Use this DeepCTR sub-skill for SparseFeat, DenseFeat,
Audit datasets for structure, missingness, labeling, suspicious values, duplicate identifiers, and documentation readiness.
Generate or improve a company-specific data analysis skill by extracting tribal knowledge from analysts.
Convert between CSV, TSV, Excel, JSONL, Parquet, and other tabular formats
Evaluates post-launch feature performance against baseline metrics and hypotheses to deliver actionable decision recommendations.
Bulk data enrichment. Adds web-sourced fields (CEO names, funding, contact info) to lists of companies, people, or products. Use for…
Export Claude Code session and analytics data in JSON, CSV, or Markdown formats.
Enforces user-facing data portability in an offline-first app — backup/restore (exact, machine round-trippable) kept strictly separate…
Find and assess datasets for a research question.
Generates a Mermaid sequence diagram showing how data moves between components.
Review data integrity for Rails changes.
Write a Data Management and Sharing Plan (NIH DMSP) or Data Management Plan (NSF DMP, DoD equivalents) — data types, standards…
Establishes a lean product metrics framework, event tracking plan, and analytics dashboard to capture critical user data from day one.
Plan and execute database migrations, data transformations, and system migrations safely with rollback strategies and data integrity…
Large-scale data migrations with validation, rollback, and zero-downtime strategies.
[Deprecated] Optional advanced tool for complex data modeling.
Enforces rigorous safety protocols, multi-layer backups, and phased execution for high-risk production database operations.
Design partitioning and sharding strategies for data at scale.
Orchestrate marketing data collection, transformation, aggregation, and reporting workflows across platforms
Expert data engineer for ETL/ELT pipelines, streaming, data warehousing.
ETL/ELT patterns, batch vs streaming, idempotency, data quality framework, and pipeline orchestration