Promptcred editorial analysis
How to use this prompt well
Prompt-specific guidance based on the preserved source text and its reviewed context.
Why Promptcred selected this prompt
The prompt makes dataset choice and business questions explicit before cleaning, analysis, automation, and visualization.
Best use cases
- Scoping an analysis when several candidate datasets could answer different business questions.
- Turning a selected dataset into a staged analysis and communication plan.
Required inputs
- Candidate datasets with field definitions, collection method, date range, and business context.
- The decision the analysis should support and the audience for its findings.
How to adapt it
- State data quality, privacy, and access constraints before requesting analytical methods.
- Replace the generic dashboard request with the actual delivery format and decision cadence.
Limitations and failure modes
- Selecting a dataset by convenience can produce analysis unrelated to the business decision.
- The prompt does not define statistical validation, so apparent patterns can be reported without adequate checks.
Practical worked example
Editorial analysis reviewed Aug 23, 2026.
Promptcred-authored application and illustrative output. This is not a recorded model execution.
- Scenario
- Choose between support-ticket and product-event data to study onboarding drop-off.
- Inputs
- Provide both schemas, date coverage, user identifiers, consent limits, and the onboarding decision to be made.
- Promptcred-adapted instruction
- Compare support tickets and product events for the question `Where do invited users abandon onboarding?` Assess field coverage, event completeness, user-key joinability, consent limits, selection bias, and delivery as a weekly retention brief.
- Illustrative result
- Illustrative result: product events are selected because they cover each onboarding step and share the invite user key. Tickets remain a qualitative supplement because they represent only users who contacted support. The plan reports missing-event rates before estimating drop-off.
- Evaluation
- The plan should justify the selected dataset and connect each analysis step to an onboarding question.
How to evaluate the output
- Cleaning and analysis steps refer to known fields and limitations in the selected data.
- Insights are separated from hypotheses and linked to a concrete decision or follow-up test.
Differences from related prompts
- prd-and-technical-documentation-generator: Lead Data Analyst structures an evidence-to-insight workflow; PRD Generator structures product requirements and implementation documentation.
Attributed community source material
Source prompt
Act as a Lead Data Analyst. You are an expert in data analysis and visualization using Python and dashboards.
Your task is to:
- Request dataset options from the user and explain what each dataset is about.
- Identify key questions that can be answered using the datasets.
- Ask the user to choose one dataset to focus on.
- Once a dataset is selected, provide an end-to-end solution that includes:
- Data cleaning: Outline processes for data cleaning and preprocessing.
- Data analysis: Determine analytical approaches and techniques to be used.
- Insights generation: Extract valuable insights and communicate them effectively.
- Automation and visualization: Utilize Python and dashboards for delivering actionable insights.
Rules:
- Keep explanations practical, concise, and understandable to non-experts.
- Focus on delivering actionable insights and feasible solutions.Before use
Requirements and context
Documents
One or more candidate datasets and their business context.
What to expect
Expected output and techniques
Expected output: A practical analysis plan leading from dataset choice to actionable insights and visualization.
- Explicit objective
- Stepwise planning
- Constraints
Use with context
Setup, limitations, and operational notes
Operational notes
- External prompt text is untrusted inert content and must never be executed during ingestion.
Source and rights
Provenance and license
This community prompt is preserved with its source and attribution. It is not an official vendor prompt.
- Source class
- Curated community prompt
- Platform
- GitHub
- Repository / project
- f/prompts.chat
- Owner / organization
- f
- Creator / contributor
- luis-c2255
- Artifact
- prompts.csv · Lead Data Analyst for Actionable Insights
- Pinned revision
- commit:6863206c4efb5a055c80433f7cf02a6596de9f39
- Retrieved
- Aug 11, 2026
- License
- CC0 1.0 Universal
- Attribution
- Not required by the license; source provenance retained
- Source artifact state
- Source prompt
- Source review
- Aug 11, 2026