data-analysis
Data Analysis handles the full workflow of scientific data exploration: load CSV, Excel, or JSON files; identify and remove missing values, duplicates, and outliers; generate distributions and correlation heatmaps; and run parametric or non-parametric tests depending on your data's characteristics. Fit OLS, logistic, or mixed-effects regression models and export publication-ready results with effect sizes and confidence intervals.
Data Analysis performs statistical testing, regression modeling, and visualization on CSV, Excel, and JSON datasets using Python.
AI-generated summary based on this skill's SKILL.md
Install
beita6969/ScienceClaw/data-analysis · repository language: TypeScript
git clone https://github.com/beita6969/ScienceClaw
cp -r ScienceClaw/skills/data-analysis ~/.claude/skills/data-analysisFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What can Data Analysis do with my dataset?
Data Analysis handles the complete scientific data workflow: load CSV, Excel, or JSON files; identify and remove missing values, duplicates, and outliers; generate distributions and correlation heatmaps; run parametric or non-parametric tests; and fit OLS, logistic, or mixed-effects regression models. Results include effect sizes and confidence intervals ready for publication.
How do I clean my dataset with Data Analysis?
Data Analysis provides tools to handle missing values, detect and remove duplicates and outliers, and assess data quality issues. The skill guides you through cleaning workflows and prepares your data for downstream analysis, ensuring statistical validity before testing or modeling.
Can Data Analysis run regression analysis on my data?
Yes. Data Analysis fits OLS, logistic, and mixed-effects regression models and reports results with effect sizes and confidence intervals. The skill handles model specification, diagnostics, and exports publication-ready summaries of your regression findings.
What statistical tests does Data Analysis support?
Data Analysis performs parametric tests (t-tests, ANOVA) and non-parametric alternatives (chi-square, Mann-Whitney U) depending on your data's characteristics. The skill selects appropriate tests, calculates effect sizes, and interprets results in context of your research question.
How does Data Analysis perform exploratory data analysis?
Data Analysis generates distributions, correlation heatmaps, and summary statistics to reveal patterns in your data. It supports correlation studies and EDA workflows on CSV files and other formats, helping you understand relationships and structure before formal hypothesis testing.
What file formats does Data Analysis accept?
Data Analysis loads CSV, Excel, and JSON files. Once imported, the skill applies the full analysis pipeline—cleaning, visualization, statistical testing, and modeling—across all supported formats with consistent workflows.
SKILL.md
rendered from the published skill — quoted content, verbatim
Data Analysis
Scientific data analysis with Python. All scripts use the venv at /Users/zhangmingda/clawd/.venv.
Setup
source /Users/zhangmingda/clawd/.venv/bin/activate
Workflow
1. Data Loading
import pandas as pd
import numpy as np
# CSV
df = pd.read_csv('data.csv')
# Excel
df = pd.read_excel('data.xlsx', sheet_name='Sheet1')
# JSON
df = pd.read_json('data.json')
# Clipboard (from user paste)
# Save user's data to a temp file first, then read
# Quick inspection
print(f"Shape: {df.shape}")
print(f"Columns: {list(df.columns)}")
print(df.dtypes)
print(df.describe())
print(f"Missing values:\n{df.isnull().sum()}")
2. Data Cleaning
```python
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
skills/data-analysis/SKILL.md