Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

Create interactive, production-ready UI mockups and prototypes using NuxtJS 4 (Vue) or Next.js (React), TypeScript, and TailwindCSS v4. Use when building web mockups, prototypes, landing pages,...

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources. Use when the user needs thorough investigation, market...

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange...

Analyzes legacy JCL (Job Control Language) scripts to assist with migration to modern workflow orchestration and batch processing systems. Extracts job flows, step sequences, data dependencies,...

Jeffrey Emanuel's comprehensive markdown planning methodology for software projects. The 85%+ time-on-planning approach that makes agentic coding work at scale. Includes exact prompts used.

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,...

Conducts comprehensive frontend design reviews covering UI/UX design quality, design system validation, accessibility compliance, responsive design patterns, component library architecture, and...

SSH remote access patterns and utilities. Connect to servers, manage keys, tunnels, and transfers.

Creates comprehensive frontend UI/UX designs including user interfaces, design systems, component libraries, responsive layouts, and accessibility implementations. Produces wireframes, mockups,...

Simplify and refine recently modified code for clarity and consistency. Use after writing code to improve readability without changing functionality.

深度调研的多Agent编排工作流：把一个调研目标拆成可并行子目标，用 Claude Code 非交互模式（`claude -p`）运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终交付"成品报告文件路径 +...

Conducts comprehensive requirements review including completeness validation, clarity assessment, consistency checking, testability evaluation, and standards compliance. Produces detailed review...

Sentry error monitoring and performance tracing patterns for Next.js applications.

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with...

The philosophy and practical benefits of agent fungibility in multi-agent software development. Why homogeneous, interchangeable agents outperform specialized role-based systems at scale.

Expert frontend development guidance covering React, Vue, Angular, TypeScript, state management, component architecture, performance optimization, accessibility, testing, and modern web APIs....

Provides comprehensive Oracle Cloud Infrastructure (OCI) guidance including compute instances, networking (VCN, load balancers, VPN), storage (block, object, file), database services (Autonomous...

Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes',...