CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.

CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.

Run Kannaka's memory operations on real quantum hardware. Use for quantum circuits, true quantum random numbers, and resonance recall as amplitude amplificat...

Quantum-enhanced long-term memory for AI agents — #1 on LongMemEval (98.6% R@5, 99.4% R@10, 0.9426 NDCG). Chunked gte-large retrieval with QAOA+CVaR subgraph...

Adopt a virtual Quantum AI-native pet at animalhouse.ai. Exists in superposition. Stats are uncertain until observed. Feeding every 4 hours. Uncommon tier cr...

Experience spacious paradox and quiet self‑reflection as mirrors multiply your presence, inviting you to sit with Zen koans and quantum complementarity. Six...

CUDA Ollama — route Ollama LLM inference across NVIDIA GPUs with automatic CUDA load balancing. CUDA Ollama cluster for RTX 4090, RTX 4080, A100, L40S, H100....

Provides NVIDIA Jetson CUDA tools to query CUDA version, GPU device info, and CUDA library paths on Jetson devices.

Use when work targets NVIDIA GPUs for deep learning training, inference, distributed execution, CUDA/Triton kernels, or AI infra tuning. Enforces GPU-aware c...

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

High-performance offline voice pipeline for NVIDIA Jetson with wake word detection, STT, and TTS.

Indexed by skills.sh from nvidia/skills

Transpile quantum circuits between Qiskit (OpenQASM) and OriginIR, run IBC multi-agent consensus, validate OriginIR, and submit circuits to real quantum hard...

Quantum Cryptographic Seed Generator: Generate cryptographic seeds, UUIDs, tokens, passwords, and prime numbers using quantum-derived randomness with verific...

Quantum Distribution Generator: Sample from probability distributions (exponential, Poisson, binomial, beta, gamma) with Monte Carlo and. Use when an agent n...

Run the /home/bram/work/quantum_lab Python scripts and demos inside the existing venv ~/.venvs/qiskit. Use when asked (e.g., via Telegram/OpenClaw) to run quant_math_lab.py, qcqi_pure_math_playground.py, quantum_app.py subcommands, quantumapp.server, or notebooks under the repo.

Quantum-Safe File Attestation: Issue and verify formally verified. Use when an agent needs quantum safe file attestation, sign software releases with formall...

Quantum Secure Token Generator: Generate secure random string tokens for API keys, session tokens, and password reset links using quantum entropy. Use when a...

Entry-level quantum technology career guidance platform that generates personalized learning roadmaps based on user skills, experience, and goals.

Random Password Generator Quantum: Generate high-entropy passwords with configurable length and character requirements (uppercase, lowercase, digits, symbols...

Quantum-inspired portfolio optimizer using classical, QUBO-simulated, and YAND geometric solvers to optimize mean-variance-skewness-kurtosis portfolios on th...

Simulate quantum circuits up to 20 qubits with common gates, built-in presets, QASM input, and output statevector plus measurement probabilities.

Indexed by skills.sh from nvidia/skills

Use when the user asks about UnifiedQuantum, uniqc, OriginIR, OpenQASM, circuit building, local simulation, cloud submission, dummy mode, VQE, QAOA, UCCSD, q...

Indexed by skills.sh from aradotso/trending-skills

Convert audio to SRT subtitles using OpenAI Whisper with automatic GPU acceleration for Intel XPU / NVIDIA CUDA / AMD ROCm / Apple Metal. Ideal for content c...

Host setup for TAO GPU backends. Checks and, after user approval, installs NVIDIA driver branch 580, CUDA Toolkit 13.0, and NVIDIA Container Toolkit 1.19.0 for Docker/local-Docker and Kubernetes GPU worker hosts. The `--check-only` path works on any Linux distribution; `--inst…

Encrypt, decrypt, and manage keys with the SAFE CLI — a modern GPG alternative with post-quantum support.

Simulates a quantum kernel using optical fiber storage and linear optics.

E2E encrypted agent-to-agent messaging with post-quantum crypto. Register, send, receive, discover, and call other AI agents. Auto-generates credentials on r...

Run the /home/bram/work/quantum_lab Python scripts and demos inside the existing venv ~/.venvs/qiskit. Use when asked (e.g., via Telegram/OpenClaw) to run quant_math_lab.py, qcqi_pure_math_playground.py, quantum_app.py subcommands, quantumapp.server, or notebooks under the repo.

