Agent skills

Join two datasets with automatic strategy selection (joinp vs join vs sqlp)

Write a Data Management and Sharing Plan (NIH DMSP) or Data Management Plan (NSF DMP, DoD equivalents) — data types, standards…

Design field mapping specifications between source and destination systems for synchronizing insurance AMS and CRM data, LOS to reporting…

Database migration patterns: zero-downtime schema changes, data backfills, Alembic, Prisma Migrate, Rails migrations

Plan and execute database migrations, data transformations, and system migrations safely with rollback strategies and data integrity…

Optional advanced tool for complex data modeling.

Design Power BI data model relationships and Power Query transformation specifications for combining insurance and financial services data…

Enforces rigorous safety protocols, multi-layer backups, and phased execution for high-risk production database operations.

ETL/ELT patterns, batch vs streaming, idempotency, data quality framework, and pipeline orchestration

Profile source data quality, completeness, and anomalies before migration to identify cleansing requirements and assess fitness for…

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

Use when the user asks to "design a new data model that stores personal data", "add a retention policy", "figure out how long to keep…

Data science methodology for Python research: EDA, validation, causal inference (IV, DiD, RD, synthetic control), clustering/PCA/UMAP…

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

Build and navigate DSP (Data Structure Protocol) — graph-based long-term structural memory of codebases for LLM agents, storing entities…

Load before calling data-tables or parse-file. Use for natural standalone requests like "what data tables do I have?", "show/list my tables", or "what columns are in this table?", and whenever the…

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

Converts any local folder of mixed documents (docx, pdf, xlsx, duckdb, csv, images, text) into a Google Open Knowledge Format (OKF) v0.2…

QA an analysis before sharing with stakeholders — methodology checks, accuracy verification, and bias detection.

When to activate: data validation, Great Expectations, Pandera, data contracts, drift detection, Evidently, data quality