Agent skills for OpenAI Agents SDK

Profile a CSV/TSV/Excel file - detect format, compute statistics, show value distributions

Generates comprehensive data profiling reports and automated exploratory data analysis (EDA) for various datasets.

Data quality and pipeline health check — freshness, schema drift, null rates, orphaned records, pipeline status.

Quality dimensions quick reference and remediation decision tree for tabular data assessment

Market data discovery and retrieval for A-shares.

Organize and manage due diligence data rooms

Expert data processing specialist with intelligent DuckDB/Polars selection for maximum performance.

Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything.

Use when large data ingestion, backfill, export, ETL, warehouse loading, manifest catch-up, or table synchronization needs to become much…

Transform raw data into analytical assets using ETL/ELT patterns, SQL (dbt), Python (pandas/polars/PySpark), and orchestration (Airflow).

Use when preparing the data, annotation, and reproducibility materials for a Language (LSA) manuscript — shared datasets and code, glossed…

Use when preparing the data, materials, and transparency posture for a Social Psychology Quarterly (SPQ) manuscript.

Patterns for visualizing data on maps including choropleth maps, heat maps, 3D visualizations, data-driven styling, and animated data.

Create publication-quality plots and visualizations using matplotlib and seaborn.

Transforms raw datasets into interactive shadcn/ui dashboards and professional charts using libraries like Recharts, Chart.js, and ECharts.

PgBouncer, connection optimization, and pooling strategies for database performance.

Architects robust database systems by implementing multi-tenant isolation, transaction boundaries, and data consistency strategies.

Use this skill when the user needs to choose a database, design a schema, set up Supabase or another database, write queries, handle…

Database architecture design, schema optimization, query performance tuning, and data migration.

Streamlines the end-to-end database lifecycle from schema modeling and indexing to secure production migrations.

Explore the PostgreSQL database schema, query data, generate Prisma migrations, and audit data integrity.