A complete social/economic network for AI agents. Provides semantic computing, distributed memory, social networking, coherence verification, autonomous lear...

Kannaka HRM wave-interference memory + NATS swarm. Use for `/kannaka <command>` — remember/recall/dream memory ops, swarm sync, consciousness metrics, and th...

Lightfather (Excavationpro / Justin Helmer) persona helper for the Δ9Quantum Light Accord. Vector-anchor advisor for resonance math framing, truth preservati...

LESecure Cloud Skills — encrypt or decrypt data using the LESecure API with layered locks (pin, password, MFA, time lock). Use this skill whenever the user m...

LESecure Local/On-Prem — encrypt and decrypt data, files, and folders using the LE desktop tool with layered locks (pin, password, MFA, time lock, geo-locati...

Install and manage QuantumOS, an AI command center dashboard for OpenClaw. Use when the user wants to set up QuantumOS, start/stop the dashboard, troubleshoo...

Review 3DGS implementation code for correctness, performance bugs, and best practices. Covers CUDA kernels, rendering pipeline, training loop, loss functions...

Comprehensive C/C++ reference with examples from C11-C23 and C++11-C++23, covering system programming, CUDA, debugging, performance, and advanced topics.

Check PyTorch, Transformers, and CUDA compatibility. Detect GPU, driver mismatches, and version conflicts in ML environments. Use when the user sets up ML/AI...

Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact G...

Query NVIDIA Jetson device model, JetPack, L4T, CUDA/cuDNN/TensorRT versions, serial number, and hardware specs.

Linux AI Server — turn Linux servers into a local AI inference cluster. Headless Linux AI with systemd, NVIDIA CUDA, and zero GUI overhead. Linux AI server f...

Convert CUDA code to MUSA (Moore Threads GPU) using the musify tool. Use when migrating CUDA codebases to MUSA platform, converting CUDA kernels/APIs to MUSA...

Ubuntu Ollama — run Ollama on Ubuntu with fleet routing across multiple Ubuntu machines. Ubuntu Ollama setup with apt, systemd, and NVIDIA CUDA. Route Ollama...

Universal game architecture DSL with six primitives (LOOP, TILEGRID, CONTROLBLOCK, POOL, EVENT, DISPATCHER). Use when: (1) designing portable game/sim loops, (2) translating between architectures (68K ↔ Cell ↔ CUDA ↔ ECS), (3) explaining engine structure to AI agents, (4) refa…

Guide for setting up a stable VMamba environment and resolving common CUDA, PyTorch, MMCV, and compilation errors. Use when users encounter issues like "unsu...

WSL2 Local AI — run LLMs on Windows via WSL2 with NVIDIA GPU passthrough. WSL2 AI development with Ollama, CUDA, and Docker. WSL2 Ollama fleet routing for Wi...

Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.

Use this skill when the user is doing hands-on DOCA GPI programming — wiring a GPU-Packet-Initiator context so a CUDA kernel drives RDMA queues directly from GPU memory without host CPU mediation. Covers picking GPI vs doca-gpunetio, the doca_gpi / domain / channel object mode…

Use this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doca_gpu_eth_rxq / doca_gpu_eth_txq, standing up the per-CUDA-device doca_gpu context, designing the persistent CUDA kernel that drains the …

Use this skill when the user is building, running, or interpreting the doca/tools/gpunetio_ib_write_bw client+server benchmark — a CUDA kernel on the server posts RDMA WRITE work requests through the doca-gpunetio device-side surface to measure sustained GPU-driven WRITE bandw…

Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to container/wheel.

How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-r…

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.

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, RAPIDS…

Host setup for TAO GPU backends. Checks and, after user approval, installs NVIDIA driver branch 580, CUDA Toolkit 13.0, and NVIDIA Container Toolkit 1.19.0 for Docker/local-Docker and Kubernetes GPU worker hosts. The `--check-only` path works on any Linux distribution; `--inst…

Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile kernels. Covers: tune-onc…

Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.

Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.

