Total 50,402 skills, AI & Machine Learning has 8470 skills
Showing 12 of 8470 skills
Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test.
Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.
Create and configure AI agents, upload files for RAG, manage MCP servers, and handle agent memories using the Cargo CLI. Use when the user wants to create or update agents, upload knowledge base files, connect MCP tool servers, or manage agent memories. For sending messages to agents, use the cargo-orchestration skill instead.
Search agentmemory for past observations, sessions, and learnings about a topic. Use when the user says "recall", "remember", "what did we do", or needs context from past sessions.
Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).
Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile operator/kernel in TileGym, or when asking how to register a new cuTile op.
Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.
Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM fixes.
Google Model Armor: Sanitize a model response through a Model Armor template.
Execute workflow agents iteratively for refinement and progressive improvement until quality criteria are met. Use when tasks require repetitive refinement, multi-iteration improvements, progressive optimization, or feedback loops until convergence.
Set up and optimize context management for any project. Use this skill when the user says "set up context management", "optimize my CLAUDE.md", "context setup", "configure compact instructions", "set up rules", or when starting a new project and wanting best practices for long sessions, memory, compaction, and subagent delegation. Also trigger when the user mentions problems with context loss, compaction losing info, or sessions getting slow.