Card snapshot

This is a frozen copy of the agent's agent-card.json as we observed it at the timestamp above. We capture a new snapshot every time the card's content hash changes. Useful for: forensic drift analysis, verifying downstream callers see the right version, reproducing routing decisions made historically.

{
  "name": "Nixtla",
  "url": "https://nixtlaverse.nixtla.io/",
  "version": "1.0.0",
  "protocolVersion": "0.3",
  "preferredTransport": "HTTP+JSON",
  "supportedInterfaces": [
    {
      "url": "https://nixtlaverse.nixtla.io/",
      "protocolBinding": "HTTP+JSON",
      "protocolVersion": "0.3"
    }
  ],
  "provider": {
    "url": "https://nixtlaverse.nixtla.io/",
    "organization": "Nixtla"
  },
  "documentationUrl": "https://nixtlaverse.nixtla.io/",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false
  },
  "defaultInputModes": [
    "text/plain"
  ],
  "defaultOutputModes": [
    "text/plain"
  ],
  "skills": [
    {
      "id": "nixtlaverse",
      "name": "Nixtlaverse",
      "description": "Use when building time series forecasting pipelines, comparing statistical vs machine learning vs neural approaches, scaling forecasts across millions of series, reconciling hierarchical forecasts, generating synthetic data for testing, or evaluating model performance. Agents should reach for this skill when working with time series data in long format (unique_id, ds, y), choosing between StatsForecast, MLForecast, NeuralForecast, HierarchicalForecast, or SynForecast based on the forecasting task.",
      "tags": [],
      "url": "https://nixtlaverse.nixtla.io/.well-known/agent-skills/nixtlaverse/skill.md"
    }
  ]
}