CSV Data Summarizer
Runs pandas on a CSV and auto-generates stats plus four charts
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 17, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 680964a
Task: run a summary analysis on resources/sample.csv (20 rows) — first without the skill, then with the analyze.py bundle. Baseline (regular pandas: describe + isnull + head) yielded only text and 0 graphs; the skill produced 4 valid PNGs (verified by file: 2100x1500 RGBA), correlations (quantity/revenue 0.394), and category breakdowns — with no failures on three datasets and an edge case with missing values. But a real bug was found: the date detector caught the substring 'time', so on the repository's own showcase file, the customer_lifetime_value column (2400, 8500) silently went into pd.to_datetime and printed the section 'Date range: 1970-01-01 00:00:00.000002400, Span: 0 days' — fabricating a non-existent time series. The date column additionally ended up in categorical analysis (each date at 5%). README promised 'Intelligent & Adaptive — automatically detects data type (sales, customer, financial)', but analyze.py had no data type detection branches: the logic was fixed, all 'adaptivity' was a text instruction for the model, hence docs 2/5. It required pip install pandas/matplotlib/seaborn, hence setup.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 4/5
- Output vs. baseline 6/10
- Docs & honesty 2/5
What CSV Data Summarizer does
Bundles a pandas/matplotlib script that profiles a CSV — dtypes, missing values, describe(), correlations, category frequencies — and writes four PNG charts without asking follow-up questions. Triggers when you hand Claude a CSV and ask for a summary, analysis, or trends.
How to install CSV Data Summarizer
git clone https://github.com/coffeefuelbump/csv-data-summarizer-claude-skill.git
mkdir -p ~/.claude/skills/csv-data-summarizer
cd csv-data-summarizer-claude-skill && cp -r SKILL.md analyze.py requirements.txt resources ~/.claude/skills/csv-data-summarizer/
pip install -r requirements.txt
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger CSV Data Summarizer
-
/csv-data-summarizerRuns pandas on a CSV and auto-generates stats plus four charts
It also activates on plain-language prompts like these:
-
Summarize this CSV for me with stats and a few charts, no questions needed -
Run a quick profile on this sales CSV, missing values and correlations too -
Give me four charts and a stats breakdown from this financial data file
Frequently asked questions
- Is the CSV Data Summarizer skill free?
- Yes. The skill itself is free from coffeefuelbump/csv-data-summarizer-claude-skill. SkillProof publishes the install command and an independent test verdict at no cost.
- Does CSV Data Summarizer work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. Task: run a summary analysis on resources/sample.csv (20 rows) — first without the skill, then with the analyze.py bundle. Baseline (regular pandas: describe + isnull + head) yielded only text and 0 graphs; the skill produced 4 valid PNGs (verified by file: 2100x1500 RGBA), correlations (quantity/revenue 0.394), and category breakdowns — with no failures on three datasets and an edge case with missing values. But a real bug was found: the date detector caught the substring 'time', so on the repository's own showcase file, the customer_lifetime_value column (2400, 8500) silently went into pd.to_datetime and printed the section 'Date range: 1970-01-01 00:00:00.000002400, Span: 0 days' — fabricating a non-existent time series. The date column additionally ended up in categorical analysis (each date at 5%). README promised 'Intelligent & Adaptive — automatically detects data type (sales, customer, financial)', but analyze.py had no data type detection branches: the logic was fixed, all 'adaptivity' was a text instruction for the model, hence docs 2/5. It required pip install pandas/matplotlib/seaborn, hence setup.
- What is the CSV Data Summarizer SkillProof Score?
- 6.8/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 6/10, docs & honesty 2/5.
- How do I install CSV Data Summarizer?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use CSV Data Summarizer with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.