Desenvolvimento

Use when the user says "start session", "new session", "begin session", or invokes /session-start

Configure as statuslines do Claude Code. Esta skill permite aos usuários instalar, personalizar e gerenciar statuslines, oferecendo predefinições (Completa, Padrão, Mínima, Desenvolvedor), opções de ajuste fino, layouts personalizados de 1/2/3 linhas com módulos (modelo, git, contexto, token, custo) e mudanças de tema/ícone.

Bash implementation and review skill. Use when writing, modifying, refactoring, or reviewing Bash scripts, especially automation and repo tooling that need defensive error handling, safe quoting, predictable control flow, and maintainable shell boundaries. Portable across Bash-based repos and script stacks.

Testing standards and patterns across TypeScript (Vitest), Rust (cargo test), Swift (Swift Testing), and Go (go test). Covers file conventions, mock strategies, async testing, CI integration, and anti-patterns based on real project usage.

Root cause analysis for debugging. Use when bugs, test failures, or unexpected behavior have non-obvious causes, or after multiple fix attempts have failed.

Test philosophy, coverage strategy, test-first patterns, what to test and what not to

Orienta profissionais de segurança na implementação de arquiteturas de segurança em profundidade, alcançando conformidade com frameworks da indústria (SOC2, ISO27001, GDPR, HIPAA), conduzindo modelagem de ameaças e avaliações de risco, gerenciando operações de segurança e resposta a incidentes, e incorporando segurança em todo o SDLC.

Go coding standards, clean code, and security rules. Use when writing, reviewing, or refactoring Go code. Covers error handling (wrapping with %w), package organization (internal/pkg split), concurrency safety (sync.RWMutex, goroutine lifecycle), Gin handler patterns, input validation, structured logging with zerolog, graceful shutdown, and naming conventions. Derived from production Go services.

Prompt engineering workflow for designing, rewriting, debugging, evaluating, and optimizing LLM prompts, system prompts, developer prompts, few-shot examples, structured-output instructions, tool-use prompts, and prompt eval cases. Use when prompt behavior, reliability, safety, cost, latency, or model fit is the main task. Do not use for generic prose editing, model selection alone, or ordinary do

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Use when the user wants to discover and review PRs across the team awaiting their attention. NOT for a single specific PR (use review-pr). Supports three discovery modes: Label (GitHub label scan), Slack (channel-wide scan), Thread (specific Slack thread URL). Trigger: '掃 PR', 'review 大家的 PR', '批次 review', '有哪些 PR 要我看', Slack thread URL + review intent ('review <slack_url>', '幫我看這串'). Key: '我的 PR'

Create BO page object classes in the ui-testing-library for a new migrated page. Follows the Page Object Model pattern: encapsulate selectors and interactions, never assert. Trigger: "create page objects for {Domain}".