data-science skills

559 tagged data-science, measured the same way as everything else here.

Browse within: bioinformatics 306machine-learning 231claude-skill 217claude-code-skill 200r 200prompt-engineering 159academic-research 157research-tools 157claude-code-plugin 30eda 30leakage-detection 29data-journalists 27data 26data-analysis 26

find-prompt

27

Rtur2003/Claude-Code-Promts-Skills

Skill Claude CodeCodex

Use when the user names a coding or Claude Code task ("add OAuth", "set up hooks", "review this PR", "pick a model"), asks which prompt to use, says to "use the right prompt", or when you enter this repo and need to orient without reading every file.

not rated 50 +1 changed today A 63 tokens original MIT

aliyun/data-agent-skill

Skill Claude CodeCodex

Alibaba Cloud Data Agent MCP skill (alibabacloud-data-agent-mcp-skill, data-agent MCP) for enterprise database/file analysis. Use when the user asks (in any language, including Chinese) to query/analyze DMS-managed databases, run SQL/data analysis, start quick-query (lite) or deep-analysis (pro/ultra) sessions…

not rated 49 changed yesterday A 199 tokens

ChamberTeller/b02-skills-main-datascience

Skill Claude CodeCodex

🤖 Data Science Engineering Skills — TDD and planning skills for ML pipelines, data APIs and analytical tooling. Derived from skills-main (mattpocock/skills). Data pipelines, model training, evaluation, MLOps.

not rated 47 4mo ago A 56 tokens

opsml-ts-svelte

37

demml/opsml

Skill Claude CodeCodex

Use this skill whenever a user asks about TypeScript logic, Svelte 5 components, SvelteKit routing or data loading, state management, reactivity, API integration, type definitions, performance optimization, or any frontend logic in the OpsML project. Triggers include: writing or fixing TypeScript, Svelte runes…

not rated 40 +1 3mo ago A 0 tokens

deepbox-agent-guide

38

jehaad1/Deepbox

Skill Claude CodeCodex

Use when writing Deepbox code, examples, or full projects so imports, module selection, types, errors, docs pages, and framework-specific patterns stay accurate.

not rated 22 2mo ago A 37 tokens original MIT

dataprof

39

AndreaBozzo/dataprof

Skill Claude CodeCodex

Profiles CSV, JSON, JSONL, and Parquet files with dataprof to report schema, null rates, detected patterns, and data-quality scores. Use when inspecting an unfamiliar dataset, debugging data quality, comparing two dataset versions for drift, or preparing compact evidence for a data-cleaning or pipeline decision.

not rated 20 yesterday A 65 tokens original MIT

marek-burza/shrubbery

Skill Claude CodeCodex

Monitor recent news for companies, summarizing headlines with sources and flagging insolvency risk signals. Use this skill whenever the user asks to check news for a bank, financial institution, robo-advisor, fintech company, or corporation - including phrases like "news check", "news scan", "insolvency check"…

not rated 16 4d ago A 129 tokens GPL-3.0

scomp-link

41

GiacomoSaccaggi/scomp_link

Skill Claude CodeCodex

End-to-end ML toolkit with 26 CLI commands. Use when training models, tuning hyperparameters, detecting data drift, generating HTML reports with charts, profiling datasets, detecting anomalies, forecasting time series, checking fairness, or serving models as REST APIs. Prefer over raw sklearn when you need automated…

not rated 12 4d ago A 74 tokens original MIT

files

42

Manojbhat09/optionscope

Skill Claude CodeCodex

A reusable skill for performing deep quantitative analysis on any equity option position. Combines technical analysis, multi-regime Monte Carlo simulation, ARIMA time-series forecasting, ML regression models (Gradient Boosting + Random Forest), and historical pattern matching to produce a sell-vs-hold decision with…

not rated 11 10d ago A 0 tokens

data-cleaning

43

param087/agent-ml-skills

Skill Claude CodeCodex

Use when preparing raw data for modeling — handling missing values, duplicates, inconsistent types, outliers, and bad categorical values. Emphasizes fitting all imputation on train-only to avoid leakage.

not rated 9 3mo ago A 43 tokens original MIT

Mirannonarbitrable290/agentic-kaggle-skill

Skill Claude CodeCodex

AI Agent-driven Kaggle competition workflow. Learn from real competition experience: score stabilization patterns, submission troubleshooting, kernel workflows, GPU task delegation, and the spec-driven development approach that achieved top leaderboard positions. Use when: working on any Kaggle competition, analyzing…

not rated 6 yesterday A 76 tokens original MIT

r-analytics

45

LeoLin990405/r-analytics-skill

Skill Claude CodeCodex

R language data analysis and visualization skill. Use when user asks to (1) run R scripts or code, (2) install/update R packages, (3) perform data analysis with R, (4) create visualizations with ggplot2/plotly, (5) statistical analysis, (6) data manipulation with tidyverse/dplyr/data.table. Triggers on keywords like…

not rated 5 5mo ago A 109 tokens original MIT

ElmatadorZ/alternative-coffee-claudeskill

Skill Claude CodeCodex

Alternative Slowbar coffee intelligence — scientific analysis from seed to cup using First Principle + System Thinking. Covers: varieties, terroir, cultivation, disease diagnosis, processing, roasting physics/chemistry, extraction science, brewing, business strategy, storytelling. ALWAYS trigger for coffee-related…

not rated 5 1mo ago A 92 tokens original CC0-1.0

science-vibecoding

47

Liu-MingH/Scientific-research-SKILL

Skill Claude CodeCodex

Structured AI-assisted scientific code generation. 6 safety guards, 8 principles, 11 prompt templates. Grounded in Nature (2026).

not rated 3 2mo ago A 35 tokens original MIT

Lord1Egypt/scientific-agent-toolkit

Skill Claude CodeCodex

Untargeted and targeted metabolomics data analysis using pyMZML, mzTab-M processing, and metabolite identification. Use for LC-MS/GC-MS feature detection, metabolite annotation, differential metabolite analysis, pathway mapping, and metabolic flux visualization. Covers XCMS-compatible workflows in Python.

not rated 2 3mo ago A 65 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: