Skip to content
Agentmart
Submit a tool

eda

Standardized initial exploration of a new dataset.

Skill by G4rb4sh

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/g4rb4sh-eda

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Standardized initial exploration of a new dataset. Use when the user says "explore this dataset", "EDA", "what is in this data", or when starting an ML project with data the team does not know yet.

Use cases: data, ml

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/eda

What's inside

Skill name
eda
Description
Standardized initial exploration of a new dataset. Use when the user says "explore this dataset", "EDA", "what is in this data", or when starting an ML project with data the team does not know yet.
License
MIT
Instructions
19 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

Generate a reproducible exploratory analysis (script or notebook according to
the repo convention) and a summary. Cover:

1. Shape: rows, columns, types, memory. Sample of 5 rows.
2. Quality: nulls by column, duplicates, constants, cardinality
   of categoricals, impossible or suspicious ranges.
3. Distributions: statistics for numerics, top values for
   categoricals, target balance if it exists.
4. Relationships: strong correlations with the target and between features;
   data leakage signals (features that "know" the future).
5. Temporality: if dates exist, covered range, gaps, visible drift.
6. Modeling risks: short, prioritized list of issues that
   would affect a model, with proposed treatment.

Rules: never upload or copy client data outside the project environment;
the summary uses aggregates, never individual records with sensitive
information.

From G4rb4sh/MLE-setup, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 30, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from G4rb4sh

Cite this page

eda skill. Agent Mart. https://agentmart.dev/skills/g4rb4sh-eda (last updated 2026-10-24)