Skills for data processing, visualization, and analytics pipelines.
Azure Database for PostgreSQL management. Schema design, query optimization, Citus distributed tables, and pgvector setup.
Transforms raw data and analysis into polished, structured reports in Markdown, HTML, or PDF format with executive summaries and visualizations.
Analyzes Excel and CSV files to produce statistical summaries, pivot tables, charts, and actionable insights without leaving your AI workflow.
Profiles, cleans, and standardizes messy datasets by detecting and fixing inconsistencies, outliers, duplicates, and formatting issues.
Analyzes SQL queries for performance issues, rewrites slow queries, recommends index strategies, and explains execution plans across PostgreSQL, MySQL, and SQLite.
Reshapes, merges, filters, and transforms JSON data structures using declarative mappings with schema validation and diff output.
Create and execute Jupyter notebooks for data analysis
Build operational metrics dashboards with Grafana, Prometheus, or Recharts displaying real-time KPIs, time-series charts, and configurable alerts.
Generates data visualizations, charts, and dashboards using Python (matplotlib, plotly, seaborn), JavaScript (D3, Chart.js), and BI tool configurations.
Optimizes Python pandas workflows by writing efficient DataFrame operations, fixing common performance pitfalls, and converting between pandas, polars, and SQL.
Design and implement A/B tests with proper statistical methodology, sample size calculation, feature flags, and significance testing for conversion optimization.
Designs and implements ETL/ELT data pipelines using Python, SQL, and orchestration tools like Airflow, dbt, and Prefect for batch and streaming workflows.
Build data quality validation pipelines with schema enforcement, anomaly detection, referential integrity checks, and data quality reports.
Designs relational and NoSQL database schemas with proper normalization, indexing strategies, migration scripts, and entity-relationship diagrams.
Collects data from REST and GraphQL APIs with pagination, rate limiting, error handling, authentication, and output normalization into structured formats.
HF Hub CLI for models, datasets, repos, and compute jobs
Create and manage datasets with configs and SQL querying
Model evaluation with vLLM/lighteval and eval tables
Train models with TRL: SFT, DPO, GRPO, GGUF conversion
Transforms, cleans, and converts data between CSV, JSON, Excel, and other tabular formats with column mapping, type casting, and validation.
Access protein structure predictions from AlphaFold DB
Fetch and analyze Federal Reserve economic data series
Web scraping, search, and browsing toolkit for AI agents. Scrape pages, search the web, browse interactive sites.