Desenvolvimento

Convergence diagnostics, fit evaluation, and debugging for Marketing Mix Models. Use when checking rhat, ESS, divergences, evaluating model fit metrics (R-squared, MAPE, wMAPE), debugging sampling issues, assessing overfitting, running model comparison (LOO/WAIC), or validating cross-validation results. Also activate when the user encounters convergence warnings, poor model fit, or needs to unders

Use when tracking tech debt across a codebase, when planning a refactor, when deciding whether to rewrite vs incrementally improve, when a workaround has appeared in three places, or when a refactor PR is about to be combined with feature work.

Remove a saved preference from CLAUDE.md. Triggered by /forget or phrases like "forget about..." or "stop remembering...".

Activate when the user wants to install, deploy, test, or materialize an APM package into runtime directories such as .agents/, .github/, .claude/, .cursor/, .gemini/, .codex/, .opencode/, or .windsurf/. Use after creating or converting an APM package.

Recupere e utilize de forma unificada o histórico de conversas do Claude Code, Codex e AntiGravity. Permite encontrar o conteúdo original por data, palavras-chave, ID da sessão, Conversation Reference ou Conversation Prompt, e também pode extrair, resumir ou organizar notas de conversas específicas ou de um dia, mediante solicitação explícita do usuário.

Enforce Vertical Slice Architecture (VSA) when building applications in any language (Go, .NET/C#, Java, Kotlin, TypeScript, Python, etc.) and any type (web API, mobile backend, CLI, event-driven). Organize code by feature/use-case instead of technical layers. Each feature is a self-contained vertical slice with a single entry point that receives the router/framework handle and its dependencies. U

Use when you need to automate, test, scrape, or debug any web page. State your goal — I'll ask questions, plan, execute autonomously, and report results.

Git-native ADRs as shared, enforceable context for AI coding agents and humans.

Use this skill at the START of every coding task — new builds, bug fixes, and change requests. Classifies the work item, validates it against project scope, produces a high-level estimate, proposes a technology stack, and checks stack compatibility. Writes a plan artifact to .claude/sdlc/plans/ that every downstream phase and hook depends on. Must run before any Edit, Write, or code-generation too

Use this skill alongside the build skill to resist over-engineering. Enforces YAGNI (no speculative features), KISS (the simplest thing that could possibly work), and DRY-when-it-actually-repeats (not DRY-in-advance). Prefer standard library over new dependencies. Prefer editing existing code over creating new files. Prefer adding one function over adding one class. Prefer flat over nested. Trigge

Use when user describes a new idea, project, or feature they haven't fully thought through, when an idea needs to be pressure-tested before writing a spec, when assumptions about users, business model, or distribution are unstated, or when the user wants to surface what they don't know before committing engineering effort.

Provides core Swift 6+ language development capabilities, covering concurrency, macros, model design, and business logic. Use this skill when writing ViewModel, Service, or Repository layer code, defining data models, implementing algorithms, writing unit tests, or fixing concurrency warnings and data races.