Data Science & Analytics Bundle

Data analysis, SQL mastery, visualization, statistical modeling, and data pipeline skills for data professionals.

Browse all skill bundles

Included Skills (90)

Ibis — Ibis translates pandas‑like expressions into SQL, allowing analysts to perform complex analytics directly on the database that stores their data. It supports DuckDB, PostgreSQL, BigQuery, Snowflake, Spark, Polars, and many other engines, so a single script runs efficiently across multiple databases. Data scientists and engineers develop locally and deploy to production warehouses without loading data into memory.
dlt (Data Load Tool) — Python-First Data Ingestion — dlt is an open‑source Python library that automatically loads data from APIs, files, and databases into data warehouses and lakes, inferring schemas and managing incremental state. It enables data engineers and analysts to build Python pipelines that load REST APIs into DuckDB, BigQuery, Snowflake, or Postgres, set up incremental or merge loading, and enforce schema contracts, replacing hand‑written ETL scripts or hosted ELT connectors.
Apache Spark — Apache Spark is a distributed engine that processes batch, SQL, and streaming data, accessible through Python via PySpark. It enables users to perform large‑scale computations, build ETL pipelines, analyze data at scale, read Parquet files from S3, and stream from Kafka. The skill is essential for data engineers and analysts handling big data workloads.
Data Validator — The Data Validator examines CSV, JSON, and database exports for missing values, type mismatches, duplicates, outliers, and schema violations. Data engineers and analysts use it to audit ETL pipelines, verify data freshness, and enforce data contracts between teams. By ensuring consistent, high‑quality data, it supports reliable analytics and decision making.
Data Warehouse Analyst — This tool helps data analysts plan, validate, and review read-only warehouse queries to ensure accurate, privacy-compliant, and reproducible business insights.
Google Cloud Solution Agentic Analytics Spark Knowledge Catalog — The skill delivers a fully governed analytics solution that unifies Google Cloud Knowledge Catalog with Managed Service for Apache Spark, allowing data scientists to process structured and unstructured data from S3, Azure Blob, AlloyDB, and Iceberg in a single workflow. It enforces metadata governance through Knowledge Catalog aspect types, ensuring data integrity and compliance. Developers build robust analytics pipelines with confidence using agentic IDEs such as VS Code and Antigravity via the Google Cloud Data Agent Kit.
Data Engineering Expert — This skill helps data scientists and analysts by building scalable data pipelines, ETL/ELT systems, and robust data infrastructure.
BigQuery Pipeline Auditor — This tool audits Python and BigQuery pipelines for cost efficiency, idempotency, and production readiness to help data engineers prevent expensive runtime errors.
BI Calculation Architect — This tool crafts, debugs, and optimizes complex BI metrics across Power BI, Tableau, and Looker to ensure accurate reporting for data analysts.
Jupyter Notebook Assistant — Assists data scientists and researchers with interactive data analysis, visualization, and reproducible research using Jupyter notebooks.
Polars — Polars is a high‑performance in‑memory DataFrame library that processes datasets up to 100 GB, leveraging lazy evaluation and parallel execution on an Apache Arrow backend. It enables data scientists and engineers to build faster ETL pipelines and analytics workflows than with pandas, provided the data fits in RAM. For workloads exceeding memory limits, users typically switch to Dask or Vaex.
Advanced Analytics Dashboard — Dashboard metric register: metric, source module, formula, period, value, target, trend, owner and last-updated, as CSV, SQL, JSON Schema or Notion on request. Use for KPI dashboards.
Embedded Analytics Database — This skill helps data professionals use DuckDB, an embedded analytical database, for local data exploration and ETL pipelines.
BigQuery ML Assistant — This tool empowers data analysts to execute advanced machine learning, predictive modeling, and generative AI tasks directly within BigQuery using SQL.
Power BI Visualization Consultant — This expert assistant helps data analysts and developers design accessible, high-impact Power BI reports through structured visualization selection and user-centric layout strategies.
BigQuery Data Analyzer — Analyze large datasets using Google BigQuery, enabling data professionals to run SQL queries and build machine learning models.
Bigquery Basics — Manages datasets, tables, and jobs in BigQuery. Use when you need to interact with BigQuery, run SQL queries, manage BigQuery resources (datasets, tables, views), or perform basic data ingestion and analysis.
Malloy — Malloy translates semantic models into SQL for major data warehouses, enabling analysts and developers to build reusable models, sources, views, joins, and nested queries. By running .malloy files from VS Code, the malloy‑cli, or Node.js, users replace repetitive SQL with maintainable, reusable measures, streamlining complex analytics. The result is a more efficient, consistent, and collaborative data modeling workflow.
