Loading...
Loading...
Found 87 Skills
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
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 flexible infrastructure backends.
USE FOR image search. Returns images with title, source URL, thumbnail. Supports SafeSearch filter. Up to 200 results.
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 scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
Comprehensive technical research by combining multiple intelligence sources — Grok (X/Twitter developer discussions via Playwright), DeepWiki (AI-powered GitHub repository analysis), and WebSearch. Dispatches parallel subagents for each source and synthesizes findings into a unified report. This skill should be used when evaluating technologies, comparing libraries/frameworks, researching GitHub repos, gauging developer sentiment, or investigating technical architecture decisions. Trigger phrases include "tech research", "research this technology", "技术调研", "调研一下", "compare libraries", "evaluate framework", "investigate repo".
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
Write comprehensive literature reviews for medical imaging AI research. Use when writing survey papers, systematic reviews, or literature analyses on topics like segmentation, detection, classification in CT, MRI, X-ray, ultrasound, or pathology imaging. Triggers on requests for "review paper", "survey", "literature review", "综述", "systematic review", or mentions of writing academic reviews on deep learning for medical imaging.
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 alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, and Socratic guided modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review.
USE FOR RAG/LLM grounding. Returns pre-extracted web content (text, tables, code) optimized for LLMs. GET + POST. Adjust max_tokens/count based on complexity. Supports Goggles, local/POI. For AI answers use answers. Recommended for anyone building AI/agentic applications.
USE FOR news search. Returns news articles with title, URL, description, age, thumbnail. Supports freshness and date range filtering, SafeSearch filter and Goggles for custom ranking.