Data analysis
Skill yigityildiz0/universal-ai-skill-library/skills/common/data-analysis
531 searchable AI Agent Skills for Claude Code, OpenAI Codex, and OpenCode — EN/TR catalog, platform and risk notes, direct ZIPs, and curated bundles.
npx -y skills add yigityildiz0/universal-ai-skill-library --skill data-analysisAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
3 things to look at
- 18 days oldThe repository was created 18 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Perform defensible exploratory, descriptive, statistical, or diagnostic analysis on structured data. Use for analyze data, investigate a metric, statistics, data quality, trends, correlations, outliers, or evidence-based findings.
SKILL.md
1.0 KB, as published. Nobody here has run it
Data Analysis
Analyze evidence before interpreting it. If a managed analytics capability is available in the active host, use it; otherwise use the available local tools without installing packages unless authorized.
- Inspect schema, grain, time range, source, missingness, duplicates, units, and known collection issues.
- Define the question, population, comparison, metric, and decision before selecting a method.
- Separate descriptive observations, statistical inference, and causal claims.
- Test robustness with sensible slices, outliers, denominators, and time windows; report uncertainty and limitations.
- Produce reproducible steps, not only a conclusion.
Do not hide data quality issues, overstate causation from correlation, or fabricate precision beyond the source.