correlation-analysis
/correlation-analysis
Detect and compute correlations between numeric variables in a dataset. Use when the user wants to see how variables in a CSV/Parquet/Excel file move together — Pearson, Spearman, or Kendall — with a short report flagging the strongest positive and negative pairs.
- Author
- danielrosehill ↗
- Repository
- claude-data-analyst-plugin ↗
- Licence
- MIT
- Last repository change
- 15.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 15.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Detect and compute correlations between numeric variables in a dataset. Use when the user wants to see how variables in a CSV/Parquet/Excel file move together — Pearson, Spearman, or Kendall — with a short report flagging the strongest positive and negative pairs.
Original author description
Detect and compute correlations between numeric variables in a dataset. Use when the user wants to see how variables in a CSV/Parquet/Excel file move together — Pearson, Spearman, or Kendall — with a short report flagging the strongest positive and negative pairs.
How it works
- Inputs
- Recommended CLI tooling
- Procedure
- Output
SKILL.md preview
--- name: correlation-analysis description: Detect and compute correlations between numeric variables in a dataset. Use when the user wants to see how variables in a CSV/Parquet/Excel file move together — Pearson, Spearman, or Kendall — with a short report flagging the strongest positive and negative pairs. --- # Correlation Analysis Produce a first-pass correlation report for a dataset in a folder. ## Inputs - Path to a dataset file (CSV, TSV, Parquet, XLSX) or folder containing one. - Optional: correlation method (`pearson` default, `spearman` for non-linear/ranked, `kendall` for small-n or many ties). - Optional: target variable — if given, rank all other numeric columns by absolute correlation to it. ## Recommended CLI tooling - `duckdb` — fastest way to load mixed formats and run `CORR(x, y)` in SQL. - `uv run --with pandas --with scipy python -c '...'` — for Spearman/Kendall and heatmap export. - `csvstat` (csvkit) — quick column types and null counts before correlating. ## Procedure 1. **Load and profile**: identify file format, row count, and column dtypes. Drop or flag non-numeric columns. 2. **Null/variance screen**: exclude columns with >50% nulls or zero variance — note them in the report. 3. **Compute correlation matrix** using the chosen method. 4. **Rank pairs** by absolute correlation. Report: - Top 5 positive (r > 0.3) - Top 5 negative (r < -0.3) - Any suspicious pairs (|r| > 0.95 — likely duplicates or derived columns) 5. **Caveats**: correlation is not causation; check for confounders; Pearson assumes linearity; small-n results are unreliable (flag if n < 30). ## Output Write a markdown report next to the dataset (`<dataset>-correlations.md`) with: - Method used and sample size - Ranked pair table - Flagged column exclusions - One-paragraph plain-English summary of the strongest relationships If a `--target` was given, lead with a ranked list of predictors of that target.
Versions
The database has no other skills named correlation-analysis.
Database snapshot: 13.11.2026 · package version 711a4a602062 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100correlation-auditor
Analyzes correlation matrices (Pearson/Spearman), computes partial correlations to control for confounding variables, and flags potential spurious correlations in your data. Triggered when users ask about relationships between variables, need correlation matrices, or mention… - 100sample-correlation-analysis
Use when performing correlation analysis between two variables including Pearson and Spearman correlation methods. Supports command-line parameter input, automatic data format detection, parameter validation, result directory creation, and CSV or TXT format result export. - 100data-analysis
Explore, clean, summarize or answer questions about a tabular dataset (CSV, Excel, Parquet, JSON, or a pasted table): distributions, outliers, correlations, group comparisons, trends, seasonality. Use whenever the answer must be computed from rows and columns. Writes code,… - 100data-analysis
Analyze a dataset end-to-end: load, clean, compute statistics, find patterns/correlations, and optionally plot — using pandas when available (stdlib fallback otherwise). Use when users hand over data (CSV/Excel/JSON) and want insights, trends, summaries, correlations, or charts,… - 90analyze-correlations
Run correlation analysis on connected data, identify strong relationships, and suggest regression models. Use when exploring relationships between variables. - 90multivariate-analysis
Test relationships among three or more variables simultaneously — partial correlations, controlled effects, multicollinearity, interaction terms, and dimensionality reduction. Use when a pairwise correlation sweep isn't enough and the user wants to know how variables behave…