{
  "schemaVersion": "1.0",
  "item": {
    "slug": "s2s-forecasting-expert",
    "name": "S2S Forecasting Expert (FuXi, FengWu, AIFS)",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/manmeet3591/s2s-forecasting-expert",
    "canonicalUrl": "https://clawhub.ai/manmeet3591/s2s-forecasting-expert",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/s2s-forecasting-expert",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=s2s-forecasting-expert",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/s2s-forecasting-expert"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/s2s-forecasting-expert",
    "agentPageUrl": "https://openagent3.xyz/skills/s2s-forecasting-expert/agent",
    "manifestUrl": "https://openagent3.xyz/skills/s2s-forecasting-expert/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/s2s-forecasting-expert/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "S2S Model Builder (Subseasonal-to-Seasonal Forecasting)",
        "body": "This skill actively helps you design, implement, and train S2S forecasting models from scratch.\n\nIt generates:\n\nPyTorch model architectures\nTraining loops\nCRPS loss implementations\nData preprocessing pipelines (ERA5-style)\nEvaluation scripts\nMulti-GPU training configurations\nInference pipelines\n\nSupported paradigms include:\n\nFuXi-style transformer architectures\nFengWu-style Earth system transformers\nAIFS-inspired probabilistic models\nEnsemble neural forecasting\nMulti-lead-time forecasting heads"
      },
      {
        "title": "1. Model Architecture Code",
        "body": "3D spatiotemporal transformers\nGlobal grid attention models\nMulti-variable input pipelines (Z500, T2M, winds, SST)\nLead-time conditioned decoders\nEnsemble output heads"
      },
      {
        "title": "2. Training Infrastructure",
        "body": "PyTorch training loops\nDistributed training (FSDP-ready structure)\nMixed precision support\nGradient accumulation\nCheckpoint saving"
      },
      {
        "title": "3. Probabilistic Forecasting",
        "body": "CRPS loss (Gaussian & ensemble forms)\nQuantile regression heads\nSpread-skill diagnostics\nReliability calibration utilities"
      },
      {
        "title": "4. Evaluation Code",
        "body": "CRPS computation\nACC metric implementation\nRMSE across forecast horizons\nSkill vs climatology baseline"
      },
      {
        "title": "5. Deployment-Ready Inference",
        "body": "Batched inference scripts\nMemory-optimized forward passes\nModel export patterns"
      },
      {
        "title": "Example Prompts",
        "body": "“Generate a FuXi-style transformer in PyTorch for 30-day Z500 forecasting.”\n“Build a CRPS loss function for ensemble S2S outputs.”\n“Create a full ERA5 training pipeline scaffold.”\n“Design a multi-lead-time S2S forecasting head.”\n“Implement distributed training for global 1° resolution data.”"
      },
      {
        "title": "External Endpoints",
        "body": "This skill does not call external APIs.\n\nEndpointPurposeData SentNoneN/ANone\n\nAll generated code runs locally within the user’s environment."
      },
      {
        "title": "Security & Privacy",
        "body": "No external API calls\nNo automatic dataset downloads\nNo remote execution\nNo hidden scripts\nAll code is generated transparently\n\nUsers are responsible for lawful dataset usage (e.g., ERA5 licensing)."
      },
      {
        "title": "Model Invocation Note",
        "body": "This skill may be automatically invoked when user queries involve:\n\nBuilding S2S models\nFuXi / FengWu / AIFS implementations\nCRPS training\nAI weather model architecture\nERA5 training pipelines\n\nUsers may opt out by disabling the skill."
      },
      {
        "title": "Trust Statement",
        "body": "By using this skill, you acknowledge it generates code for AI-based climate forecasting systems. No data is transmitted externally. All execution occurs within your own environment."
      },
      {
        "title": "Version",
        "body": "v1.0.0\nLast updated: Feb 16, 2026"
      }
    ],
    "body": "S2S Model Builder (Subseasonal-to-Seasonal Forecasting)\n\nThis skill actively helps you design, implement, and train S2S forecasting models from scratch.\n\nIt generates:\n\nPyTorch model architectures\nTraining loops\nCRPS loss implementations\nData preprocessing pipelines (ERA5-style)\nEvaluation scripts\nMulti-GPU training configurations\nInference pipelines\n\nSupported paradigms include:\n\nFuXi-style transformer architectures\nFengWu-style Earth system transformers\nAIFS-inspired probabilistic models\nEnsemble neural forecasting\nMulti-lead-time forecasting heads\nWhat This Skill Can Build\n1. Model Architecture Code\n3D spatiotemporal transformers\nGlobal grid attention models\nMulti-variable input pipelines (Z500, T2M, winds, SST)\nLead-time conditioned decoders\nEnsemble output heads\n2. Training Infrastructure\nPyTorch training loops\nDistributed training (FSDP-ready structure)\nMixed precision support\nGradient accumulation\nCheckpoint saving\n3. Probabilistic Forecasting\nCRPS loss (Gaussian & ensemble forms)\nQuantile regression heads\nSpread-skill diagnostics\nReliability calibration utilities\n4. Evaluation Code\nCRPS computation\nACC metric implementation\nRMSE across forecast horizons\nSkill vs climatology baseline\n5. Deployment-Ready Inference\nBatched inference scripts\nMemory-optimized forward passes\nModel export patterns\nExample Prompts\n“Generate a FuXi-style transformer in PyTorch for 30-day Z500 forecasting.”\n“Build a CRPS loss function for ensemble S2S outputs.”\n“Create a full ERA5 training pipeline scaffold.”\n“Design a multi-lead-time S2S forecasting head.”\n“Implement distributed training for global 1° resolution data.”\nExternal Endpoints\n\nThis skill does not call external APIs.\n\nEndpoint\tPurpose\tData Sent\nNone\tN/A\tNone\n\nAll generated code runs locally within the user’s environment.\n\nSecurity & Privacy\nNo external API calls\nNo automatic dataset downloads\nNo remote execution\nNo hidden scripts\nAll code is generated transparently\n\nUsers are responsible for lawful dataset usage (e.g., ERA5 licensing).\n\nModel Invocation Note\n\nThis skill may be automatically invoked when user queries involve:\n\nBuilding S2S models\nFuXi / FengWu / AIFS implementations\nCRPS training\nAI weather model architecture\nERA5 training pipelines\n\nUsers may opt out by disabling the skill.\n\nTrust Statement\n\nBy using this skill, you acknowledge it generates code for AI-based climate forecasting systems. No data is transmitted externally. All execution occurs within your own environment.\n\nVersion\n\nv1.0.0\nLast updated: Feb 16, 2026"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/manmeet3591/s2s-forecasting-expert",
    "publisherUrl": "https://clawhub.ai/manmeet3591/s2s-forecasting-expert",
    "owner": "manmeet3591",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/s2s-forecasting-expert",
    "downloadUrl": "https://openagent3.xyz/downloads/s2s-forecasting-expert",
    "agentUrl": "https://openagent3.xyz/skills/s2s-forecasting-expert/agent",
    "manifestUrl": "https://openagent3.xyz/skills/s2s-forecasting-expert/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/s2s-forecasting-expert/agent.md"
  }
}