Data Analysis Workflow Planner
Design a reliable data-analysis workflow from raw files to validated insights, including cleaning, checks, methods, outputs, and reproducibility.
Data Analysis Workflow Planner is a free AI skill for data workflows. Design a reliable data-analysis workflow from raw files to validated insights, including cleaning, checks, methods, outputs, and reproducibility. It works with Claude, ChatGPT, Cursor and is ready to use out of the box.
About this skill
Data Analysis Workflow Planner turns a business or research question and one or more datasets into a structured analysis plan. It defines data requirements, schema checks, cleaning logic, validation, exploratory analysis, suitable methods, visualizations, uncertainty handling, reproducibility, and final reporting.
What it does
The skill clarifies the decision or hypothesis, inventories available data, checks whether the data can answer the question, defines cleaning and transformation rules, specifies quality tests, selects analysis methods, proposes visualizations, documents assumptions and limitations, and creates an implementation sequence for spreadsheets, Python, SQL, or BI tools.
What is included
- Analysis objective
- Data inventory
- Schema and quality checks
- Cleaning and transformation plan
- Exploratory analysis steps
- Method selection
- Visualization plan
- Reproducibility checklist
How to use it
1. Download the data-analysis-workflow-planner-SKILL.md file 2. Upload it to your AI or analytics workspace 3. Provide the business question and available data description 4. Include sample columns, units, frequency, and known data issues 5. Use the final workflow to guide analysis in Excel, Python, SQL, or BI software
Examples
Plan an analysis workflow for 15-minute PV plant data containing inverter power, DC voltage, DC current, irradiance, module temperature, and ambient temperature. The goal is to detect underperforming inverters.
A full workflow covering schema validation, timestamp alignment, missing-data handling, sensor checks, normalization by irradiance and temperature, inverter peer comparison, anomaly rules, plots, confidence checks, limitations, and reproducible outputs.
FAQ
What is this skill for?
Can it work before I upload the data?
Can it choose statistical methods?
What if the data quality is poor?
Can it generate code?
How is this different from directly analyzing the data?
Related Skills
CSV Data Cleaning & Insights Reporter
Reviews a pasted CSV/table sample, flags data quality issues, proposes cleaning steps, and surfaces the top 3 insights worth investigating.
Data Analysis Assistant
Turns a raw dataset description or file into a structured analysis: key metrics, trends, anomalies, and plain-language findings.
Data Pipeline Quality Engineer
Design data quality controls for ingestion, transformation, validation, lineage, freshness, observability, and recovery.
Related Prompts
Form-to-Database Validation Workflow
Design a safe form-ingestion workflow that validates, normalizes, deduplicates, and stores submitted data with review queues and privacy controls.
Cross-App Data Sync & Deduplication
Design reliable one-way or two-way synchronization between business apps with field ownership, conflict rules, deduplication, replay safety, and reconciliation.
Related Articles
How to Use AI for Excel Formulas
A practical guide to using AI for Excel and Google Sheets formulas, spreadsheet cleanup, error debugging, summaries, and dashboard-ready calculations.