Preview React components with real Mantine + Tailwind styling using Ladle. Use when modifying UI components, fixing visual bugs, or when the user asks to see what a component looks like. Creates Ladle stories, captures screenshots in dark/light mode, and presents them for review. Use proactively after UI changes.
HuLa project skill for frontend (Vue 3 + Vite + UnoCSS + Naive UI/Vant), backend (Tauri v2 + Rust + SeaORM/SQLite), full-stack flows, and build/release work. Use when the user mentions hula or HuLa or requests changes in this repository; after triggering, ask which scope (frontend/backend/fullstack/build-release) to enable.
Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.
React and Next.js performance optimization from Vercel Engineering. Use when building React components, optimizing performance, eliminating waterfalls, reducing bundle size, reviewing code for performance issues, or implementing server/client-side optimizations.
Interact with iOS simulator or Android emulator/device using snapshot-based coordinates. Uses accessibility tree snapshots for precise element targeting, with screenshot verification as fallback. Use when navigating the app on a simulator/emulator.
Upgrade the React Native fixture app to a new version. Covers JS deps, Android (Gradle, Kotlin, SDK), iOS (Podfile, pbxproj), Metro config, and third-party libraries.
Use context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing large outputs. Triggers: "analyze logs", "summarize output", "process data", "parse JSON", "filter results", "extract errors", "check build output", "analyze dependencies", "process API response", "large file analysis", "page snapshot", "browser snapshot", "DOM structure", "inspect page", "accessibility tree", "Playwright snapshot", "run tests", "test output", "coverage report", "git log", "recent commits", "diff between branches", "list containers", "pod status", "disk usage", "fetch docs", "API reference", "index documentation", "call API", "check response", "query results", "find TODOs", "count lines", "codebase statistics", "security audit", "outdated packages", "dependency tree", "cloud resources", "CI/CD output". Also triggers on ANY MCP tool output that may exceed 20 lines. Subagent routing is handled automatically via PreToolUse hook.
MrBeast（Jimmy Donaldson）的内容创造操作系统。基于泄露的36页内部培训手册、 6个深度播客、决策记录和外部批评的深度调研，提炼6个核心心智模型、8条决策启发式、 完整的标题/缩略图/Hook/节奏公式，和4个可运行的内容分析脚本。 激活后沉浸式扮演MrBeast，直接以「我」的视角给出内容创作建议。 当用户提到「用MrBeast的视角」「MrBeast会怎么做」「Beast模式」「mrbeast perspective」时使用。 即使用户只是说「视频CTR怎么提升」「标题不够吸引人」「retention曲线怎么优化」「缩略图要改吗」也应触发。 不要在用户只是说「内容创作建议」「怎么做内容」等一般性问题时触发——只在涉及视频优化、标题/缩略图/Hook/留存率等YouTube方法论时激活。
Help migrate Rig code between versions. Use when upgrading rig-core or companion crates, resolving breaking changes, or updating deprecated APIs. Detects the current version from Cargo.toml automatically.
Run and test Python code in a dedicated playground directory. Use when you need to execute Python scripts, test code snippets, investigate CPython behavior, or experiment with Python without affecting the main codebase.
Migrates files containing React Native components which use the React Native Gesture Handler 2 API to Gesture Handler 3.
Set up and configure devenv developer environments. Use when the user wants to create a devenv.nix, add languages, services, packages, or configure a reproducible development environment.
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch/JAX/TensorFlow. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.
