Loading...
Loading...
Found 805 Skills
Use whenever the user mentions LLM prompt/prefix cache misses, cached_tokens=0, cache_read_input_tokens/cache_creation_input_tokens, prompt_cache_key, cache_control/cachePoint placement, stable prefixes, tool/schema stability, TTFT/prefill latency, OpenAI/Claude/Bedrock/OpenRouter routing, vLLM/SGLang KV reuse, or LLM cost/speed regressions on repeated long prompts. Use when reviewing LLM request shape changes: prompt text, message order, request builders, tools, schemas, response_format, provider API surface, model/router settings, agent loop structure, context compaction, or inference deployment. Use for speeding up agents only when prompt-cache stability, TTFT, or cache cost is central. Do not use for generic prompt writing, generic RAG design, token counting, or non-LLM performance.
Opinionated React and TypeScript conventions for JSX, hooks, routing, shared state, and query wiring. Use for style cleanups, refactors, review feedback, or code generation.
API Gateway patterns (Kong, Traefik, AWS API Gateway) — rate limiting, auth, routing, versioning. Use when implementing API gateway, reverse proxy, or API management.
Implement internationalization (i18n) with Paraglide JS — a compiler-based i18n library that compiles translation files into tree-shakable JavaScript functions. Use when working with Paraglide JS, @inlang/paraglide-js, or any i18n task involving compiled message functions, locale strategies, i18n routing, or multilingual rendering. Covers setup, message compilation, locale detection strategies, URL-based i18n routing, SSR/SSG middleware, variants (pluralization/gendering), formatting, markup, and integration with any framework (React, Vue, Svelte, Solid, Next.js, SvelteKit, Astro, etc.).
Complete guide for Axum web framework including routing, extractors, middleware, state management, error handling, and production deployment
Async communication patterns using message brokers and task queues. Use when building event-driven systems, background job processing, or service decoupling. Covers Kafka (event streaming), RabbitMQ (complex routing), NATS (cloud-native), Redis Streams, Celery (Python), BullMQ (TypeScript), Temporal (workflows), and event sourcing patterns.
TanStack Start full-stack React framework. Use for: server functions with createServerFn, TanStack Router file-based routing, TanStack Query SSR integration, Cloudflare Workers deployment.
Svelte and SvelteKit expert including components, stores, and routing
Load PROACTIVELY when task involves application state, data fetching, or form handling. Use when user says "manage state", "add data fetching", "set up Zustand", "handle form validation", or "add React Query". Covers server state (TanStack Query with caching, optimistic updates), client state (Zustand stores), form state (React Hook Form with Zod validation), URL state (search params, routing), and choosing between state solutions.
Configure Prometheus Alertmanager with routing trees, receivers (Slack, PagerDuty, email), inhibition rules, silences, and notification templates for actionable incident alerting. Use when implementing proactive monitoring with automated incident detection, routing alerts to the appropriate team by severity, reducing alert fatigue through grouping and deduplication, integrating with on-call systems like PagerDuty, or migrating from legacy alerting to Prometheus-based alerting.
Linux networking expert for iptables, nftables, routing, DNS, and network troubleshooting
The ultimate master control guide for Lazycat MicroServer application development. It is triggered when users raise any requirements related to Lazycat MicroServer application development, lpk packaging, routing configuration, deployment parameters, OIDC authentication system, or SDK calls.