github-ops

Workflow-first MCP server design with schema-first tools, context-aware outputs, and evaluation discipline.

Multi-model orchestration and advisor routing: tri-model review and canonical advisor routing.

Subagent orchestration, wave execution, persistent completion, autonomous delivery, and migration batching.

Analytics engineering, dbt patterns, BigQuery optimization, data quality, and pipeline workflows.

Core developer workflow skills: planning, execution, communication, and powerup discovery.

ML pipeline design, experiment tracking, model evaluation, training debugging, and reproducibility.

Quality gates for spec-driven development: adversarial plan verification and structured code review.

Search-first codebase understanding, context retrieval, mapping, pattern detection, and living project intelligence.

Graph-backed memory and context optimization workflows with graphify first and document conversion helpers second.

Error diagnosis, fault isolation, log forensics, and incident investigation.