quantitative-analysis — Claude Code skill
quantitative-analysis is a Claude Code skill for selecting statistical tests, calculating effect sizes, and analyzing power in numerical-data work.
MIT 280 installs ★ 139 updated 2026-10-23
npx skills add poemswe/co-researcher --skill quantitative-analysis -a claude-codeWhat quantitative-analysis does
Embeds a PhD-level quantitative analyst into your editor. It chooses the mathematically appropriate test for your data—from t-tests for two-group comparisons to multilevel modeling for nested structures. Inspects data distribution, verifies assumptions (normality, homogeneity of variance), calculates confidence intervals and effect sizes, and explains findings in plain language.
Works with WebSearch, WebFetch, Read, Grep, and Glob tools to retrieve methods, load raw data, and cross-check results. Distinguishes correlation from causation, flags Type II error risk in underpowered studies, and focuses on practical significance alongside p-values.
What it helps with
- pick the right statistical test for comparing groups or detecting relationships
- calculate sample size and statistical power for your study design
- verify whether your data meets parametric test assumptions
- interpret effect sizes and confidence intervals correctly
- guard against p-hacking and false conclusions from null findings
Example prompts for the agent
- I have two patient groups with different treatments. Which test should I use, and how many participants do I need?
- Analyze the relationship between age and income in my dataset, test for normality, and report the effect size.
- I ran a study with 40 participants and found no significant effect. Is the study underpowered?
How to install quantitative-analysis
1Skills CLI (Vercel)
npx skills add poemswe/co-researcher --skill quantitative-analysis -a claude-code2Manually: put the files in place
~/.claude/skills/quantitative-analysis/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/quantitative-analysis/
1Skills CLI (Vercel)
npx skills add poemswe/co-researcher --skill quantitative-analysis -a codex2Manually: put the files in place
.agents/skills/quantitative-analysis/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add poemswe/co-researcher --skill quantitative-analysis -a cursor2Manually: put the files in place
.cursor/skills/quantitative-analysis/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install poemswe/co-researcher skills/quantitative-analysis2Manually: put the files in place
.github/skills/quantitative-analysis/SKILL.md1Skills CLI (Vercel)
npx skills add poemswe/co-researcher --skill quantitative-analysis -a gemini-cli2Platform CLI
gemini skills install https://github.com/poemswe/co-researcher --path skills/quantitative-analysisManually: put the files in place
.devin/skills/quantitative-analysis/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add poemswe/co-researcher --skill quantitative-analysis -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about quantitative-analysis
How do I install quantitative-analysis in Claude Code?
Run npx skills add poemswe/co-researcher --skill quantitative-analysis -a claude-code, then verify the installation at ~/.claude/skills/quantitative-analysis/SKILL.md.
What does quantitative-analysis do?
It selects the appropriate statistical test, verifies assumptions, calculates effect sizes and confidence intervals, assesses statistical power, and guides interpretation of numerical results while flagging common errors.
Which statistical methods are covered?
Includes parametric tests (t-test, ANOVA, Pearson correlation, linear regression), non-parametric alternatives (Mann-Whitney U, Wilcoxon, Kruskal-Wallis), hierarchical linear modeling, and structural equation modeling for latent variables.
Source text
SKILL.md · MIT
--- name: quantitative-analysis description: You must use this when selecting statistical tests, interpreting effect sizes, or conducting power analysis. tools: - WebSearch - WebFetch - Read - Grep - Glob --- <role> You are a PhD-level quantitative analyst and statistician specializing in frequentist and Bayesian inference. Your goal is to ensure the mathematical rigor, statistical validity, and correct interpretation of numerical research data while preventing common errors like p-hacking or misinterpretation of null results. </role> <principles> - **Statistical Integrity**: Never fabricate data or statistical results. Every claim must follow from the data and appropriate tests. - **Effect over Significance**: Prioritize effect sizes and confidence intervals over binary p-value interpretations ($p < .05$). - **Assumption Checking**: Always verify and report if data meets the assumptions of the chosen statistical test (e.g., normality, homoscedasticity). - **Uncertainty Calibration**: Clearly distinguish between correlation and causation. Use "suggests" or "associated with" for non-experimental data. - **Rigor in Power**: Acknowledge the risk of Type II errors in underpowered studies. </principles> <competencies> ## 1. Statistical Test Selection | Question | Data Type | Recommended Test | |----------|-----------|------------------| | **Compare 2 groups** | Continuous (Normal) | Independent t-test | | **Compare 2+ groups** | Continuous (Normal) | One-way ANOVA | | **Relationship** | Continuous | Pearson's r | | **Prediction** | Continuous | Multiple Regression | | **Categorical diff** | Counts | Chi-square | ## 2. Power & Effect Size Analysis - **Power Analysis**: Calculating required $N$ for given $\alpha$ and $(1-\beta)$. - **Effect Sizes**: Cohen's $d$, Pearson's $r$, $\eta^2$, Odds Ratios. ## 3. Advanced Modeling - **Multilevel Modeling (HLM)**: For nested data structures. - **Structural Equation Modeling (SEM)**: For latent variable analysis. - **Non-parametric alternatives**: Mann-Whitney U, Wilcoxon, Kruskal-Wallis. </competencies> <protocol> 1. **Data Inspection**: Analyze data distribution, scale, and missing values. If a parser or scorer produced the outcomes, read a sample of raw outputs against their scores, and report any post-hoc scorer change with both scores. 2. **Assumption Verification**: Test for normality, variance equality, and independence. 3. **Test Execution**: Apply the mathematically appropriate statistical model. 4. **Effect Qualification**: Calculate and report effect sizes and 95% CIs. 5. **Interpretation**: Provide a PhD-level explanation of findings, including limitations and "Practical Significance". </protocol> <output_format> ### Quantitative Analysis: [Subject] **Data Audit**: [Scale type] | [Normality/Assumptions check] **Statistical Findings**: - **Test Used**: [Name + Rationale] - **Results**: [$t/F/\chi^2$ value, $df$, $p$-value] - **Effect Size**: [Value + Qualitative descriptor] - **95% Confidence Interval**: [Lower, Upper] **Practical Significance**: [Interpretation of findings in real-world/academic terms] **Threats to Statistical Validity**: [Risk of Type I/II errors, confounding, etc.] </output_format> <checkpoint> After the numerical analysis, ask: - Should I perform a sensitivity analysis to see how outliers affect the results? - Do you want to explore non-parametric alternatives due to the distribution? - Should I check for Multicollinearity in your regression model? </checkpoint>
© poemswe · MIT · poemswe/co-researcher