$npx skillfedfor your agent

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

869 101 MITupdated by beita6969

Decision gist · record as of 2026-06-08

Data Analysis performs statistical testing, regression modeling, and visualization on CSV, Excel, and JSON datasets using Python. 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.

manual: git clone https://github.com/beita6969/ScienceClaw → cp -r ScienceClaw/skills/data-analysis ~/.claude/skills/data-analysis
skills/data-analysis/SKILL.md · version 1155853d

Use it when

  • Data Analysis provides tools to handle missing values, detect and remove duplicates and outliers, and assess data quality issues.
  • Yes.

Verify before relying

Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.

Same gist for agents: .md · .json

Install

beita6969/ScienceClaw/data-analysis · repository language: TypeScript

Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.

Frequently 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)

File tree — 1 file
skills/data-analysis/SKILL.md

Let your AI agent find skills like this

Example. Real query, live index.

You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.

wish › “Analyze and clean datasets with statistical testing and visualization”

Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →

Related skills

statsmodels-stats
by beita6969 · beita6969/ScienceClaw

statsmodels-stats provides regression modeling, hypothesis testing, and time series analysis for statistical workflows. Build OLS, logistic, and generalized linear models; run t-tests, ANOVA, and proportion tests; fit ARIMA and VAR models; and perform survival analysis with diagnostic plots and rigorous statistical reporting.

MITupdated Jun 2026
★ 869repo stars
statistical-analysis
by K-Dense-AI · K-Dense-AI/scientific-agent-skills

Conduct rigorous statistical tests—t-tests, ANOVA, chi-square, correlation, regression, and Bayesian methods—with systematic assumption verification and effect size reporting. The skill walks you through test selection, data inspection, assumption diagnostics, and APA-style write-ups so your analysis withstands peer review.

MITupdated Jul 2026
★ 31,940repo stars
statistics
by beita6969 · beita6969/ScienceClaw

This skill guides you through test selection for continuous, categorical, and time-to-event data across different study designs. It includes assumption verification methods, multiple comparison corrections, and effect size benchmarks to ensure rigorous analysis. Follow integrated reporting standards to communicate results with full transparency.

MITupdated Jun 2026
★ 869repo stars
Statsmodels Statistical Modeling
by jaechang-hits · jaechang-hits/SciAgent-Skills

Statsmodels provides classical statistical modeling with rigorous inference for Python, covering linear regression, generalized linear models, discrete choice analysis, and time series forecasting. It emphasizes coefficient interpretation, hypothesis testing, and model diagnostics rather than prediction optimization. Use this skill when you need detailed statistical inference, confidence intervals, and assumption validation.

no license declared → metadata onlyupdated Jul 2026
★ 284repo stars
statsmodels
by tondevrel · tondevrel/scientific-agent-skills

Statsmodels delivers rigorous statistical inference through comprehensive model estimation, diagnostic testing, and publication-ready summaries. It excels at linear and generalized linear regression, time series modeling, ANOVA, survival analysis, and causal inference—all with the p-values and confidence intervals essential for academic and scientific work.

MITupdated Feb 2026
★ 19repo stars
data-analysis
by bytedance · bytedance/deer-flow

Data Analysis lets you query uploaded Excel and CSV files using SQL, supporting multi-sheet workbooks, aggregation, filtering, and cross-file joins. Run statistical summaries, inspect schemas, and export results in multiple formats. Built on DuckDB for efficient columnar analysis.

MITupdated Jul 2026
★ 77,986repo stars

More skills data-stats-analysis (MIT) · scikit-learn-ml (MIT) · statistical-testing (MIT)

Tags
statistical-inferencedata-wranglinghypothesis-testingpredictive-modelingdata-visualizationquality-assuranceassumption-checkingeffect-sizes