Desenvolvimento

Expression-level code cleanup — guard clauses, naming, magic values, conditional simplification, duplication. Language-agnostic. Out of scope: architecture, module decomposition. Use when user asks to clean code, simplify expressions, flatten nesting, or invokes /logic-cleaner.

🏗️ Universal 8-phase methodology for planning and building enterprise-grade, mission-critical software with AI coding agents. Supports Cursor AI, Claude Code, Kimi Code, Windsurf & Google Antigravity. Includes ADR validator, microtask linter & CI/CD templates. ≥99% test coverage. MIT.

Context handoff for fresh sessions. Saves unsaved session knowledge to notebook, then produces a short orientation block to paste into a new chat. Use when user says '/memento', 'hand off context', 'prepare for fresh chat', 'save and brief', or before clearing context. NOT for: recovering context (use /notebook recover) or saving a single note.

Uma skill de foco baseada em sessões que atua como um parceiro de estudo silencioso. Ela executa blocos de foco estruturados com definição de metas, configuração de ambiente, check-ins de pausas e um log de sessão em markdown, acumulando valor através de relatórios semanais/mensais.

This skill should be used when the user reports a bug, describes unexpected behavior, says something is "broken", "not working", "failing", mentions an "error", "issue", or "problem" in code, or asks to "fix" something. Enforces test-driven bug fixing workflow.

Testing patterns for React Native with Jest and React Native Testing Library. Use when writing tests, mocking Expo modules, testing Zustand stores, or debugging test failures.

Create or update CLAUDE.md files following best practices for optimal AI agent onboarding

Audits code against CI/CD style rules, quality guidelines, and best practices, then rewrites code to meet standards without breaking functionality. Use this skill after functionality validation to ensure code is not just correct but also maintainable, readable, and production-ready. The skill applies linting rules, enforces naming conventions, improves code organization, and refactors for clarity

Side-route skill and single entry point for bug conversations. Use when the user is reporting observed failures and wants durable GitHub issues filed in project language. Delegates per-issue to /triage-issue for bugs that need root-cause diagnosis, then returns to the loop. Not for already-scoped implementation work (use /execute).

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Run ESLint and TypeScript type checking on the frontend codebase. Use when user mentions "lint", "type check", "check code", "eslint", "tsc", or before committing changes.

Adversarial pressure-test of a decision, plan, or piece of work. Articulates the case FOR the current approach, then spawns a subagent to steel-man the best alternative, returns a synthesis with mandatory verdict. Invoke ONLY via /adversary — do NOT trigger on 'what do you think' or 'any concerns'.