AI Agent Workflow Collection

Generate and evaluate genuinely different approaches to a product, workflow, or system problem. Use when the user explicitly wants a bold, contrarian, experimental, or non-incremental alternative and a testable recommendation.

Refine underdefined product or system architecture through focused interactive decisions. Use when the user wants architecture sparring before a formal implementation plan or contract update.

Implement testable production behavior through a red-green-refactor cycle. Use for bug fixes, features, and behavior-changing refactors, whether or not they belong to a formal plan phase.

Explain a pull request, commit range, branch, or local diff from a system-design perspective. Use for practical understanding of changed behavior, boundaries, flow, ownership, operations, risks, and verification rather than defect review.

Verify terminal-hosted CLI or TUI behavior with repeatable local evidence. Use for output, prompts, interactive input, signals, hangs, resizing, startup, exit status, or terminal restoration.

Create one concise evidence-linked product journey record for one actor pursuing one goal. Use when product behavior needs traceable ownership, acceptance, telemetry, or service-flow documentation for a current decision or delivery gate.

Review dependency provenance and reproducibility without modifying them. Use when manifests, lockfiles, vendor state, generated dependency state, registries, fetched tools, or version pins change.

Review documentation for drift caused by the current code or configuration change. Use to identify concrete inaccuracies and, when authorized, repair only directly affected documentation.

Go Code Review: Reviews Go code for idiomatic patterns, error handling, concurrency safety, and performance. Covers goroutines, channels, interfaces, error wrapping, context propagation, and common Go anti-patterns. Use when the user wants a review of Go code, mentions .go files, Go modules, goroutines, channels, gin, echo, fiber, gRPC, or any Go framework.

Supplement code review with macOS, Swift, and SwiftUI-specific correctness analysis. Use for a diff, flow, module, or full app involving state ownership, structured concurrency, sandboxing, entitlements, XPC, signing, or notarization.

Validate exactly one implemented phase or scoped change against its authoritative contract. Use after implementation to re-derive criterion-level conclusions from current evidence and fix only required implementation gaps.

Create a high-level plan with research for user review before generating detailed subplans. Use when the user asks to plan, design, scope, or break down a feature or task. Keywords: plan, planning, design, scope, research, plan document, high-level plan.

Create, update, or consolidate adopted current-state documentation under docs/context/. Use for durable implemented architecture, ownership, runtime, domain, flow, terminology, or engineering-practice context.

Review cross-cutting operational readiness after implementation and before deployment. Use when a concrete change may alter runtime prerequisites, failure visibility, deployment order, rollback, recovery, or production failure modes.

Make a minimal evidence-backed update to a non-plan product, architecture, API, schema, or behavior contract. Use when implementation or validation cannot determine correctness from the current authoritative contract.

Resolve one correctness-blocking external or version-specific technical uncertainty through bounded investigation. Use when cheap local inspection cannot establish framework, library, tool, runtime, protocol, or platform behavior needed by the current task.

Review whether existing tests and verification credibly prove a scoped behavior contract. Use during validation when evidence may omit important behavior or provide false confidence.

Verify graphical browser, desktop, or Electron behavior through the actual interface. Use when screenshot, accessibility, console, network, trace, or browser-driven evidence is required; exclude terminal-hosted interfaces.

Gerencia commits automaticos ao final de cada fase do SDLC. Garante que artefatos de cada fase sejam commitados e rastreados.