Loading...
Loading...
Found 346 Skills
Boilerplate templates for Claude Code extensions. Triggers on: create agent, new skill, command template, hook script, extension scaffold.
Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.
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, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to "run" any process. Also handles Perplexity-based research and Google Sheets data tracking.
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.
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 distributed architecture and GPU resource sharing.
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
Query resource usage metrics for Railway services. Use when user asks about resource usage, CPU, memory, network, disk, or service performance like "how much memory is my service using" or "is my service slow".
Check current Railway project status for this directory. Use when user asks "railway status", "is it running", "what's deployed", "deployment status", or about uptime. NOT for variables or configuration queries - use railway-environment skill for those.
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.