Y]% higher retention rate. Cross-reference this information with the [Segmentation Variables: Geography, Subscription Plan, Device] segments to create a profitability heat map by user type. Conclude the prompt by generating a 'Proactive Intervention Strategies' section. Based on the designed journey map, propose 3 high-impact A/B experiments to reduce churn in the [Critical Stage phase, e.g. Onboarding]. Each experiment should include a data-driven hypothesis, the primary metric to move, and the estimated impact on 90-day retention. The output must be a detailed technical report, structured and ready to be presented to C-Suite level stakeholders.
Act as a Senior Data Engineer with extensive experience in modern data architectures such as Medallion (Bronze, Silver, Gold) and Data Lakehouse. Your mission is to design a robust and scalable ETL process under the concept of "Stage Layer Transformation", whose main objective is the transition of raw data from the landing zone (Landing) to a technical and clean Staging layer (Silver). You must process the information coming from [Data Source], which is originally delivered in [Source Format]. The process must perform extensive cleanup that includes standardizing data types, normalizing headers under the [Naming Convention] standard, and resolving encoding conflicts. It is vital that the design ensures data integrity before any business logic is applied in subsequent layers. Implements a deduplication strategy based on [Identifier Key], ensuring that only the most recent or valid records are persisted in the Stage layer. For change management, it uses incremental loading logic through [Update Date Field], optimizing the use of computational resources. If records do not comply with the predefined schema in [Target Schema], they should be automatically redirected to an exception table or 'Dead Letter Queue' for auditing. The resulting code must be written in [Programming Language or SQL] and be compatible with the [ETL Tool or Framework] environment. Be sure to include error handling blocks, logging metrics (logs) of how many records were read, transformed and rejected, and a final data quality validation that compares the totals against the original source. The code must be modular, parameterized and follow Clean Code principles to facilitate its long-term maintenance. As a final delivery, it provides the complete transformation script, a visual schematic descriptive of the data flow (in Markdown or text format) and a deployment guide that considers the defined [Load Frequency]. Briefly justify why the applied transformations reduce technical debt in the final data analysis for the Data Analyst role.
Acts as a Senior Data Analyst expert in Growth Marketing and Customer Retention. Your mission is to run a comprehensive monthly cohort analysis using the transaction/user data set I will provide below: [Insert Dataset or Data Description]. The main objective is to break down user behavior from their first month of acquisition to their current lifecycle, identifying critical churn patterns and Customer Lifetime Value (LTV) optimization opportunities. First, generate a user retention matrix where the rows represent the 'Acquisition Month' (Cohort) and the columns represent the 'Nth month' of the customer's life. The values within the matrix should show both the absolute number of active users and the retention percentage relative to the initial size of each cohort. Specifically analyze whether there is a significant drop (Churn Cliff) in the first [Number of Months, e.g. 3 months] and compare the performance of cohorts captured during [Specific Season or Campaign] versus standard organic cohorts. Secondly, it performs a cost-effectiveness analysis by cohort. Calculate the monthly Average Revenue Per User (ARPU) for each group and determine the cumulative LTV. Compare this data to the estimated Customer Acquisition Cost (CAC) of [CAC Amount] to identify the 'Time to Recover CAC' or break-even point per cohort. I need you to identify which are the 'high quality' cohorts (those with higher retention and average ticket) and what temporal or segmentation factors in [Segmentation Variable, ex: Acquisition Channel] could be influencing these positive results. Finally, synthesize your findings into an executive report that includes: 1. Identification of anomalies (cohorts with unusually low or high performance). 2. Hypothesis about the detected behavior based on the seasonality of [Year/Period]. 3. Strategic CRM recommendations to mitigate abandonment in the critical points detected. Provides the code in [Language: Python/SQL/R] necessary to automate this analysis by visualizing the results in a Heatmap with the library [Library, e.g.: Seaborn or Plotly].