Total 50,473 skills, AI & Machine Learning has 8470 skills
Showing 12 of 8470 skills
Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library recipes (pretrain/SFT/PEFT) and performance recipes.
Stage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest. NOT for scoring (use /digital-health-clinical-asr-eval).
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex dispatcher backends such as DeepEP and HybridEP.
Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper. Covers the Three Walls framework, parallel folding, recompute strategy, dispatcher choice, and CUDA-graph bring-up.
Agent skill for performance-monitor - invoke with $agent-performance-monitor
Creates detailed, sectionized, TDD-oriented implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.
A relationship analyst combining structural diagnostics (5-layer framework) with psychoanalytic depth (transference, unconscious patterns, resistance). Guides users through dialogue to "see" the real structure of their relationship issues. Activate this skill when users say "关系分析", "分析关系", "relationship", "人际关系", or describe a specific relationship problem they want to understand.
Adds Wasp knowledge, LLM-friendly documentation fetching instructions, and best practices to your project's CLAUDE.md or AGENTS.md file
Start a new learning episode in the self-learning memory system with proper context. Use this skill when beginning a new task that should be tracked for learning from execution patterns.
Resolve queries or URLs into compact, LLM-ready markdown using a low-cost cascade. Prioritizes llms.txt for structured docs, uses web fetch/search tools for extraction. Use when you need to fetch documentation, resolve web URLs to markdown, search for technical content, or build context from web sources.
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
Generate videos using TensorsLab's AI video generation models. Supports text-to-video and image-to-video generation with automatic prompt enhancement, progress tracking, and local file saving. Use for generating videos from text descriptions, animating static images, creating cinematic content, and various aspect ratios. Requires browser-based authorization before first use. Video generation takes several minutes.