HR-Analytics

Specialized skill for optimizing cloud data INFRASTRUCTURE costs and resource utilization at the platform level. Use when: rightsizing warehouses, configuring auto-suspend policies, optimizing storage formats, setting budget alerts, or forecasting cloud spend. Do NOT use for query-level cost analysis — use `finding-expensive-queries` instead. Do NOT use for optimizing individual SQL queries — use `optimizing-query-text` or `optimizing-query-by-id` instead.

Specialized skill for data contracts, access controls, compliance, and PII handling. Use when: implementing RBAC/RLS policies, defining data contracts between producers and consumers, handling PII/PHI masking, GDPR/CCPA compliance, or managing data ownership. Do NOT use for dbt model documentation — use `documenting-dbt-models` instead. Do NOT use for data lineage tracing — use `tracing-upstream-lineage` or `tracing-downstream-lineage` instead.

Specialized skill for establishing and monitoring data quality at the INFRASTRUCTURE level. Use when: setting up Great Expectations suites, Soda checks, custom SQL quality monitors, schema drift detection, or anomaly detection logic. Do NOT use for dbt-specific tests — use `testing-dbt-models` instead. Do NOT use for data freshness spot-checks — use `checking-freshness` instead.

General pipeline orchestration for NON-Airflow tools (Dagster, Prefect, custom schedulers). Use when: the user mentions Dagster, Prefect, Luigi, or custom pipeline orchestration. Do NOT use for Airflow — use `airflow` or `authoring-dags` instead. Do NOT use for dbt — use `creating-dbt-models` or `developing-incremental-models` instead.

Cross-system incident response and post-mortem Root Cause Analysis for data platforms. Use when: investigating MULTI-system failures, correlating failures across infra + data + code, writing post-mortem reports, or diagnosing cascading failures. Do NOT use for single Airflow DAG failures — use `debugging-dags` instead. Do NOT use for single dbt model errors — use `debugging-dbt-errors` instead.

Create, manage, and cleanup git worktrees with Claude Code agents across all projects. USE THIS SKILL when user says "create worktree", "spin up worktrees", "new worktree for X", "worktree status", "cleanup worktrees", "sync worktrees", or wants parallel development branches. Also use when creating PRs from a worktree branch (to update registry with PR number). Handles worktree creation, dependency installation, validation, agent launching in Ghostty, and global registry management.