yeaight7/agent-powerups

Prompt, skill, red-team, and agent behavior evaluation workflows.

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

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

Safe refactoring, dead-code removal, legacy modernization, and dependency hygiene.

Review-first runbooks for connected-app workflows and multi-system deployment sequencing.

Context-efficient routing: dispatch tables for workflow, review, and codebase-intelligence commands.

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

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

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

Documentation architecture, API reference authoring, ADR writing, readme hardening, and doc quality.

GitHub review, comment handling, and CI triage workflows with approval-gated write actions.

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

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

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

Quality enforcement: TDD discipline, code review workflows, release verification, and CI failure analysis.

Security review guidance for agent configs, MCP and filesystem exposure, red-team scenarios, and audit prompts.

Skill creation and extraction workflows for reusable agent guidance.

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

Requirements clarification, phase planning, workstreams, and wave-based execution for reviewable delivery.

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

Browser, MCP, retrieval, and agent runtime integration skills with conservative setup and safety boundaries.