Data Science Skills

lllllllama/RigorPilot-Skills

RigorPilot Skills provides a research-first suite of agent skills designed to keep AI-assisted deep learning experiments grounded in reproducibility, evidence, and auditable changes.

iOfficeAI/OfficeCLI

OfficeCLI is an AI-friendly command-line tool that enables seamless creation, inspection, proofreading, and modification of Microsoft Office documents (.docx, .xlsx, .pptx) without requiring an Office installation.

yanyiwu/nodejieba

NodeJieba is a high-performance Node.js wrapper for the Jieba Chinese text segmentation library, powered by C++. It provides multiple tokenization algorithms, part-of-speech tagging, and keyword extraction capabilities.

yfedoseev/pdf_oxide

PDFOxide is an ultra-fast, specification-compliant PDF processing toolkit built in Rust with multi-language bindings and an MCP server for AI assistants.

kenforthewin/atomic

Atomic is an AI-augmented personal knowledge base that transforms freeform markdown notes into a semantically-connected knowledge graph using Rust and SQLite. It operates as a Tauri desktop application, headless server, or Model Context Protocol (MCP) bridge with pluggable AI providers.

firecrawl/firecrawl

Firecrawl is an API and toolset designed to search, scrape, crawl, and interact with web pages at scale, converting them into clean Markdown or structured JSON for AI applications.

unclecode/crawl4ai

Crawl4AI is an open-source, LLM-friendly web crawler and scraper that converts web content into clean, structured Markdown for RAG and AI pipelines.

infiniflow/ragflow

RAGFlow is an open-source Retrieval-Augmented Generation engine based on deep document understanding. It provides robust ingestion, OCR, parsing, and workflow canvas components for building enterprise-grade RAG applications.

ZhuLinsen/daily_stock_analysis

An intelligent multi-market stock analysis system powered by large language models that fetches financial data, performs technical evaluations, and generates automated daily decision dashboards and reports.

Yigtwxx/awesome-rag-production

A curated, production-focused collection of frameworks, decision guides, and reference architectures for building scalable Retrieval-Augmented Generation (RAG) systems.

FrankS-IntelLab/agentic-kaggle-skill

An end-to-end framework and operating loop designed for competitive machine learning on Kaggle, emphasizing robust cross-validation, multi-notebook pipelines, and scored submissions.

minihellboy/factorminer

FactorMiner is a governed research framework for discovering, evaluating, and combining interpretable alpha factors using typed domain-specific languages and LLM-guided workflows. It enables quantitative researchers to backtest portfolios, generate tearsheets, and manage factor libraries under strict transaction costs.

posit-dev/pointblank

This skill guides the definition and enforcement of data contracts and pipeline validation using the Pointblank library. It covers creating schemas, validation steps, and orchestrating input/output checks.

adrianco/retort

This skill acts as a qualitative analysis tool for Retort Design of Experiments (DoE) runs, aggregating factor effects, evaluating replicate variance, and surfacing code divergence.

zhnnky329/MathModeling-skills

MathModeling-skills is a rigorous framework for mathematical modeling tasks that strictly separates human modeling judgment from AI mechanical execution.

opensource-observer/oss-directory

This skill provides instructions for creating and maintaining project collections within the Open Source Observer (OSO) directory repository. It covers everything from gathering project lists and mapping GitHub URLs to validating and committing the collection YAML files.

TechyNilesh/DeepImageSearch

DeepImageSearch is a Python library for building multimodal image search engines supporting text, image, and hybrid queries via vector embeddings and LLM captioning. It features built-in agent integrations including a Model Context Protocol (MCP) server and LangChain tool wrappers.

DeepXiv/deepxiv_sdk

This skill builds a structured markdown baseline table for any research topic by leveraging the DeepXiv SDK to search arXiv papers, screen metadata, inspect structures, and extract experimental datasets and scores.

galaxyproject/galaxy-skills

A comprehensive collection of agent skills and instructions for developing, converting, and integrating tools and workflows within the Galaxy bioinformatics platform.

