nvidia
11 verified skills4,339 total stars
cuopt-model-mapper
Use after optimization intent and basic data interpretation are established, when the goal is to solve quickly by mapping data directly into cuOpt rather than building a replayable intermediate artifact.
development451
cuopt-sandbox
Read FIRST whenever a request involves linear programming (LP), mixed-integer linear programming (MILP), quadratic programming (QP), or vehicle routing (VRP, TSP, PDP) — including small / pedagogical / made-up problems ("invent an LP example", "show me a small MILP", "find optimal X under constraints", "minimize cost", "plan deliveries", "schedule with constraints"). In this sandbox, cuOpt is the default solver and must be used whenever it is available; this skill points at the per-task skills (cuopt-user-rules, cuopt-numerical-optimization-api-python, cuopt-routing-api-python, numerical-optimization-formulation, etc.) and covers sandbox-specific setup (venv at /sandbox/.openclaw-data/cuopt, host.openshell.internal networking, REST 5000 / gRPC 5001).
development451
optimization-intent-router
Use when a user provides data and asks a natural-language business or planning question that may require optimization rather than simple analytics.
data-ai451
optimization-mode-router
Use when a user asks a question that may be answered by solving an optimization problem from uploaded or provided data, and you need to decide whether to proceed directly to cuOpt or preserve a structured reusable model artifact.
testing451
optimization-from-data-orchestrator
Use when a user uploads or provides data and asks a question that may be answered by optimization. This skill sequences optimization-intent-router, optimization-mode-router, tabular-optimization-ingestion, formulation skills, and cuOpt model-building skills.
development451
tabular-optimization-ingestion
Use when a user provides CSV, Excel, JSON-like tables, or similar structured data and asks a question that may become an LP, MILP, QP, or routing problem.
data-ai451
cuopt
Use NVIDIA cuOpt to solve vehicle routing (VRP/CVRPTW) and linear programming (LP/MIP) optimization problems. Use when the user asks to optimize routes, solve a routing problem, minimize cost, plan deliveries, solve an LP, or use cuOpt.
tools436
generic-max-supply
Multi-period supply chain planning model: data files, BOM structure, variable/constraint reference for the max-supply base model.
data-ai434
cuopt-debugging
Troubleshoot cuOpt LP/MILP problems including errors, wrong results, infeasible solutions, performance issues, and status codes. Use when the user says something isn't working, gets unexpected results, or needs help diagnosing issues.
development434
osmo-deploy
How to deploy OSMO to a Kubernetes cluster on Azure (AKS), AWS (EKS), MicroK8s (single-node), or any kubectl-reachable cluster (BYO). Use this skill whenever the user asks to install, deploy, set up, or stand up OSMO; whenever they ask to provision an OSMO cluster; whenever they mention deploy-osmo-minimal.sh, deploy-k8s.sh, or "OSMO helm install"; whenever they ask to wire up workflow storage (MinIO / Azure Blob / S3); or whenever they ask to add a GPU pool to an OSMO cluster, install KAI scheduler, install the NVIDIA GPU Operator, or run the post-install smoke tests. Targets OSMO 6.3 (ConfigMap mode).
testing173
osmo-agent
Operate the OSMO CLI to discover GPU resources, submit and monitor workflows, debug PENDING/FAILED/stuck workflows, interpret OSMO errors, surface OSMO workflow Grafana and Kubernetes dashboard links, and publish workflows as OSMO apps. Trigger when the user asks about OSMO pools, quota, GPUs, workflow status/logs/submission, OSMO errors, OSMO apps, or about the Grafana or Kubernetes dashboard for an OSMO workflow — even if they don't say "OSMO" explicitly. Do NOT use for general kubectl install/configuration, raw Kubernetes setup unrelated to an OSMO workflow, NVIDIA hardware/product questions unrelated to OSMO, or non-OSMO compute platforms.
tools156