First-pass data analysis toolkit: correlations, PII flagging, anomalies, hypothesis tests, data dictionaries, and trend analysis on a dataset in a folder.
Scan a dataset for significant anomalies — outliers, distribution shifts, impossible values, and unusual groupings. Use when the user wants a first-pass integrity and anomaly sweep of a CSV/Parquet/Excel file before deeper 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.
Generate a data dictionary for a dataset, combining automatic profiling with the user's description of what the data represents. Use when the user wants documentation of columns — names, types, semantic meaning, units, allowed values, and nullability — for a CSV/Parquet/Excel file.
Identify what the user is trying to analyse, diagnose gaps in the current dataset, propose external data sources that could fill them, then plan and implement the enrichment. Use when the dataset alone can't answer the user's question and extra context (reference data, lookups, joinable public datasets) is needed.
Produce a parametric PDF report describing a dataset — size, schema, distributions, key statistics, and findings from other skills — compiled via Typst. Use when the user wants a shareable, print-ready document about their data, not a one-off markdown summary.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
First-pass data analysis toolkit for Claude Code. Point it at a CSV, Parquet, or Excel file and get an initial impression — correlations, PII audit, anomalies, hypothesis checks, a data dictionary, or a trend narrative.
| Skill | What it does |
|---|---|
correlation-analysis | Compute Pearson/Spearman/Kendall correlations and rank the strongest variable pairs. |
pii-flag | Scan columns and values for likely PII; mask samples; recommend remediation. |
anomaly-analysis | Three-layer anomaly sweep: value sanity, distribution outliers, multivariate/temporal. |
hypothesis-testing | Formalise a user-stated hypothesis, pick the right test, and return supports/refutes/inconclusive. |
data-dictionary-creator | Merge auto-profiled schema with the user's description into a full data dictionary. |
trend-analysis | Identify and narrate the major trends — directional, seasonal, compositional, per-segment. |
setup-data-workspace | Discover data files in the current repo, load them into a DuckDB database, and update CLAUDE.md with query instructions. |
data-enrichment | Diagnose gaps between the user's analytical goal and the dataset, propose external sources, plan and implement enrichment. |
multivariate-analysis | Partial correlations, VIF, regression with interactions, Lasso, and PCA to tell which variables actually drive the target and which are redundant. |
forensic-sweep | Flag data that looks suspiciously clean, imputed, smoothed, or pre-normalised — so the user knows what was done upstream before they got it. |
type-consistency-sweep | Detect within- and cross-file type inconsistencies that block analysis or DB loading; fix trivial cases or delegate to a Claude-Data-Wrangler skill. |
standard-deviation | Compute SD (plus variance, IQR, MAD, CV) for numeric columns with trustworthiness flags for skew, heavy tails, and small n. |
sample-size | Characterise the effective sample size per analytical question, flag underpowered segments, and give a go/no-go verdict. |
data-reporting | Generate a parametric PDF report (Typst) describing the dataset — schema, distributions, quality, findings from prior skills. |
The skills assume (and will suggest) these are available on PATH:
duckdb — SQL over CSV/Parquet/Excel at speed.csvkit — csvstat, csvcut, csvlook.miller (mlr) — pivots and tallies on CSV.uv — run pandas/scipy/statsmodels/scikit-learn one-liners without a persistent venv.Optional:
presidio-analyzer — ML-backed PII entity detection (via uv run --with presidio-analyzer).claude plugins install claude-data-analyst@danielrosehill
MIT.
npx claudepluginhub danielrosehill/claude-code-plugins --plugin claude-data-analystClaude Code plugin for image editing, batch operations, format conversion, and filesystem organisation of image libraries — bucket by resolution, aspect ratio, orientation, format, EXIF capture time, camera, and dedupe duplicates / near-duplicates.
Claude Code plugin: ideation and planning workflow — capture, evaluate, rank, simulate, and plan ideas, with ideation/single-idea-eval/multi-idea-ranking/feature-ideas/simulation/idea-capture variants.
Manage a Proxmox VE host via SSH and the Proxmox API — guided first-run onboarding, VM/CT lifecycle, storage and ZFS inspection, log review, and update workflows. Per-host config is stored outside the plugin so the same install works across multiple Proxmox environments.
Personal budgeting workflow primitives — transaction logging, categorization, budget creation, spending analysis, goal tracking, and forecasting — plus a provisioning skill for a fresh budgeting workspace.
Hardware-aware desktop-to-laptop environment sync. Gathers package and dotfile snapshots from a base (desktop) and remote (laptop) Ubuntu/Debian system over SSH, then runs an AI analysis to recommend incremental sync, removal, and skip decisions — without forcing perfect replication.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.