Snowflake Development Assistant — Assists data engineers and analysts in developing Snowflake SQL, data pipelines, and Snowpark Python applications efficiently and effectively.
Great Expectations — Great Expectations (GX Core) is a Python framework that allows data professionals to define precise expectations for datasets, such as null counts, value ranges, uniqueness, and allowed values. It validates pandas DataFrames or SQL tables against these expectations, integrates checkpoints into data pipelines, and generates Data Docs that clearly indicate which checks passed or failed. Analysts, data engineers, and data scientists benefit from reliable, documented data quality assurance.
SQL Query Generator — This tool transforms natural language requirements into optimized SQL queries, helping analysts and engineers efficiently retrieve data across various database platforms.
Analytics Reporting Assistant — This skill enables the Google Analytics Data API and generates customized reports for developers needing to programmatically query metrics and dimensions from properties.
Evidence Dashboard Assistant — Provides expert guidance for Evidence, helping developers build data reports as code and create self-service analytics dashboards from SQL and Markdown.
MotherDuck SQL Assistant — Provides expert guidance for MotherDuck, helping developers perform SQL analytics on cloud data and build hybrid local-cloud data pipelines.
Bigquery Troubleshooting — The skill provides diagnostic workflows and root‑cause analysis for BigQuery jobs that are broken, failing, or slow, pinpointing bottlenecks in execution graphs, query plan stages, system performance, or cost spikes. It interprets symptoms, isolates bottlenecks, and determines remediation steps for unexpected workload expenses or performance issues, benefiting data engineers and analysts who need to resolve operational problems quickly. The skill does not cover SQL writing, proactive capacity planning, or storage layout design.
Product Analytics — Use when defining product KPIs, building metric dashboards, running cohort or retention analysis, or interpreting feature adoption trends across product stages.
Basin — Basin enables engineers to construct and debug analytics workflows on Cloudflare’s platform with Basin Pipelines, Catalog, and SQL. It streams data into R2 Iceberg tables, manages catalogs, and queries those tables while integrating seamlessly with legacy Data Platform, Pipelines, R2 Data Catalog, and R2 SQL interfaces. Data engineers and analysts benefit from a reliable, end‑to‑end data processing and querying solution within Cloudflare’s ecosystem.
Data Analysis — Analyze spreadsheet data, generate insights, and create visualizations. Use when a user asks to analyze data, explore a dataset, find trends, generate statistics, create charts from CSV or Excel data, summarize data, or answer questions about tabular data.
Openpiv — The Openpiv skill extracts velocity fields from image pairs by cross‑correlating interrogation windows and validating vectors to eliminate spurious data. It automatically computes vorticity, strain rate, and turbulence statistics, delivering precise flow analysis. Engineers and researchers in fluid dynamics and flow visualization rely on this tool for accurate velocity field measurements.
BigQuery DataFrames Assistant — Generates optimized Python code using BigFrames to help data engineers and analysts perform scalable BigQuery data processing, analysis, and machine learning tasks.
Power BI Architect — This tool provides expert design reviews for Power BI developers to optimize data model architecture, relationships, and performance for scalable reporting solutions.
Google Cloud Solution Agentic AI Data Science Workflow — The Google Cloud Solution Agentic AI Data Science Workflow designs a customized, multi-product agentic data science architecture on Google Cloud, embedding opinionated best practices. It is used by architects building agent-based data analytics or machine learning solutions across multiple products. The skill is not intended for simple queries, non-agentic pipelines, general cloud reviews, or writing agent code.
Spark Optimization — Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.
Product Analytics Strategist — This skill assists product managers and developers in implementing tracking, analyzing user behavior, and defining key metrics to drive data-informed product decisions.
Mixpanel Analytics Automator — This tool enables product managers and developers to automate Mixpanel data retrieval, event tracking, and cohort management directly through Rube MCP workflows.
Data Science Expert — This skill provides advanced analytics, machine learning, and statistical modeling support to help data professionals execute complex data workflows and generate actionable business insights.
Weather Pipeline Performance Diagnosis — Diagnose slow weather-data workflows by measuring discovery, transfer, parsing, scientific processing, and rendering separately before changing code.
Data Quality Orchestrator — This skill assists data engineers in implementing robust validation frameworks, dbt testing suites, and data contracts to ensure reliable, high-quality production data pipelines.
Power BI Optimizer — This expert diagnostic tool helps Power BI developers systematically identify, analyze, and resolve performance bottlenecks within data models, reports, and complex query structures.
Google Analytics Automator — This tool streamlines Google Analytics 4 reporting and property management tasks for data analysts by automating complex data retrieval through the Rube MCP interface.
