Trusted skills for AI agents from official vendors and established maintainers. Every skill is attributed to its author, scanned, and comes with install steps for your AI tool.
300 skills
NVIDIAOfficial
A token-efficient execution kit that compiles agentic workflows into stateless stage cards for repeated, low-cost execution.
Builder.ioOfficial
A mandatory protocol for grounding AI responses in authoritative, up-to-date documentation rather than model memory.
Builder.ioOfficial
A framework for orchestrating complex tasks by delegating sub-tasks to cost-effective models while retaining high-level control.
Builder.ioOfficial
A structured workflow for comparing, merging, and arbitrating competing execution plans from multiple AI agents.
Builder.ioOfficial
An alias skill for the efficient-orchestrator agent tool.
Builder.ioOfficial
Enables autonomous agent operation by converting ambiguity into stated assumptions and minimizing routine clarification stops.
Builder.ioOfficial
A workflow for managing long-running agent tasks by monitoring usage limits and scheduling pauses to stay within budget.
Builder.ioOfficial
A standardized convention for providing clear, color-coded status updates at the end of AI agent responses.
Builder.ioOfficial
Transform text-based plans into interactive, visual artifacts with wireframes, diagrams, and structured documentation.
Builder.ioOfficial
An alias skill for the efficient-orchestrator agent tool.
Builder.ioOfficial
Transforms existing workflows, skills, or project contexts into functional, Agent-Native web applications with integrated AI controls.
SentryOfficial
A comprehensive meta-skill for creating, maintaining, and iteratively improving agent skills using a structured, specification-driven workflow.
NVIDIAOfficial
Plan and execute Nemotron model customization pipelines using repo-native steps.
NVIDIAOfficial
A navigation assistant for the PhysicsNeMo repository, helping users identify models, datapipes, and examples for SciML and AI4Science tasks.
NVIDIAOfficial
Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software, SDKs, GPUs, Jetson/JetPack/L4T/BSP/SDK Manager/driver/flashing/setup, CUDA, NIM, NeMo, Omniverse/OpenUSD/SimReady, Isaac, RAPIDS/cuDF, cuPyNumeric, cuOpt, Dynamo, Holoscan, TensorRT, DeepStream, VSS, TAO, NGC/NVCF. Do not use for generic non-NVIDIA route, optimize, deploy, AI, video, data, or infrastructure tasks.
NVIDIAOfficial
Provides instructions for AI agents to access and utilize canonical NemoClaw documentation and MCP server resources.
NVIDIAOfficial
Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or discussing skill capabilities.
NVIDIAOfficial
Generates and maintains a durable ethos.md file to document an AI agent's purpose, constraints, and success criteria.
NVIDIAOfficial
Convert NVIDIA TAO DAFT datasets between supported formats using the tao-daft CLI.
NVIDIAOfficial
Captures an AI agent's intended behavior into a durable ethos.md contract through codebase analysis and a mandatory intent interview.
NVIDIAOfficial
A shared library of internal NVFLARE conversion policies, templates, and guidance for agent-based federated learning workflows.
NVIDIAOfficial
A central router for managing NVIDIA Neural Reconstruction (NuRec) workflows and coordinating between specialized sibling skills.
NVIDIAOfficial
Orchestrates the creation and maintenance of an agent's ETHOS.md intent snapshot.
NVIDIAOfficial
A structured workflow for maintaining durable, human-readable session state to enable seamless agent continuity across disconnects and long-running tasks.