Data analyzer
Claude Skills for software engineers and developers
npx -y skills add wachawo/claude-skills --skill data-analyzerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 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
Systematic exploratory data analysis. Activate when a dataset needs profiling — structure check, nulls, outliers, distributions, correlations — before deeper analysis begins.
SKILL.md
2.3 KB, as published. Nobody here has run it
When to use
- You receive a new dataset and need to understand its shape and quality before analysis
- An analysis produces surprising numbers and you want to verify the underlying data first
- A stakeholder asks "is this data reliable?" or "what's in this table?"
- You're about to run a model or statistical test and need data-quality assurance
Process
- Load and overview — run
scripts/data_overview.pyto get row count, dtypes, memory usage, and a sample. Confirm grain (what one row represents). - Null profile — run
scripts/null_profiler.py; compare output against thresholds inreferences/quality_thresholds.mdand flag columns above limits. - Outlier detection — run
scripts/outlier_detector.py(IQR + z-score) on numeric columns; document flagged values and decide: real signal or data error? - Distribution summary — run
scripts/distribution_summary.pyfor descriptive stats and univariate histograms on each numeric column. - Correlation exploration — run
scripts/correlation_explorer.py; flag pairs with |r| > 0.8 as potential multicollinearity or redundancy. - EDA checklist sign-off — work through
references/eda_checklist.mdand confirm each item before declaring the dataset profiled. - Write findings — fill
assets/eda_report_template.mdwith full profiling output; distil top issues intoassets/findings_summary.md.
For pattern recipes (e.g. polars vs pandas equivalents, chunked reads for large files), see references/pandas_polars_recipes.md.
Inputs the skill needs
- Required: dataset path (CSV / Parquet / Excel) or a DataFrame already in scope
- Required: business context — what does one row represent?
- Optional: quality threshold overrides (defaults in
references/quality_thresholds.md) - Optional: columns to skip (PII, binary blobs, high-cardinality IDs)
Output
assets/eda_report_template.md(filled) — full profiling report with per-column statsassets/findings_summary.md(filled) — top 3–5 quality issues and recommended next steps- Console output / plots from scripts for interactive inspection
Gives 0 of the 12 instructions most data analysis skills give
Counted across 286 of the 286 authors here whose files we hold, read 2026-08-06
- use excel formulas instead of hardcoded calculated valuesin 35 of 286, across 7 files
- match existing template conventions when modifying filesin 35 of 286, across 7 files
- document sources for all hardcoded valuesin 35 of 286, across 7 files
- write minimal concise python codein 35 of 286, across 7 files
- place all assumptions in separate assumption cellsin 32 of 286, across 5 files
- apply industry-standard color coding to financial modelsin 31 of 286, across 5 files
- format years as text stringsin 30 of 286, across 3 files
- recalculate formulas using recalc.py after modificationsin 30 of 286, across 3 files
- format negative numbers using parenthesesin 30 of 286, across 3 files
- fix all identified formula errors before finishingin 27 of 286, across 1 file
- use colorblind-safe palettesin 19 of 286, across 12 files
- Name tests after the prevented bugin 13 of 286, across 8 files
Said here and by no other author read
- generate a data overview for the dataset
- confirm the grain of one row
- profile nulls and flag columns above thresholds
- detect outliers in numeric columns
- decide if flagged outlier values are errors
- generate distribution summaries for numeric columns
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.