Skip to content

CSV Data Summarizer skill

Inspect CSV structure, missing values and numeric summaries with local Python charts.

Community · coffeefuelbump
Authorcoffeefuelbump
LicenceMIT (README declaration; no LICENSE file)
Sourcecoffeefuelbump/csv-data-summarizer-claude-skill · SKILL.md on GitHub
Works inClaude Code · Codex, Gemini CLI, Cursor, Copilot
Read from the source on

csv-data-summarizer guides a Python inspection of CSV rows, types, missing values, distributions and correlations. The bundled analyze.py produces a text report and applicable PNG plots.

The script infers date candidates from column names and uses pandas defaults. Domain interpretation, identifier handling and date aggregation need review; generated correlations are not causal evidence.

From the skill's SKILL.md: CSV Data Summarizer

This is a community skill by coffeefuelbump, not checked by us or by Anthropic. Skills can tell the agent to run code, read files or call the network. Before installing, read its SKILL.md and every script in the folder, and look for anything that does not match what it says it does.

What it does

  1. Read the CSV and inspect types and missing cells.
  2. Summarize numeric and selected categorical fields.
  3. Generate relevant plots and interpret only patterns supported by the data.

What you get

  • A text summary and applicable distribution, correlation and time-series PNGs.
  • Files written in the current working directory by analyze.py.

When to use it

  • Get an initial overview of an unfamiliar CSV.
  • Find missing data and candidate trends before deeper analysis.

When not to use it

  • Treating automatic type/date inference as validated domain analysis or exposing sensitive CSVs to an unreviewed host.

What it needs

  • Python 3.8 or later with pandas 2+, matplotlib 3.7+ and seaborn 0.12+ as declared upstream.
  • Local file access and a suitable working directory; host assistant access to the data follows its own privacy terms.

Files in the skill

File or folderWhat it is for
SKILL.mdAnalysis workflow and reporting guidance.
analyze.pyCSV summaries and PNG chart generation.
requirements.txtDeclared Python package requirements.
resources/sample.csvExample dataset, not evidence for another dataset.

Licence as found in the repository on 2026-11-18: MIT (README declaration; no LICENSE file).

Example prompts

Type one of these after installing; naming the skill makes sure it is used.

  • Inspect this CSV and report missing cells before choosing charts.
  • Explain which columns analyze.py treats as dates or categories and flag likely misclassifications.
  • Run a reviewed local analysis in a new output folder so existing PNGs are not overwritten.

How to install csv-data-summarizer

Python environment and output folder

Install the declared requirements in an isolated environment after reviewing analyze.py. The folder does not bundle Python or its libraries.

PNG names are fixed and written into the working directory. Use a dedicated output folder. README declares MIT, but no standalone LICENSE file was present.

A skill is a folder with a SKILL.md file. You install it once; the agent reads its short description at the start of each session and loads the full instructions only when a request matches. Pick the place you use:

Claude Code: copy the folder into your skills folder

Put the skill's folder in ~/.claude/skills/ to use it in every project on this computer, or in .claude/skills/ inside a repository to share it with everyone who works there (commit it).

git clone --depth 1 https://github.com/coffeefuelbump/csv-data-summarizer-claude-skill.git
mkdir -p ~/.claude/skills/csv-data-summarizer
git -C csv-data-summarizer-claude-skill archive HEAD | tar -x -C ~/.claude/skills/csv-data-summarizer

Claude Code notices new or changed skills in these folders during the session. If the skills folder did not exist when the session started, run /reload-skills once. Then type /csv-data-summarizer or just describe the task.

On Windows, run the commands in Git Bash or WSL, or copy the folder into the same place with File Explorer.

Codex, Gemini CLI, Cursor and GitHub Copilot

These agents read the same SKILL.md folders. The one folder all four accept inside a project is .agents/skills/, so this copies the skill there:

git clone --depth 1 https://github.com/coffeefuelbump/csv-data-summarizer-claude-skill.git
mkdir -p .agents/skills/csv-data-summarizer
git -C csv-data-summarizer-claude-skill archive HEAD | tar -x -C .agents/skills/csv-data-summarizer
AgentProject folderYour user folderNotes
OpenAI Codex
.agents/skills/
~/.agents/skills/
Type $ or run /skills to pick a skill; Codex also chooses one when your task matches.
Gemini CLI
.agents/skills/
.gemini/skills/
~/.agents/skills/
~/.gemini/skills/
Or install from Git with gemini skills install <git URL> --path <folder> --consent. Google replaced Gemini CLI with Antigravity CLI for free-tier and Google One users on 18 June 2026; Antigravity uses .agents/skills/ in a project and ~/.gemini/config/skills/ for you.
Cursor
.agents/skills/
.cursor/skills/
~/.agents/skills/
~/.cursor/skills/
Type / in Agent chat to pick a skill. Cursor also reads Claude Code's .claude/skills/ folders.
GitHub Copilot
.github/skills/
.agents/skills/
.claude/skills/
~/.copilot/skills/
~/.agents/skills/
Works in Copilot CLI, the cloud agent, and agent mode in VS Code, Visual Studio and JetBrains (IDE support depends on the version). Or run gh skill install OWNER/REPOSITORY SKILL (public preview, GitHub CLI 2.90.0 or later).
Only install skills you trust. Anthropic's advice is to use skills only from trusted sources, and to read every file of any other skill before using it: a skill can direct the agent to run commands, read files or send data in ways its description does not mention.

Sources for these steps

Checked against each vendor's documentation on 2026-11-14:

Inspect the automatic report

Missing-value counts and type summaries are useful starting evidence. A no-missing-cells result is not proof of complete or accurate real-world data.

Sparse dates, constant columns, numeric IDs and high-cardinality categories can produce unhelpful charts. Review the actual PNGs and report rather than trusting a completion message.

Questions about csv-data-summarizer

Does it require uploading to a chart service?

The script itself reads local CSV and writes local PNGs. The host AI assistant may still receive data under its own terms.

How are dates detected?

The script selects column names containing date or time, then attempts pandas conversion. That heuristic needs inspection.

Can numeric IDs distort correlations?

Yes. Numeric columns enter numeric summaries and correlations; review identifier columns rather than assuming meaningful relationships.

Will it handle every CSV encoding or delimiter?

Not automatically. The bundled script uses pandas read_csv defaults and does not expose every parsing option; adapt and verify unusual files.

More AI skills

Related skills

Skill categories