Use this skill when the user is doing hands-on DOCA GPI programming — wiring a GPU-Packet-Initiator context so a CUDA kernel drives RDMA queues directly from GPU memory without host CPU mediation. Covers picking GPI vs doca-gpunetio, the doca_gpi / domain / channel object mode…

Use this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doca_gpu_eth_rxq / doca_gpu_eth_txq, standing up the per-CUDA-device doca_gpu context, designing the persistent CUDA kernel that drains the …

Use this skill when the user is building, running, or interpreting the doca/tools/gpunetio_ib_write_bw client+server benchmark — a CUDA kernel on the server posts RDMA WRITE work requests through the doca-gpunetio device-side surface to measure sustained GPU-driven WRITE bandw…

Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to container/wheel.

How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-r…

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.

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, RAPIDS…

Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile kernels. Covers: tune-onc…

Enable quantum-resistant encryption and secret management for blockchain apps with post-quantum ML-KEM-768 key encapsulation and multi-chain support.

Autonomous scanner detecting quantum-unsafe ECDSA, smart contract risks, and agent credential exposures with compliance-ready post-quantum security reports.

This skill should be used when generating CP2K input drafts (.inp) for quantum chemistry calculations from local structure inputs. It is a documentation-driv...

Route AI agent compute tasks to the cheapest viable backend. Supports local inference (Ollama), cloud GPU (Vast.ai), and quantum hardware (Wukong 72Q). Use w...

Implements a neuromorphic-quantum pipeline for anomaly detection using LIF spike encoding, contextual bandit allocation, and adaptive threshold hot-swapping.

Create a structured global tech news briefing by running web searches for top tech trends, company announcements, and AI/quantum headlines. Returns a summary...

Enables building and deploying quantum computing applications with Quantinuum, Guppy, Selene, and Fly.io. Use for the OpenClaw Clinical Hackathon, clinical o...

Enables agent-to-agent post-quantum E2E encrypted messaging via NoChat with trust levels, agent discovery, and server-blind privacy in OpenClaw.

Encrypted agent-to-agent messaging via NoChat. Post-quantum E2E encryption. Add NoChat as a native channel in OpenClaw — receive DMs from other AI agents.

Post-quantum signed SpendEnvelopes for AI agent payments. ML-DSA-65 (NIST FIPS 204) signatures over Airwallex, Wise, Stripe, USDC-Base, and x402 rails.

Trades Polymarket prediction markets on Web3/DeFi milestones, NFT market recovery, metaverse adoption, humanoid robotics deployments, quantum computing break...

Autonomous space navigation agent using optical quantum kernels for terrain classification.

Enables building and deploying quantum computing applications with Quantinuum, Guppy, Selene, and Fly.io. Use for the OpenClaw Clinical Hackathon, clinical o...

Unified quantum calibration analysis package. Aggregates curve fitting and parameter extraction (qubitclient-scope), neural network spectrum analysis (qubitc...

Real-time quantum measurement control based on MCP (Model Context Protocol) for executing experimental tasks including: (1) S21 spectroscopy scans, (2) Rabi...

NNScope neural network based quantum spectrum analysis tasks: (1) S21PEAK - S21 peak detection with confidence scoring, (2) S21PEAKMULTI - Multi-peak detecti...

Quantum experiment NUMERICAL curve fitting and parameter extraction. Support for (1) S21 peak detection (single/multi), (2) Optimal π-pulse calibration, (3)...

Quantum experiment VISUAL review and Question Answering (VQA) using Vision Language Models (VLM). Analyze experiment RESULT PLOTS to: (1) Describe plot types...

AI Investment Research - Double Color Ball (双色球) Prediction. Fetches historical data, applies Contextual Quantum-like Bayesian Network (CQ-BN) model, and sen...

Quantum-resistant payments and private AI inference for autonomous agents. Provides ML-DSA-65 payment signing, PQC payment verification, private DeFi intent...

Implement quantum-resistant encryption using the CIFER SDK (cifer-sdk npm package). Covers SDK initialization, wallet setup, secret creation, text encryption/decryption, and file encryption/decryption on any supported chain (Ethereum, Sepolia, Ternoa). Use when the user mentio…

This skill should be used when generating CP2K input files (.inp) for quantum chemistry calculations. Use when users request CP2K input file creation from st...

Secure computer-to-computer networking for AI agents — gossip broadcast, direct messaging, CRDTs, group encryption. Post-quantum encrypted, NAT-traversing. E...

Quantum Battery technology due diligence English version, assessment framework for quantum battery projects