Product Analytics Advisor — Provides expert product analytics guidance, enabling product teams to define metrics, analyze funnels, and make data-driven decisions.
Invokely Statistics — Use Invokely MCP to find official statistics, retrieve values and series, compare or rank places, and report each figure with its period, unit, and source citation.
Customer Data Routing — This skill helps developers and marketers track and route customer data to various analytics and marketing tools using Segment's CDP.
Snowflake Semantic Modeler — This tool enables data engineers to efficiently create, modify, and validate Snowflake semantic views using the Snowflake CLI for streamlined data modeling.
Pandas Data Assistant — This skill assists users with loading, cleaning, transforming, and analyzing tabular data using the pandas library in Python.
MySQL Database Management — This skill helps developers manage MySQL databases, covering installation, SQL queries, schema design, and client integration with Node.js and Python.
Pipeline Health Analyzer — This tool evaluates sales opportunity quality and win probability to help sales managers prioritize pipeline reviews and improve data hygiene.
Codonfm Finetune — Fine-tune public CodonFM Encodon checkpoints on labeled coding-sequence or coding-variant data using LoRA, head-only, or full fine-tuning. The skill is employed when a user explicitly requests regression or classification fine-tuning of CodonFM or Encodon. It supports only generic public‑v1 Encodon workflows, rejecting Decodon, MissenseDataset, missense_synom_agg, and generation workflows.
Neon Postgres — Neon Postgres offers expert guidance on configuring and optimizing Lakebase Postgres on Neon, covering connections, pooling, schema migrations, branching, autoscaling, and advanced features like read replicas and logical replication. Developers and database administrators benefit from best practices for inspection, search, and integration with Neon tools, ensuring efficient database management and performance.
Accelerated Computing Cudf — Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
Agent Platform Rag Engine Management — The Agent Platform Rag Engine Management skill enables professionals to list, inspect, and query RAG corpora and files within the Agent Platform, retrieving grounded contexts via the Google GenAI SDK. Data scientists and AI developers use it to generate content anchored in a specific RAG corpus, ensuring precise, contextually relevant information. It is not intended for general database queries or other RAG products such as Google Workspace RAG or gRAG.
Monte Carlo Monitoring Advisor — Analyze data coverage, create monitors for warehouse tables and AI agents. Covers coverage gaps, use-case analysis, data monitor creation, and agent observability.
Scanpy — Scanpy is a scalable Python toolkit that analyzes single-cell RNA‑seq data using the AnnData framework. It supports end‑to‑end workflows, including quality control, normalization, dimensionality reduction, clustering, marker gene identification, visualization, and trajectory analysis. Researchers and bioinformaticians use Scanpy to extract biological insights from complex single‑cell datasets.
Command Center Designer — This skill provides design guidelines and implementation patterns for developers building high-stakes monitoring dashboards, enterprise control rooms, and real-time data visualization interfaces.
Power BI Architect — This assistant helps data professionals design, optimize, and document efficient Power BI semantic models by providing expert guidance on DAX, schemas, and performance.
Pandas Performance Accelerator — This tool accelerates pandas operations by utilizing a ClickHouse engine, helping data scientists process large tabular datasets and cross-source joins with familiar syntax.
Video Reasoning Annotator — This pipeline transforms raw video into structured Chain-of-Thought training data, providing data scientists with automated multi-level captions, detailed descriptions, and reasoning-based QA pairs.
TimesFM Time Series — Forecast time series data using Google's TimesFM foundation model for zero-shot prediction, assisting data scientists and analysts.
Lancedb — LanceDB is an embedded, serverless vector database that stores data in the Lance columnar format on local disk or object storage, accessed through Node.js, Python, and Rust clients. It enables lightweight, local vector search, full‑text search, hybrid search, and filtering without requiring a separate server, making it ideal for developers building RAG systems or applications that need fast, on‑device vector retrieval.
Business Intelligence Analyst — This skill empowers professionals to transform complex data into actionable strategic insights through advanced analytics, predictive modeling, and effective data storytelling techniques.
RAG Pipeline Architect — This tool helps developers design, optimize, and evaluate production-grade RAG pipelines by utilizing data-driven chunking strategies and rigorous retrieval performance metrics.
D3 Visualization Assistant — This skill helps developers build custom interactive data visualizations using D3.js for charts, graphs, maps, and complex diagrams.
Advanced Data Scientist — This skill provides expert statistical modeling, causal inference, and machine learning workflows to help data scientists build robust, production-grade predictive systems.