TulipaEnergy/TulipaEnergyModel.jl

An AI agent configuration and developer guide for TulipaEnergyModel.jl, a Julia package for energy system modeling and optimization.

caylent/tufte-data-viz

This skill applies Edward Tufte's data visualization principles to create clean, readable charts, graphs, and dashboards. It supports popular libraries like Recharts, ECharts, Chart.js, matplotlib, Plotly, and D3.

frank-luongt/faos-skills-marketplace

This skill analyzes A/B test results using statistical rigor to determine whether to ship, extend, or stop an experiment. It enforces disciplined evaluation by verifying sample sizes, checking guardrail metrics, and calculating confidence intervals.

Power-Agent/PowerMCP

PowerMCP is a collection of Model Context Protocol (MCP) servers and a Python management package designed to integrate LLMs with power system simulation and control software.

jordan-gibbs/hyperresearch

Hyperresearch transforms Claude Code into a comprehensive deep research agent executing a rigorous 16-step pipeline with persistent source vaults and adversarial review. It produces verified, fully cited reports ranging from quick briefs to full dissertations.

opendatalab/MinerU-Ecosystem

The MinerU-Ecosystem skill integrates the MinerU open-source document parsing engine to convert complex PDFs, office documents, images, and web pages into clean Markdown or multi-format output. It supports two modes: a token-free flash extraction for quick tasks and a precision extraction mode with OCR, layout analysis, and batch processing.

bertram-eu/halcon-skill

Generates, refactors, and reviews MVTec HALCON vision scripts in HDevelop and HDevelopEVO formats, ensuring production-grade, headless-compatible machine vision pipelines.

skills-il/tax-and-finance

Fetch and analyze official Bank of Israel economic data including interest rates, Consumer Price Index, and representative exchange rates.

aristoteleo/PantheonOS

PantheonOS is a distributed multi-agent framework tailored for bioinformatics and data science pipelines, supporting automated single-cell analysis and agentic code evolution.

traceloop/opentelemetry-mcp-server

An MCP server that enables AI assistants to query and analyze OpenTelemetry traces and LLM telemetry backends directly from development environments.

holistics/skills

This skill enables an AI data analyst agent to review past user conversations on Holistics and generate structured insight reports. The output consists of three specific sections covering summary, recap, and actionable suggestions for improvement.

Hawkynt/2dimagefilter

A comprehensive .NET collection of pixel art scaling algorithms, resamplers, and ditherers designed to enlarge low-resolution graphics without blurring. It offers a standalone GUI application, a Paint.NET plugin, and a command-line interface.

hssqz/plate-rotation-skill

An expert AI financial analyst skill specializing in A-share sector rotation, dual-source cross-verification, and short-term market momentum analysis.

googlecolab/google-colab-cli

An intelligent command-line tool designed to manage, execute code within, and interact with remote Google Colab runtime sessions seamlessly from the terminal.

deepak-pmcurve/product-skills

Conducts structured, web-powered market research and competitive analysis to provide actionable intelligence for product decisions and business opportunities.

redis-developer/redis-ai-resources

A curated collection of code recipes, tutorials, and demos demonstrating how to use Redis for AI applications, vector search, and agent memory systems.

monk1337/resp

RESP is an academic research paper search library and MCP server that queries multiple databases like arXiv, Semantic Scholar, and Google Scholar. It allows developers and AI agents to fetch papers, retrieve citations, and discover related literature.

martaldsantos/gh-copilot-for-enterprise

A comprehensive enterprise-grade hackathon resource featuring 19 challenge tracks to master GitHub Copilot across various roles and tech stacks.

meteora-pro/devboy-tools

Analyze high-level usage patterns in Claude Code sessions to generate graphical periodic digests, metrics, and behavioral archetypes. It processes local log files into structured parquet bundles and markdown reports.

