全部能力

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory),…

当用户希望将单一内容转换为多种格式，或在不同以文本为主和以视觉为主的平台（如 LinkedIn、Twitter/X 等）上适配内容时（……

React 19/19.2 modern patterns for concurrent rendering, Server Components, actions, ref-as-prop, document metadata, resource hints, hooks, and memoization —…

Best practices and guidelines for Parcel, the zero-configuration web application bundler

Expert HR business partnership covering talent strategy, organizational development, employee relations, and people analytics. Use when building workforce plans, designing performance review cycles, resolving employee relations cases, running calibration sessions, structuring compensation philosophy, or advising leadership on organizational change.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model…

Language models exhibit predictable degradation patterns as context length increases. Understanding these patterns is essential for diagnosing failures and…

Query resource usage metrics for Railway services. Use when user asks about resource usage, CPU, memory, network, disk, or service performance like "how much…

Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with…

Update context-mode from GitHub and fix hooks/settings. Pulls latest, builds, installs, updates npm global, configures hooks. Trigger: /context-mode:ctx-upgrade

TanStack Query v5 performance optimization for data fetching, caching, mutations, and query patterns. This skill should be used when using useQuery,…

Documents TypeScript code with JSDoc comments, generates API documentation, and creates type-safe documentation. Use when users request "JSDoc", "code…

Angular 20+ 性能优化指南，涵盖 Signals、httpResource、signal inputs/outputs、@defer 以及原生控制流（@if、@for）。适用于…

Generate optimized prompts for Gemini 2.5 Flash Image (Nano Banana). Use for image generation, crafting photo prompts, art styles, or multi-turn editing…

You are an error tracking and observability expert specializing in implementing comprehensive error monitoring solutions. Set up error tracking systems,…

When the user wants to find patterns in what content works and what doesn't. Also use when the user mentions 'what's working,' 'content patterns,' 'best…

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need…

When the user wants platform-specific tactical guidance for LinkedIn, Twitter/X, Threads, or Bluesky. Also use when the user mentions 'LinkedIn strategy,'…

React Router performance and architecture patterns. Use when writing loaders, actions, forms, routes, or working with React Router data fetching. Triggers on…

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference…