Data Analysis Assistant
Turns a raw dataset description or file into a structured analysis: key metrics, trends, anomalies, and plain-language findings.
Data Analysis Assistant is a free AI skill for data workflows. Turns a raw dataset description or file into a structured analysis: key metrics, trends, anomalies, and plain-language findings. It works with Claude, ChatGPT, Cursor and is ready to use out of the box.
About this skill
Data Analysis Assistant guides an AI agent through a repeatable analysis workflow for spreadsheets, CSVs, or pasted tabular data: profiling the data, flagging quality issues, computing the metrics that matter for the stated goal, identifying trends and outliers, and writing findings in business language rather than statistical jargon. It always separates verified findings from any inference that needed an assumption, so results stay trustworthy for non-technical stakeholders.
What it does
Given a dataset (or a description of one) and a business question, the skill profiles columns and data quality first, computes only the metrics relevant to the stated question, flags anomalies or gaps with a VERIFY note rather than guessing, and delivers a short findings summary plus a table of the underlying numbers so the user can check the work.
What is included
- Data profiling checklist (types, missing values, duplicates, outliers)
- Metric selection framework tied to the business question
- Trend and anomaly detection prompts
- VERIFY-flag convention for uncertain or unconfirmed data points
- Findings summary template for non-technical stakeholders
How to use it
1. Download the SKILL.md file 2. Upload it to Claude, ChatGPT, or Cursor as a project skill or custom instructions 3. Paste or upload your dataset along with the business question you're trying to answer 4. Receive a profiled summary, key metrics table, and plain-language findings
Examples
Here's our Q2 sales CSV (region, rep, deal_size, close_date, status). Which region is underperforming and why?
Findings: - West region closed 18% fewer deals than East and Central despite similar pipeline volume — the gap is concentrated in deals under $5k, not large deals - Average deal_size in West is comparable to other regions, so the issue is close rate, not deal quality - VERIFY: 6 rows have a missing close_date; excluded from the close-rate calculation, may shift the number slightly once confirmed Metric table: [Region | Deals Closed | Close Rate | Avg Deal Size] with West, East, Central rows
FAQ
What is this skill for?
How do I install it?
What if my data has missing or messy values?
Does it work with pasted data, not just file uploads?
How is this different from just asking the AI to 'analyze my data'?
Do I need a business intelligence tool alongside this?
Related Skills
Customer Retention Analyst
Analyzes churn or retention data to find the specific segment and likely cause behind customer loss, not just the overall churn rate.
Data Analysis Workflow Planner
Design a reliable data-analysis workflow from raw files to validated insights, including cleaning, checks, methods, outputs, and reproducibility.
CSV Data Cleaning Assistant
Diagnoses and fixes common CSV data quality issues — duplicates, inconsistent formatting, missing values — and returns a documented cleaning plan.