Loading...
Loading...
Found 10,570 Skills
Show that code works with evidence instead of guesswork. Define contracts and invariants, add observability, run deterministic checks, and save artifacts that show what passed and what failed.
Use when examining a confirmed code, pull request, module, application, endpoint, dependency, or configuration scope for vulnerabilities, unsafe behavior, or exploitability.
Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).
Pull production observability context from the Superlog MCP to ground debugging, incident response, and 'how is this behaving in prod right now?' questions. Triggers whenever the user is investigating a bug, regression, or incident; asking about real traffic, error rates, latency, or throughput; validating a deploy; or wants the recent history of a service.
Descobrir e refinar linguagem ubíqua de domínio, invariantes, eventos, aggregates e bounded contexts a partir de cenários concretos, evitando anemic domain model. Use quando termos, regras ou ownership de dados estiverem ambíguos, dois times usarem a mesma palavra com sentido diferente, ou uma decisão de modelo for necessária; não criar documentação paralela à fonte autorizada; não use para decisão de infraestrutura ou deployment, use `$specsfy-specialist-software-architecture` para isso.
Cartographic principles for MapLibre GL JS — label and symbol legibility on imagery vs. vector basemaps, figure-ground for point icons, styling vector roads over aerial imagery, visual hierarchy, typography (glyphs/font stacks), sprites and route shields, layer ordering for data injection, and accessibility. Use when styling a map, choosing text or symbol colors, making markers or roads readable on satellite/aerial imagery, setting up fonts or icons, debugging shields, or ordering layers correctly.
Post-task merge readiness gate with a state-backed explanation report and human explainability quiz
Instalar, compor e adaptar shadcn/ui com registry, Base UI, Radix, React Aria, theming, formulários, tabelas, gráficos, sidebars e componentes acessíveis. Use quando houver components.json, componentes shadcn já incorporados ou pedido explícito por shadcn; trate sempre o código copiado como código do projeto, nunca como dependência opaca; não use para o sistema de tokens/utilitários em si — combine com a skill Tailwind CSS — nem para uma galeria de componentes alternativa, coberta por react-ui-components.
Monitors and troubleshoots GKE TPU workloads, nodes, and node pools using GKE system metrics and PromQL. Use when monitoring TensorCore duty cycle, TPU memory, node readiness, multi-host TPU node pool availability, host maintenance or preemption interruptions, and calculating MTTR or MTBI metrics for GKE TPUs. Don't use for general non-TPU GKE workload monitoring or non-metric TPU debugging.
Refactor Spring Boot and Java code to improve maintainability, readability, and adherence to enterprise best practices. This skill transforms messy Spring Boot applications into clean, well-structured solutions following SOLID principles and Spring Boot 3.x conventions. It addresses fat controllers, improper transaction boundaries, field injection anti-patterns, and scattered configuration. Leverages Java 21+ features including record patterns, pattern matching for switch, virtual threads, and sequenced collections.
Debug SwiftUI application issues systematically. This skill helps diagnose and resolve SwiftUI-specific problems including view update failures, state management issues with @State/@Binding/@ObservedObject, NavigationStack problems, memory leaks from retain cycles, preview crashes, Combine publisher issues, and animation glitches. Provides Xcode debugger techniques, Instruments profiling, and LLDB commands for iOS/macOS development.
Refactor React Native and TypeScript code to improve maintainability, readability, and performance for cross-platform mobile applications. This skill transforms complex mobile code into clean, well-structured solutions following React Native New Architecture patterns including Fabric, TurboModules, and JSI. It addresses FlatList performance issues, prop drilling, platform-specific code organization, and inline styles. Leverages Expo SDK 52+ features, React Navigation v7, and Reanimated for smooth 60fps animations.