d6t/d6tflow

An AI assistant integration for d6tflow that helps data scientists and engineers scaffold and manage data science pipelines using Claude Code.

longbridge/longbridge-terminal

An AI-native CLI and terminal user interface for the Longbridge trading platform, providing real-time market data, portfolio management, and order execution.

handsomestWei/zhihu-fetch-skill

An intelligent skill for scraping Zhihu collections, articles, and personal interaction history with multi-tier API/Playwright fallbacks, session keep-alive, and automatic Obsidian knowledge base integration.

stevereiner/python-alfresco-mcp-server

A Model Context Protocol (MCP) server for Alfresco Content Services that enables full-text search, metadata filtering, and complete document lifecycle management.

probabl-ai/skills

Executes and audits machine learning experiment reports using a read-only Python script runner and generates markdown digests for narrative tracking.

Dayoooun/korea-stats-mcp

An MCP server that enables AI assistants to query official South Korean statistics from KOSIS via natural language.

fw-ai/cookbook

This skill provides a structured workflow for training and fine-tuning AI models on the Fireworks platform using a coding agent. It covers managed SFT, DPO, ORPO, RFT, serverless and dedicated workflows, and the cookbook repository.

IBM/ibm-watsonxdata-mcp-server

An MCP server that enables AI assistants to manage and query IBM watsonx.data lakehouses using natural language.

WolframResearch/system-modeler-ai-toolkit

Adds Wolfram System Modeler control-panel Explore annotations to Modelica .mo files to enable interactive simulation controls like sliders, checkboxes, and popup menus.

larashero3-dotcom/lieflat-charts

An agent skill that translates user requests into meticulously styled, editorial-quality data visualization HTML charts using template-driven workflows and specific visual rules.

baidu-netdisk/bdpan-storage

Manage Baidu Netdisk cloud storage files and agent memory backups directly through natural language commands.

openai/role-specific-plugins

A collection of customizable role-specific plugins designed for Codex, incorporating domain-specific skills, connector bindings, and interactive workspaces.

mikelove/awesome-multi-omics

A curated reference list of software packages and academic literature dedicated to multi-omics data analysis and multi-table statistical methods.

HKUSTDial/DataMagic

DataMagic converts tabular data into narrated, animated data videos using a declarative screenplay format called DVSpec. It provides AI agents with structured guidance for data analysis, scene planning, chart selection, and voiceover timing.

R6410418/Jackrong-llm-finetuning-guide

An educational knowledge base and collection of recipes for LLM fine-tuning, reinforcement learning, and model conversion.

davaded/Echarts-AI-Skill

An AI agent skill that transforms natural language or tabular data into deterministic Apache ECharts options and exportable HTML/SVG artifacts.

StonyBrookNLP/appworld

AppWorld is an interactive benchmark and simulation environment featuring 9 apps and 457 APIs for evaluating function calling and coding agents.

kiurakku/cursor-kit-for-ai

Cursor Kit for AI provides a curated collection of plugins and production-grade agent skills designed to turn the Cursor AI editor into a role-specific specialist.

mees/calvin

CALVIN is an open-source simulated benchmark designed for training and evaluating language-conditioned policies in long-horizon robotic manipulation tasks. It enables researchers to develop agents capable of executing continuous control based on unconstrained natural language instructions and visual sensor inputs.

sstklen/infinite-gratitude

Infinite Gratitude is a multi-agent parallel research skill that dispatches multiple sub-agents to investigate different angles of a topic and iteratively return structured reports.

MindLab-Research/mint-cookbook

This repository provides comprehensive instructions, architectural guidelines, and scaffolds for managing AI research experiments and model reproduction workflows within a monorepo.

dylanhogg/awesome-python

A comprehensive directory of curated Python libraries and frameworks categorized by domain, including specialized tools for AI agents and machine learning.