Best Best AI Agent Skills for Data Analysis

Audit websites for SEO, technical, content, performance and security issues using the squirrelscan cli.

The xlsx skill provides guidelines and requirements for creating, editing, and analyzing Excel files, ensuring zero formula errors and following established formatting standards for various types of financial models.

You are an expert in analytics implementation and measurement. Your goal is to help set up tracking that provides actionable insights for marketing and product decisions.

Transform slow database queries into lightning-fast operations through systematic optimization, proper indexing, and query plan analysis.

Master Retrieval-Augmented Generation (RAG) to build LLM applications that provide accurate, grounded responses using external knowledge sources.

Comprehensive patterns for designing effective Key Performance Indicator (KPI) dashboards that drive business decisions.

Transform raw data into compelling narratives that drive decisions and inspire action.

Interact with Google NotebookLM to query documentation with Gemini's source-grounded answers. Each question opens a fresh browser session, retrieves the answer exclusively from uploaded documents, and closes.

Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.

Build comprehensive 3-5 year financial models with revenue projections, cost structures, cash flow analysis, and scenario planning for early-stage startups.

Practical implementation guide for GDPR-compliant data processing, consent management, and privacy controls.

Builds and validates trading strategy backtests using robust methodologies to avoid biases and errors. Developers gain increased confidence in their strategy's reliability through structured tests and comprehensive analysis techniques.

Guide to selecting and optimizing embedding models for vector search applications.

Implements systematic checks for data quality in pipelines using frameworks like Great Expectations and dbt. By automating these validations, it ensures data accuracy, consistency, and compliance, significantly reducing manual oversight and error rates.

Optimizes vector indexes for enhanced production performance by tuning HNSW parameters and implementing quantization strategies. Developers benefit from improved search latency and memory efficiency, ensuring faster and more scalable vector searches in large datasets.

Implements efficient similarity search workflows for various applications, including semantic search systems and recommendation engines. By utilizing this skill, developers can significantly improve search accuracy and performance, ensuring quick retrieval of similar items even from large datasets.

Handles the integration of vector similarity with keyword-based search methods in retrieval-augmented generation systems. This skill enhances search effectiveness by combining semantic understanding with precise keyword matches, improving recall for domain-specific queries.

Facilitates the organization and quality assurance of data transformation models using dbt. This skill enhances data integrity and efficiency by providing structured patterns for building reliable data pipelines and documentation.

Calculates a variety of risk metrics for investment portfolios, such as Value at Risk and drawdown analysis. By installing this skill, users can enhance their portfolio management capabilities and make informed risk-based decisions.

Handles the extraction, analysis, and interpretation of data from memory dumps in digital forensics. By automating these processes, it boosts incident response efficiency and enhances the accuracy of malware investigations.

Defines best practices and patterns for constructing DAGs in Apache Airflow, including task dependencies and operator usage. Developers benefit from enhanced productivity and reduced errors by following these production-ready patterns to build and maintain their workflow orchestration.

Optimizes the performance of Apache Spark jobs through various strategies like tuning memory and executor configurations. By implementing these optimizations, developers significantly reduce execution time and handle larger datasets more efficiently.

Facilitates web data extraction by rendering JavaScript and bypassing anti-bot measures to capture dynamic content. Automates the process of gathering structured data from websites, saving developers time and reducing the likelihood of errors in data collection.

Implements high-performance analytics patterns for ClickHouse database management. By utilizing these patterns, users can optimize data storage and query execution, leading to efficient performance in analytical processing tasks.

MarkItDown is a Python tool developed by Microsoft for converting various file formats to Markdown, particularly useful for converting documents into LLM-friendly text format.

Facilitates the creation of publication-ready scientific figures by transforming data into visually appealing visualizations. Developers benefit from streamlined workflows that enhance figure quality, ensuring compliance with journal standards and accessibility for colorblind readers.

Conducts detailed exploratory data analysis on various scientific file formats to identify data quality and key insights. This automation helps researchers by providing comprehensive markdown reports, facilitating faster decision-making in their analyses.

Enables semantic search and content extraction from various web pages based on user intent. Speeds up research and information retrieval by allowing users to automate the search process and get structured responses.

Extracts usage cost data for AI models from CodexBar logs, providing insights into which models are most cost-effective. This helps developers optimize usage and manage expenses by automating the extraction and summarization of cost information.