Provides comprehensive Alibaba Cloud (Aliyun) guidance including ECS, ApsaraDB, OSS, SLB, VPC, RAM, ACK (Kubernetes), Function Compute, API Gateway, CDN, and monitoring services. Covers...
Comprehensive React and Vite SPA performance, architecture, and deployment guidelines. Use this skill when building, reviewing, or refactoring React applications built with Vite (SPA). Covers...
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic...
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with...
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track...
Guides comprehensive requirements gathering and analysis including stakeholder interviews, user story creation, use case documentation, acceptance criteria, requirements prioritization, and...
Guides infrastructure and platform migration including cloud-to-cloud migration (AWS to GCP, Azure to AWS), Kubernetes cluster migration, CI/CD platform changes, monitoring stack migration,...
Sentry error monitoring and performance tracing patterns for Next.js applications.
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization...
Run accessibility and visual design review on components. Use when reviewing UI code for WCAG compliance and design issues.
Guides operating system and hardware platform migrations including Linux distribution changes, Windows to Linux migration, mainframe to x86 modernization, data center migrations (physical to...
Find opportunities to improve web application code using TanStack libraries (Query, Table, Form, Router, etc.). Avoid man-with-hammer syndrome by applying TanStack after vanilla implementation works.
Conducts comprehensive frontend design reviews covering UI/UX design quality, design system validation, accessibility compliance, responsive design patterns, component library architecture, and...
Provides comprehensive KeyCloak administration guidance including realm management, user/group administration, client configuration, authentication flows, identity brokering, authorization...
Analyzes and assists with Fujitsu mainframe systems including FACOM, PRIMERGY, BS2000/OSD, OSIV/MSP, OSIV/XSP, NetCOBOL, PowerCOBOL, and Fujitsu JCL. Extracts business logic from Fujitsu COBOL...
SSH remote access patterns and utilities. Connect to servers, manage keys, tunnels, and transfers.
Use Bun instead of Node.js, npm, pnpm, or vite. Provides command mappings, Bun-specific APIs, and development patterns.
Interact with a web browser. Can start a browser, connect to it, evaluate JavaScript, make screenshots, read console logs and let the user select DOM elements. Use when interacting with unknown...
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or...
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF,...