ChatGPT Plugin

DataCleanist

EDA reports for your datasets

Brand: Unknown

Category: Pending
Primary Subcategory: Pending

Integration details

Description

DataCleanist analyzes tabular data files (CSV, TSV, Excel) and produces a deterministic exploratory data analysis: missing values, duplicates, outliers, distributions, correlations, VIF, mutual information, leakage suspects, PII flags, and a 0-100 data quality score with a five-dimension breakdown. Every number is computed by real code from the file itself - never estimated by a language model - and arrives with an interactive report card (Deep Dive statistics, per-column inspection, scatter explorer) rendered in the conversation. Intended users: data scientists, analysts, and ML engineers who want to understand and quality-check a dataset before modeling or cleaning it. Limitations: in-chat files up to 50 MB, 200,000 rows, and 300 columns; each user gets 5 analyses per rolling 30-day window; the tools analyze files - they do not clean, transform, export, or email data, and follow-up answers quote the computed summary rather than re-deriving statistics. Uploaded data is deleted automatically (raw files within 24 hours, derived outputs within 7 days) and is never used to train models. The full product - larger files, data cleaning, and chat - is available at datacleanist.com.

Integration type: Plugin
Verification status: Not applicable
Platform: ChatGPT
Category: Pending
Primary Subcategory: Pending
Secondary Subcategories: None listed
Brand: Unknown
Access: No account required
First tracked: 2026-10-29
Tool count: 4
Market: US

Agent DiscoverabilityChatGPT Plugin Discovery Score

ChatGPT organic discovery is live

Your score is coming

ChatGPT now suggests Plugins on its own when they match a user's request.Your Plugin Discovery Score measures how often yours appears, and it will show here as soon as it’s ready.

Sign up to track your Plugin See who ChatGPT suggests

ChatGPT recommends Airtable when a user asks it to update a CRM. — ChatGPT surfaces Airtable because it matches the user's request.

Primary Subcategory

Competitive lineup

No Primary Subcategory assigned yetOnce DataCleanist has a Primary Subcategory, the Plugins and Connectors it competes with will appear here with their scores.

Tools

4 tools agents can invoke

Use this when the user provides a data file (CSV, TSV or Excel) and asks for a data-quality profile, EDA, statistical summary, or cleaning assessment. Runs DataCleanist's deterministic engine: missing values, duplicates, outliers, correlations, quality findings, PII scan — all computed from the file, never estimated. Returns a compact summary and a dataset_id for render_eda_report. In-chat files are limited to 50 MB, 200,000 rows and 300 columns — for larger datasets, point the user to datacleanist.com. Do not use when no file is attached.
analyze_dataset
Use this to demo DataCleanist on a bundled public sample dataset (for example the Titanic dataset) when the user asks for a demo or has no file ready. Same deterministic engine as analyze_dataset. First call list_sample_datasets to get valid sample_id values. Do not use for the user's own files — analyze_dataset handles those.
analyze_sample_dataset
Use this when the user wants to try DataCleanist without providing a file, or asks which demo datasets are available. Returns a small bundled catalog of public sample datasets that can be analyzed in-chat. Do not use for the user's own files — use analyze_dataset for those.
list_sample_datasets
Use this after analyze_dataset or analyze_sample_dataset to display the interactive data-quality report card for a dataset that was just analyzed. Requires the dataset_id returned by the analysis tool. Do not use with a dataset_id that was never returned by an analysis tool.
render_eda_report

FAQs

DataCleanist ChatGPT Plugin FAQ

How the directory, categories and Discoverability Score work.

Read the methodology

How do I improve DataCleanist's ChatGPT Plugin discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.