{
  "schemaVersion": "1.0",
  "item": {
    "slug": "refua",
    "name": "Refua",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/jbenjoseph/refua",
    "canonicalUrl": "https://clawhub.ai/jbenjoseph/refua",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/refua",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=refua",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "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. 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. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/refua"
    },
    "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/refua",
    "agentPageUrl": "https://openagent3.xyz/skills/refua/agent",
    "manifestUrl": "https://openagent3.xyz/skills/refua/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/refua/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. 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. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Summary",
        "body": "Refua is used in drug discovery to computationally fold and score biomolecular complexes (e.g., protein–ligand/protein–protein) and optionally profile ADMET, helping prioritize which molecules to synthesize and test first in a drug discovery pipeline.\n\nThis skill runs and connects to the refua-mcp MCP server, which exposes Refua’s “unified Complex API” as MCP tools for:\n\nBoltz2 complex folding (+ optional affinity evaluation)\nBoltzGen design workflows\nOptional ADMET profiling (when installed)\n\nClawdbot supports MCP natively, so the only requirement is running this MCP server and calling its tools. (github.com)"
      },
      {
        "title": "When to use",
        "body": "Use this skill when you need to:\n\nFold a protein–ligand, protein–protein, or (fold-only) DNA/RNA complex\nEstimate binding affinity for a specified binder within a complex spec\nRun ADMET predictions for one or more SMILES ligands (if enabled)\nExecute GPU/CPU-heavy Refua workflows via MCP tool calls\n\nDo NOT use this skill when:\n\nThe task is a simple deterministic calculation (prefer a non-ML tool)\nThe user expects you to invent sequences/SMILES (request inputs instead)\nThe user requests unsafe wet-lab or clinical guidance"
      },
      {
        "title": "1) Install Refua + refua-mcp",
        "body": "Install Refua (CPU or CUDA), then install the MCP server package: (github.com)\n\nGPU support:\n\npip install refua[cuda]\n\n\nCPU-only:\n\npip install refua\n\n\nMCP server:\n\npip install refua-mcp"
      },
      {
        "title": "2) Optional: enable ADMET",
        "body": "ADMET tool support is optional and requires an extra: (github.com)\n\npip install refua[admet]"
      },
      {
        "title": "3) Download model/assets",
        "body": "Boltz2 and BoltzGen require model/molecule assets. Refua can download them automatically: (github.com)\n\npython -c \"from refua import download_assets; download_assets()\"\n\nDefault asset locations + overrides: (github.com)\n\nBoltz2 uses ~/.boltz by default\n\nOverride via tool option boltz.cache_dir if needed\n\n\nBoltzGen uses a bundled HF artifact by default\n\nOverride via tool option boltzgen.mol_dir if needed"
      },
      {
        "title": "Running the MCP server",
        "body": "Start the server using the module entrypoint: (github.com)\n\npython3 -m refua_mcp.server"
      }
    ],
    "body": "Skill: Refua\nSummary\n\nRefua is used in drug discovery to computationally fold and score biomolecular complexes (e.g., protein–ligand/protein–protein) and optionally profile ADMET, helping prioritize which molecules to synthesize and test first in a drug discovery pipeline.\n\nThis skill runs and connects to the refua-mcp MCP server, which exposes Refua’s “unified Complex API” as MCP tools for:\n\nBoltz2 complex folding (+ optional affinity evaluation)\nBoltzGen design workflows\nOptional ADMET profiling (when installed)\n\nClawdbot supports MCP natively, so the only requirement is running this MCP server and calling its tools. (github.com)\n\nWhen to use\n\nUse this skill when you need to:\n\nFold a protein–ligand, protein–protein, or (fold-only) DNA/RNA complex\nEstimate binding affinity for a specified binder within a complex spec\nRun ADMET predictions for one or more SMILES ligands (if enabled)\nExecute GPU/CPU-heavy Refua workflows via MCP tool calls\n\nDo NOT use this skill when:\n\nThe task is a simple deterministic calculation (prefer a non-ML tool)\nThe user expects you to invent sequences/SMILES (request inputs instead)\nThe user requests unsafe wet-lab or clinical guidance\nInstallation & assets (operator steps)\n1) Install Refua + refua-mcp\n\nInstall Refua (CPU or CUDA), then install the MCP server package: (github.com)\n\nGPU support:\npip install refua[cuda]\nCPU-only:\npip install refua\nMCP server:\npip install refua-mcp\n2) Optional: enable ADMET\n\nADMET tool support is optional and requires an extra: (github.com)\n\npip install refua[admet]\n3) Download model/assets\n\nBoltz2 and BoltzGen require model/molecule assets. Refua can download them automatically: (github.com)\n\npython -c \"from refua import download_assets; download_assets()\"\n\nDefault asset locations + overrides: (github.com)\n\nBoltz2 uses ~/.boltz by default\nOverride via tool option boltz.cache_dir if needed\nBoltzGen uses a bundled HF artifact by default\nOverride via tool option boltzgen.mol_dir if needed\nRunning the MCP server\n\nStart the server using the module entrypoint: (github.com)\n\npython3 -m refua_mcp.server"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/jbenjoseph/refua",
    "publisherUrl": "https://clawhub.ai/jbenjoseph/refua",
    "owner": "jbenjoseph",
    "version": "0.4.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/refua",
    "downloadUrl": "https://openagent3.xyz/downloads/refua",
    "agentUrl": "https://openagent3.xyz/skills/refua/agent",
    "manifestUrl": "https://openagent3.xyz/skills/refua/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/refua/agent.md"
  }
}