PDF documents contain valuable data that is difficult to access programmatically. This skill provides AI agents with the capabilities to extract text, tables, and form data from PDFs, and to manipulate documents through merging, splitting, and formatting operations.

Users need to communicate data insights through visual formats but lack the expertise to select the right chart type or library. This skill provides AI-driven guidance to generate clear, professional visualizations using matplotlib, seaborn, plotly, and altair.

Writing efficient SQL queries requires knowing common patterns and anti-patterns. This skill provides ready-to-use examples for CTEs, window functions, joins, and indexing strategies.

Writing database code is complex and error-prone. This skill provides battle-tested SQLAlchemy 2.0 patterns for models, queries, async sessions, transactions, and migrations.

Developers need to extract, filter, and transform data from configuration files and API responses. This skill provides ready-to-use patterns for jq and yq so you can quickly query and modify structured data without memorizing syntax.

Vector search feels slow or costly when indexes are misconfigured. This skill provides tuning templates and heuristics to improve latency, recall, and memory use for HNSW and quantization strategies.

Slow queries cause delays and high database costs. This skill provides clear optimization patterns and indexing guidance to improve performance and eliminate bottlenecks.

Slow Spark jobs waste cluster time and delay analytics. This skill provides proven tuning patterns for partitioning, caching, joins, and memory to improve performance.

Building fast semantic search is complex and error prone. This skill provides proven templates for common vector databases and hybrid retrieval methods.

You need accurate risk measurements for portfolio management. This skill provides formulas and examples for VaR, Sharpe ratio, drawdowns, and other key metrics.

You need accurate answers from private documents and changing data. This skill explains RAG components and retrieval patterns to ground responses with sources.

PostgreSQL schema design requires knowledge of data types, indexing strategies, constraints, and performance patterns. This skill provides comprehensive guidance on PostgreSQL-specific best practices, advanced features, and common pitfalls to help you build efficient, maintainable database schemas.

Machine learning teams struggle to connect data preparation, training, validation, and deployment into reliable production workflows. This skill provides comprehensive guidance for building end-to-end MLOps pipelines with proper orchestration, monitoring, and deployment strategies.

Many dashboards overwhelm teams with unclear metrics and cluttered layouts. This skill guides KPI selection, visualization best practices, and dashboard patterns that focus attention on actionable insights.

Building reliable dbt transformations can be slow without a clear structure. This skill provides layered model patterns, tests, and incremental strategies you can apply quickly.

Data insights often fail to move stakeholders without a clear narrative. This skill provides frameworks and templates to turn metrics into persuasive stories that inspire action and drive decisions.

Data quality issues cause failed analytics and broken pipelines. This skill provides proven Great Expectations, dbt tests, and data contract patterns to prevent them.

Database migrations can break production if rushed. This skill provides proven patterns for safe schema changes, data transforms, and rollbacks across Sequelize, TypeORM, and Prisma.

Trading backtests often hide bias and overstate performance. This skill provides patterns and checks to design trustworthy backtests that handle look-ahead bias, survivorship bias, and transaction costs properly.

Airflow DAGs can fail when structure and retries are not consistent. This skill provides clear patterns for design, sensors, testing, and alerts that improve pipeline reliability.