dotfiles

Use for deeper DDD decisions: strategic modeling, subdomains, bounded contexts, and integration risk.

Use when complexity is spreading and you need a simpler model, clearer abstractions, and lower cognitive load.

Use for boundary design, dependency direction, and keeping business policy separate from technical detail.

Use for readability, naming, small functions, and readable behavior-preserving implementations.

Use for disciplined implementation decisions, defensive coding, and maintainable construction choices in real code.

Use when moving from model intent into concrete tactical patterns, events, and distributed integration choices.

Use when selecting enterprise architecture patterns and avoiding accidental anti-patterns in complex business systems.

Use for practical smell-to-refactoring choices and explicit safety planning in difficult code paths.

Use for pragmatic engineering decisions, uncertainty handling, quality habits, and practical design tradeoffs.

Use when you need to search the web for current information, verify facts, or look up recent documentation using the pplx-search tool

Use when the user wants current information, recent documentation, fact verification, changelogs, release status, or source-backed web research via Perplexity.

Use when Kevin asks for a ready-to-paste implementation prompt for a Linear issue, or asks how to prompt an agent to implement an issue. Builds a prompt from the issue and repo workflow, emphasizing isolated worktrees/branches, red-green TDD, safe subagent parallelism, docs, verification, and final reporting.

Use for data-intensive systems where correctness depends on ownership, durability, consistency, replication, partitioning, schema evolution, events, streams, replay, or derived data.

Use when a task depends on domain language, bounded contexts, business rules, aggregates, entities, value objects, context mapping, or selective Domain-Driven Design Distilled guidance.

Use when changing legacy code with weak tests, unclear behavior, hidden dependencies, difficult setup, or when the user asks for characterization tests, seams, or Michael Feathers style safe change.

Use when changing existing code structure without intending behavior changes, doing preparatory cleanup, reviewing refactors, reducing code smells, or asking an agent to apply Martin Fowler Refactoring guidance.

Use for services, APIs, workers, queues, deployment paths, production readiness, operational reviews, timeouts, retries, backpressure, observability, or Release It style reliability work.

OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex".

Runpod CLI to manage your GPU workloads.

This skill should be used when writing or reviewing Swift code for iOS or macOS projects. Apply modern Swift 6+ best practices, concurrency patterns, API design guidelines, and migration strategies. Covers async/await, actors, MainActor, Sendable, typed throws, and Swift 6 breaking changes.

Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, macOS-specific APIs, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.