Agent Skills Hub

mijia-control

Control and monitor Xiaomi Mijia smart home devices including status switching, device discovery, automation scenes, and environmental statistics.

verify

Self-healing Rust verification loop that automates test execution, clippy linting, and formatting checks.

react-native

React Native best practices for Expo and bare workflow. Supports project structure, navigation, NativeWind styling, platform-specific code, and TypeScript integration.

linkerd-patterns

Implement Linkerd service mesh patterns for security, traffic policy management, and zero-trust networking in Kubernetes environments.

triage-ci-flake

Systematic triage and reproduction workflow for investigating flaky CI test failures in Payload CMS repositories.

voice-apply

Transforms content to match specific voice profiles, tones, or styles using configurable YAML templates for consistent brand and narrative output.

google-ads-scripts

Expert guidance for Google Ads Script development including AdsApp API, campaign management, keyword bidding, automated rules, performance reporting, and spend optimization.

backend-architect

Senior backend architecture expert specializing in Hexagonal Architecture, DDD, SOLID principles, clean code, and refactoring to guide development, reviews, and architectural problem-solving.

reactive-ui-patterns

Reactive UI patterns for remote data fetching, enabling smooth in-place updates, persistent scroll position, and efficient loading state management using the .current property.

chatkit-frontend

Implement production-ready AI chat interfaces using OpenAI ChatKit React components. Features include hook configuration, streaming, theming, conversation history, and custom tool integration for Next.js applications.

ai-llm-patterns

Anthropic Claude integration patterns: streaming, RAG with pgvector, tool use, model selection (Haiku/Sonnet/Opus), prompt caching, and cost management for AI-powered engineering.

code-quality-review

Holistic, multi-dimensional code review skill providing prioritized, actionable feedback on correctness, security, performance, design, and accessibility.