csv-data-summarizer-claude-skill

왜 쓰나요

핵심 기능

Automatic CSV column profiling (dtype inference, null %, cardinality)
Summary statistics for numeric and categorical columns
Missing-data heatmap + per-column null counts
Quick visualizations: histograms for numerics, bar charts for categoricals
Python + pandas, runs in the local environment

라이브 데모

실제 사용 모습

csv-data-summarizer-claude-skill.replay ▶ 준비됨

0/0

설치

작성자 저장소 · Claude Skills 공식 문서

사용 사례

실전 활용법: csv-data-summarizer-claude-skill

How to get a first look at a new CSV without writing pandas

👤 Analysts, PMs, anyone inheriting someone else's data ⏱ ~10 min beginner

언제 쓸까: You got handed a CSV and need to understand what's in it before doing anything else.

흐름

Point Claude at the file

Summarize data/sales_2024.csv — columns, nulls, and basic stats.✓ 복사됨

→ Per-column dtype, null %, min/max or top values
Ask for missing-data diagnosis

Which columns have systematic nulls? Any row-level patterns?✓ 복사됨

→ Specific columns flagged, not vague 'some nulls'
Request quick visuals

Save histograms for all numeric columns into ./charts/.✓ 복사됨

→ PNG files on disk

결과: A one-page mental model of the dataset in under 5 minutes.

함정

Huge CSVs blow the token budget — Have Claude read a sample (nrows=10000) for exploration, run stats on the full file in Python
Dtype misinference (dates read as strings) — Tell Claude which columns are dates — pandas parse_dates helps

함께 쓰기: filesystem

Use the summarizer as a data-quality gate in a pipeline

👤 Data engineers validating incoming CSVs ⏱ ~30 min intermediate

언제 쓸까: You receive a daily CSV and want to flag anomalies before downstream steps.

흐름

Baseline the expected shape

Record the summary for last week's file as the baseline.✓ 복사됨

→ Baseline JSON saved
Compare today against baseline

Compare today's CSV to the baseline — flag null-rate shifts >5%, new/missing columns, dtype changes.✓ 복사됨

→ Diff report with specific anomalies
Fail loudly if bad

If any flags are critical, exit non-zero so CI fails.✓ 복사됨

→ Non-zero exit + readable reason

결과: Bad data caught before it pollutes the warehouse.

함정

Threshold too sensitive — noisy failures — Calibrate on 30 days of baselines before enforcing

함께 쓰기: github

조합

다른 MCP와 조합해 10배 효율

csv-data-summarizer-claude-skill + filesystem

Run against a directory of CSVs and save each report next to the file

For every CSV under data/, save a matching *_profile.md file summarizing it.✓ 복사됨

csv-data-summarizer-claude-skill + jupyter

Drop the profile into a notebook for further exploration

Take the profile and create a Jupyter notebook with the loaded DataFrame and starter cells.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
csv-profile	path to CSV	First step on any new CSV	pandas runtime
missing-data-report	profile	After profiling	0
quick-charts	profile + output dir	When you want visuals alongside stats	matplotlib runtime

비용 및 제한

운영 비용

API 쿼터: none
호출당 토큰: ~2–5k tokens per CSV (plus the data sample Claude reads)
금액: free
팁: Pass nrows and a narrowed column list — don't feed Claude the whole 50MB file

보안

권한, 시크릿, 파급범위

자격 증명 저장: none

데이터 외부 송신: none — local pandas only

If the CSV contains PII, treat the generated charts and summaries as equally sensitive

문제 해결

자주 발생하는 오류와 해결

ModuleNotFoundError: pandas

pip install pandas matplotlib in the env where Claude Code runs scripts.

확인: python -c 'import pandas, matplotlib; print(pandas.__version__)'

UnicodeDecodeError on load

Tell Claude the encoding (e.g. 'encoding=latin-1') or normalize the file first.

확인: file -I path/to.csv

Charts look off for skewed data

Ask for log-scale or clipped histograms

대안