Scala Pro — Master enterprise-grade Scala development with functional programming, distributed systems, and big data processing. Expert in Apache Pekko, Akka, Spark, ZIO/Cats Effect, and reactive architectures.
Airflow Pipeline Architect — This skill assists data engineers in designing, testing, and deploying production-ready Apache Airflow DAGs using industry best practices for robust workflow orchestration.
Analytics Quality Framework — This skill helps data engineers and analysts establish robust testing, automated monitoring, and incident response protocols for analytics models and dashboards.
Cohort Performance Analyzer — This tool enables business analysts to evaluate performance trends and diagnose conversion patterns across various customer segments, booking vintages, and acquisition channels.
Analytics Instrumentation Architect — This skill helps product and data teams design, govern, and maintain standardized event tracking plans for robust analytics pipelines.
Physical AI Curator — This skill manages NVIDIA Cosmos Curator pipelines and PAIDF data mining workflows to help engineers process, annotate, and prepare high-quality datasets for physical AI.
Analytics Admin Automator — This tool enables developers to programmatically manage Google Analytics accounts, properties, and integrations, streamlining configuration tasks through the Google Cloud CLI.
Amplitude Analytics Automator — This tool enables product managers and developers to automate event tracking, user identification, and cohort management within Amplitude using Rube MCP.
Interactive Visualization Library — This tool enables data scientists and analysts to create interactive, web-ready charts featuring zoom, pan, and hover capabilities for dynamic data exploration.
Echarts — The skill enables developers to build interactive data visualizations using Apache ECharts, creating charts, dashboards, and data‑driven graphics in React, Vue, or vanilla JavaScript. It supports server‑side SVG rendering and smooth migration from ECharts 5 to 6, giving front‑end engineers and data‑visualization specialists robust, scalable chart solutions.
Hugging Face Dataset Manager — This tool enables developers to create, configure, and perform SQL-based transformations on Hugging Face Hub datasets for streamlined data management workflows.
Spreadsheet Data Analyst — This tool profiles, cleans, and analyzes spreadsheet exports using code to provide accurate, reproducible business insights and metrics for data-driven decision makers.
Recsys Pipeline Architect — Designs composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework
Qdrant Performance Optimizer — This skill diagnoses and resolves latency and throughput issues in Qdrant, helping developers optimize search performance for high-load or data-intensive vector database environments.
Functional Pipeline Reference — This tool provides developers with a concise reference for pipe and flow operations to effectively chain functions and build data pipelines in fp-ts.
Database Design — Database design principles and decision-making. Schema design, indexing strategy, ORM selection, serverless databases.
Mixpanel Analytics Integration — This skill helps developers integrate Mixpanel analytics into web and mobile applications for tracking user behavior and product performance.
Loyalty Analytics Engine — This tool empowers marketing and operations teams to analyze member behavior, segment audiences, and evaluate experiment performance through data-driven insights.
Statistical Visualization Assistant — This skill enables data scientists to generate publication-quality statistical graphics and complex multivariate plots from tabular datasets using the Seaborn Python library.
D3.js Visualization Expert — This skill assists developers in creating sophisticated, interactive, and custom data visualizations using the D3.js library for high-quality graphical output.
AOI Training Pipeline — This pipeline automates end-to-end model optimization by chaining AutoML hyperparameter tuning with DEFT loop refinement for high-performance NVIDIA AOI model training.
Functional Data Transformer — This skill provides TypeScript developers with practical functional patterns for efficiently transforming, grouping, and safely accessing complex data structures in everyday coding tasks.
Depmap — The Depmap skill retrieves and analyzes the latest Cancer Dependency Map release, integrating CRISPR Chronos gene effect data, cancer model annotations, omics biomarkers, and PRISM drug sensitivity. It enables researchers to conduct cancer‑selective dependency, co‑essentiality, and synthetic‑lethality analyses with accurate identifiers and built‑in statistical validation. This tool streamlines comprehensive dependency profiling for oncology investigators and drug discovery teams.
Data Storytelling — Transform raw data into compelling narratives that drive decisions and inspire action.
Weather Data Reproducibility — Record and verify provenance manifests for weather-data inputs and derived artifacts, including object identity, selections, software versions, transformations, and hashes.
Data Enrichment Optimizer — This skill helps RevOps and data engineering teams maximize data quality and minimize costs by optimizing provider selection and waterfall enrichment sequences.
Data Extractor — The Data Extractor skill parses any document format to produce structured output, converting PDFs, invoices, forms, and other files into JSON or CSV. It automatically identifies and extracts relevant fields, enabling users to retrieve precise data from documents without manual effort. This capability benefits analysts, data engineers, and business users who need reliable, machine-readable information from diverse document types.