Skip to main content
affpapa.org
RU EN
skill CX Codex

data-analysis · lingzhi227 — Claude Code skill: stats analysis with 4-round review

Writes statistical analysis code for a paper: picks a test that fits the data and reports p-values, effect sizes and confidence intervals.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add lingzhi227/agent-research-skills --skill data-analysis -a claude-code
Open on GitHub

What data-analysis does

The skill takes a data source (CSV, JSON, pickle or experiment logs) plus the hypothesis you want to check. It then lays out an analysis script in sections: imports, loading the data, dataset preparation, descriptive statistics, preprocessing, the tests themselves, and saving extra results to pickle.

That code goes through four review rounds. The first hunts for mistakes in the maths and statistics. The second looks at data handling: missing values, units, exclusion criteria. Rounds three and four check tables for plausible values, uncertainty measures, and consistency across the whole report. A test-selection table ships inside the skill: t-test and Mann-Whitney for two groups, ANOVA and Kruskal-Wallis for several, chi-square and Fisher's exact for categorical data, plus correlation and regression.

Two helper scripts come along. stat_summary.py detects data types, suggests a test, runs comparisons and returns effect sizes with significance stars; it needs numpy and scipy. The other, format_pvalue.py, renders p-values as stars, LaTeX or plain text and uses only the standard library. Analysis is limited to pandas, numpy, scipy, statsmodels, sklearn and pickle, so a different stack is out of scope.

What it helps with

  • pick a statistical test that matches the data type and group count
  • attach a confidence interval or p-value to every reported estimate
  • handle missing values, units and exclusion rules before tests run
  • check that values and uncertainty measures agree across tables
  • convert p-values into stars or LaTeX for typesetting

Example prompts for the agent

  • Analyse results.csv, compare methods on accuracy and report effect sizes
  • Test the group difference in experiment.json and write up a report with confidence intervals
  • Format the pvalue column of results.csv as LaTeX

How to install data-analysis

1Skills CLI (Vercel)

npx skills add lingzhi227/agent-research-skills --skill data-analysis -a claude-code

2Manually: put the files in place

~/.claude/skills/data-analysis/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/data-analysis/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about data-analysis

How to install data-analysis in Claude Code?

Run npx skills add lingzhi227/agent-research-skills --skill data-analysis -a claude-code; the skill lands at ~/.claude/skills/data-analysis/SKILL.md.

What does data-analysis do?

It generates statistical analysis code for a hypothesis, sends it through four review rounds, and produces a report with p-values, effect sizes and confidence intervals.

Which packages does the skill require?

The allowed set is pandas, numpy, scipy, statsmodels, sklearn and pickle. stat_summary.py needs numpy and scipy, while format_pvalue.py relies on the standard library.

Similar skills

All skills for Science and research →

data-analysis by other authors comes first.

data-analysis bytedance This skill inspects uploaded Excel and CSV files, runs SQL against them through DuckDB, and exports the results. CX Codex +1 3,600installs data-analysis claude-office-skills Reads Excel and CSV files, runs the statistics, spots patterns, and suggests charts and formulas. Useful when you need to make sense of a table fast. CX Codex +1 7,900installs data-analysis akillness A skill that walks the agent through dataset analysis: quality checks first, then the right method, then findings with caveats. Useful when you have an export and need an answer, not just code. CX Codex +1 598installs anysearch anysearch-ai This skill gives an agent web search, domain-specific queries, parallel batch search, and page extraction. Use it when a task needs current information or a claim needs checking. CX Codex +1 38,500installs academic-paper Imbad0202 This skill runs a 12-agent academic pipeline across 11 modes. It guides projects from literature searches and outlines to citation audits and rebuttal reviews. CX Codex +1 10,800installs nature-figure Yuan1z0825 A skill that builds, revises and audits scientific figures for manuscripts in Python or R. Useful when plots go to submission, not to a report. CX Codex +1 18,800installs academic-paper-reviewer Imbad0202 This skill reviews an academic paper through five role-based perspectives. Use it for peer review, revision checks, or a focused methodology assessment. CX Codex +1 9,800installs nature-polishing Yuan1z0825 A skill that polishes, translates and tightens existing academic prose. Facts, terminology and evidence boundaries stay intact. CX Codex +1 17,500installs nature-citation Yuan1z skill, refactored into static/dynamic layers Finds Nature and CNS-family papers for manuscript claims, maps claims to sources, and prepares a reference-manager export. Use it when the journal scope matters. CX Codex +1 15,600installs

From the same set31

math-reasoning Derives equations, writes proofs, formalizes research problems, and produces publication-ready LaTeX markup for research papers. CX Codex +1 2,200installs latex-formatting Sets up conference LaTeX templates, fixes formatting, and runs a pre-submission check. Handy when the deadline is close. CX Codex +1 2,200installs citation-management A skill that keeps citations in a LaTeX paper in order: harvests missing references via Semantic Scholar, validates cite keys against .bib, and formats the bibliography. CX Codex +1 2,100installs backward-traceability Connects every numeric value in a research PDF directly to the source code line that produced it. Helps verify data reproducibility across LaTeX documents. CX Codex +1 2,100installs deep-research Runs a systematic academic literature review on a topic: finds papers, reads them, builds a database and writes a final report. Useful when you need the state of a field, not a few search hits. CX Codex +1 1,900installs research-planning Turns a topic or idea into a structured research plan: methodology, paper sections, dependency-ordered tasks and diagrams. CX Codex +1 1,800installs github-research Finds open-source repositories matching research topics, inspects their codebases, and produces an integration blueprint. Useful when tracking down implementations of algorithms. CX Codex +1 1,800installs experiment-design Turn a research idea into staged experiments with baselines, datasets, metrics, and ablations. Useful when shaping an experimental plan for a paper. CX Codex +1 1,800installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor