- Home
- Skills
- Data & Databases
- EDA Report Builder
EDA Report Builder
Profile any dataset systematically: structure, nulls, outliers, distributions and correlations, with a findings summary.
$14
Works with the AI tools you already use
EDA Report Builder
Example session with this skill installed
Profile subscriptions.parquet before I build a churn model. One row = one customer subscription. Skip the email column (PII). Tell me the top issues and whether it's ready for modelling.
- Read your context and instructions
- Compiled the eda report builder
Illustrative example on synthetic data. It follows this skill's findings_summary.md template.
EDA Findings Summary: subscriptions
Dataset at a Glance
| Item | Value |
|---|---|
| Rows × columns | 48,210 × 13 (email skipped) |
| Grain | one row per subscription ✅ confirmed; subscription_id is unique |
| Date range | 2023-01-02 → 2026-09-28 |
| Memory | 6.1 MB |
Top Quality Issues
Issue 1: cancel_reason is 71% null
This is expected for active subscriptions, but 9% of
cancelled rows are also null. Treat those as "unknown" rather than dropping them.
Issue 2: Outliers in monthly_price
312 rows are above the IQR fence ($480+). 290 of them are enterprise plans (real signal). 22 have a price of $99,999, which is a placeholder value and a data error.
Issue 3: Redundant features
seats and monthly_price have r = 0.91. Keep one, or combine them, before fitting a linear model.
What Looks Good
- No duplicate subscriptions and no negative prices
plan_tierhas 4 clean categories with no stray casing- Signup volume is stable month to month, with no missing months
Next Step
Ready for modelling after 2 fixes: remove the 22 placeholder prices, and decide how to handle seats versus monthly_price. The full per-column stats are in eda_report_template.md.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
EDA Report Builder gives your agent a repeatable exploratory data analysis routine, so you never skip a step before real analysis starts. It confirms the grain, profiles nulls against thresholds, flags outliers with IQR and z-score, summarises distributions, and highlights highly correlated pairs. It then works through an EDA checklist and writes both a full profiling report and a short summary of the top issues.
Use it when
- You just received a new dataset and need to know what is in it
- An analysis produced surprising numbers and you want to check the data first
- Someone asks "is this data reliable?"
- You are about to fit a model or run a statistical test
What's inside (installs as one folder, programmatic-eda/):
programmatic-eda/LICENSEprogrammatic-eda/SKILL.mdprogrammatic-eda/assets/eda_report_template.mdprogrammatic-eda/assets/findings_summary.mdprogrammatic-eda/references/eda_checklist.mdprogrammatic-eda/references/pandas_polars_recipes.mdprogrammatic-eda/references/quality_thresholds.mdprogrammatic-eda/scripts/correlation_explorer.pyprogrammatic-eda/scripts/data_overview.pyprogrammatic-eda/scripts/distribution_summary.pyprogrammatic-eda/scripts/null_profiler.pyprogrammatic-eda/scripts/outlier_detector.py
Please read before buying: this is packaged from my free, MIT-licensed open-source library (https://github.com/nimrodfisher/data-analytics-skills). The same content is available there for free. You are paying for a ready-to-install package. It is a one-time purchase, sold as-is, with no support, updates or maintenance included. The MIT license is included.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 1 day ago
- Passed all security checks, Safe to install