Total 50,402 skills, AI & Machine Learning has 8470 skills
Showing 12 of 8470 skills
Preserve critical session state when compacting context. Use when context window is filling up and you need to summarize/reduce while keeping essential debugging information.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Universal tool gateway via Composio — connect to 1000+ external apps (Gmail, Slack, GitHub, Google Calendar, Notion, etc.) through the Composio Gateway. Use when the user wants to interact with external SaaS services, send emails, manage calendars, access documents, or any third-party app integration.
Use when working on the Evaluator plugin CLI, jobs, SDK-backed specs, or plugin-owned Evaluator skills.
Used for generating synthetic body MRI volumes with NV-Generate-CTMR rflow-mr. Not for paired masks or production training data.
Virtual try-on: clothing, accessories, hairstyles, makeup, glasses, hats, shoes, watches. Use when the user wants to see how an item looks on a person — e.g. "try on this dress", "put these glasses on me", "show me with this hairstyle", "what would I look like in this outfit".
Clone the latest NVIDIA Holoscan Sensor Bridge repo, ask which supported devkit is being used, configure the host per platform, build the correct demo container, run it, and verify HSB connectivity by pinging 192.168.0.2. Use for Holoscan Sensor Bridge setup, build, container launch, and first-connectivity bring-up.
Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.
Use when creating new skills, editing existing skills, or verifying if skills are valid before deployment
Give every AI agent its own computer: a persistent workspace with a filesystem, processes, shells, networking, and agent sessions on a lightweight in-process OS.
Install cuOpt for Python, C, or as a server (pip, conda, Docker) — system requirements, install commands, and verification. Use when the user wants to install or verify cuOpt for any user-facing interface. For building cuOpt from source or contributing to cuOpt, see cuopt-developer.
MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.