ai-plugins

Refactor and improve code quality across a project using parallel specialized sub-agents with a safety-first iterative approach.

Review local changes or a pull request using the shared multi-perspective review workflow.

Plan, implement, and review a feature request, bug fix, or change specification.

Stress-test a plan, design, or architecture with a relentless structured interview.

Investigate a running production application for bugs, performance issues, stability problems, and optimization opportunities by analyzing pod logs and Jaeger traces.

Refactor and improve code quality across an entire project using parallel specialized sub-agents. Covers Go, TypeScript/React, Python, Rust, Database, Shell/Build, K8s/Config, and Observability domains with a safety-first iterative approach. Use when the user wants to improve code quality, readability, maintainability, or modernize a codebase without breaking functionality.

Review pull requests and local changes with reusable multi-perspective review workflows. Use when the user asks to review a PR, review local changes, review-pr, review-change, code review, or merge request review.

Execute a three-phase Plan -> Code -> Review workflow with iterative implementation until the review passes. Enforces production-readiness with extensive logging, comprehensive testing (unit + E2E), multi-agent code review, and build validation. Metrics and tracing are added when the project already has that infrastructure. Use when the user asks to build a feature, fix a bug, or make a structured change and wants planning, production-grade coding, and review in one workflow.

Stress-test a plan, design, or architecture by conducting a relentless structured interview. Leverages review perspectives for systematic dimension coverage and explores the codebase to ask sharper questions. Use when a user wants to pressure-test an idea, get grilled on a design, or mentions "grill me".

Investigate a running production application for bugs, performance issues, stability problems, and optimization opportunities by analyzing pod logs and distributed traces. Spawns parallel specialist sub-agents, cross-references memory for recurring issues, and produces a prioritized improvement plan.