Data & Datasets

August 19, 2026 · View on GitHub

7 plugins in this category. All categories · Marketplace root

/plugin marketplace add https://github.com/danielrosehill/Claude-Code-Plugins

Claude Data Analyst

First-pass data analysis toolkit: correlations, PII flagging, anomalies, hypothesis tests, data dictionaries, and trend analysis on a dataset in a folder.

/plugin install claude-data-analyst@danielrosehill

End-to-end data annotation toolkit. Prep raw data, design annotation schemas, annotate interactively with Claude (small scale) or scaffold Gemini batch inference (large scale), and publish to Hugging Face.

/plugin install data-annotation@danielrosehill

Claude Data Wrangler

Data cleaning, enrichment, restructuring, packaging, and documentation skills for tabular and JSON datasets (no visualisation). 31 skills covering ISO standardisation, PII detection/synthesis, data dictionaries, SQL/graph/vector/HF/GeoJSON/API targets, date & Unicode hygiene, header & numeric-precision standardisation, multilingual header localisation, incremental upstream sync, and Typst-rendered PDF documents of the data.

/plugin install Claude-Data-Wrangler@danielrosehill

Data Visualisation And Publishing

Create static and interactive data visualisations for reports, repos, and data storytelling. Purpose-organised inventory of 60+ validated open-source tools as a head start — static figures (Matplotlib, Seaborn, ggplot2), web charts (Chart.js, ECharts, Plotly.js, ApexCharts, Highcharts), high-perf (uPlot, Perspective, Lightweight Charts), bespoke (D3, Observable Plot, Vega/Vega-Lite, visx, Victory), Python/R apps (Bokeh, Dash, Altair, Streamlit, Gradio, Shiny, D-Tale, Briefer, Preswald), storytelling (Vizzu, VChart, vue-data-ui, SandDance), graphs (G6, sigma.js, Cytoscape, Gephi, Graphviz, GoJS, 3d-force-graph, Constellation), maps (deck.gl, react-map-gl, Leaflet, MapLibre, OpenLayers, folium, react-globe.gl), mobile (fl_chart, F2), BI (Superset, Metabase, Grafana, Kibana, Redash, Chartbrew), diagrams-as-code (Mermaid, PlantUML), domain-specific (Iris, QuantInvestStrats, XCharts, BizCharts, Tablesaw).

/plugin install data-visualisation-and-publishing@danielrosehill

Synthetic Data

Generate synthetic datasets from schemas, real data, or LLM-driven personas. Tabular fit-and-sample (SDV: GaussianCopula, CTGAN, TVAE), Faker/Mimesis schema generation, deterministic PII swap, LLM-driven real-to-synth conversion for unstructured records, and SDMetrics-based quality/privacy evaluation (plus embedding-based leakage checks for text).

/plugin install synthetic-data@danielrosehill

Taxonomy Creation

Generate taxonomy and lookup tables (countries, currencies, languages, US states, timezones, custom domain taxonomies) and load them into Postgres, SQLite, MySQL, or export to CSV/JSON/SQL seed files. For data engineers, CMS builders, and eval pipeline authors.

/plugin install taxonomy-creation@danielrosehill

Text Corpus Analysis

Skills for analyzing large text corpora — topic modeling (BERTopic with temporal evolution), NER, categorization into fixed taxonomies, bottom-up category derivation, multi-level taxonomy design, word frequency, synonym clustering for voice-note/STT corpora, parametric stats, and metadata↔content correlation. Three execution lanes (classical NLP, local LLM via Ollama, cloud LLM via OpenRouter) with explicit cost-awareness: mandatory pre-run estimates for >1k-doc LLM passes, two-pass cheap→premium pattern, embeddings+clustering preferred over pairwise LLM comparison.