{
  "schemaVersion": "1.0",
  "item": {
    "slug": "pharma-pharmacology-agent",
    "name": "Pharmaclaw Pharmacology Agent",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Cheminem/pharma-pharmacology-agent",
    "canonicalUrl": "https://clawhub.ai/Cheminem/pharma-pharmacology-agent",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/pharma-pharmacology-agent",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pharma-pharmacology-agent",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "scripts/chain_entry.py",
      "references/api_reference.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. 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": "2026-04-30T16:55:25.780Z",
      "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/pharma-pharmacology-agent"
    },
    "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/pharma-pharmacology-agent",
    "agentPageUrl": "https://openagent3.xyz/skills/pharma-pharmacology-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pharma-pharmacology-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pharma-pharmacology-agent/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": "Overview",
        "body": "Predictive pharmacology profiling for drug candidates using RDKit descriptors and validated rule-based heuristics. Provides comprehensive ADME assessment, drug-likeness scoring, and risk flagging — all from a SMILES string.\n\nKey capabilities:\n\nDrug-likeness: Lipinski Rule of Five, Veber oral bioavailability rules\nScores: QED (Quantitative Estimate of Drug-likeness), SA Score (Synthetic Accessibility)\nADME predictions: BBB permeability, aqueous solubility (ESOL), GI absorption (Egan), CYP3A4 inhibition risk, P-glycoprotein substrate, plasma protein binding\nSafety: PAINS (Pan-Assay Interference) filter alerts\nRisk assessment: Automated flagging of pharmacological concerns\nStandard chain output: JSON schema compatible with all downstream agents"
      },
      {
        "title": "Quick Start",
        "body": "# Profile a molecule from SMILES\nexec python scripts/chain_entry.py --input-json '{\"smiles\": \"CC(=O)Oc1ccccc1C(=O)O\", \"context\": \"user\"}'\n\n# Chain from chemistry-query output\nexec python scripts/chain_entry.py --input-json '{\"smiles\": \"<canonical_smiles>\", \"context\": \"from_chemistry\"}'"
      },
      {
        "title": "scripts/chain_entry.py",
        "body": "Main entry point. Accepts JSON with smiles field, returns full pharmacology profile.\n\nInput:\n\n{\"smiles\": \"CN1C=NC2=C1C(=O)N(C(=O)N2C)C\", \"context\": \"user\"}\n\nOutput schema:\n\n{\n  \"agent\": \"pharma-pharmacology\",\n  \"version\": \"1.1.0\",\n  \"smiles\": \"<canonical>\",\n  \"status\": \"success|error\",\n  \"report\": {\n    \"descriptors\": {\"mw\": 194.08, \"logp\": -1.03, \"tpsa\": 61.82, \"hbd\": 0, \"hba\": 6, \"rotb\": 0, \"arom_rings\": 2, \"heavy_atoms\": 14, \"mr\": 51.2},\n    \"lipinski\": {\"pass\": true, \"violations\": 0, \"details\": {...}},\n    \"veber\": {\"pass\": true, \"tpsa\": {...}, \"rotatable_bonds\": {...}},\n    \"qed\": 0.5385,\n    \"sa_score\": 2.3,\n    \"adme\": {\n      \"bbb\": {\"prediction\": \"moderate\", \"confidence\": \"medium\", \"rationale\": \"...\"},\n      \"solubility\": {\"logS_estimate\": -1.87, \"class\": \"high\", \"rationale\": \"...\"},\n      \"gi_absorption\": {\"prediction\": \"high\", \"rationale\": \"...\"},\n      \"cyp3a4_inhibition\": {\"risk\": \"low\", \"rationale\": \"...\"},\n      \"pgp_substrate\": {\"prediction\": \"unlikely\", \"rationale\": \"...\"},\n      \"plasma_protein_binding\": {\"prediction\": \"moderate-low\", \"rationale\": \"...\"}\n    },\n    \"pains\": {\"alert\": false}\n  },\n  \"risks\": [],\n  \"recommend_next\": [\"toxicology\", \"ip-expansion\"],\n  \"confidence\": 0.85,\n  \"warnings\": [],\n  \"timestamp\": \"ISO8601\"\n}"
      },
      {
        "title": "ADME Prediction Rules",
        "body": "PropertyMethodThresholdsBBB permeabilityClark's rules (TPSA/logP)TPSA<60+logP 1-3 = high; TPSA<90 = moderateSolubilityESOL approximationlogS > -2 high; > -4 moderate; else lowGI absorptionEgan egg modellogP<5.6 and TPSA<131.6 = highCYP3A4 inhibitionRule-basedlogP>3 and MW>300 = high riskP-gp substrateRule-basedMW>400 and HBD>2 = likelyPlasma protein bindinglogP correlationlogP>3 = high (>90%)"
      },
      {
        "title": "Chaining",
        "body": "This agent is designed to receive output from chemistry-query:\n\nchemistry-query (name→SMILES+props) → pharma-pharmacology (ADME profile) → toxicology / ip-expansion\n\nThe recommend_next field always includes [\"toxicology\", \"ip-expansion\"] for pipeline continuation."
      },
      {
        "title": "Tested With",
        "body": "All features verified end-to-end with RDKit 2024.03+:\n\nMoleculeMWlogPLipinskiKey FindingsCaffeine194.08-1.03✅ Pass (0 violations)High solubility, moderate BBB, QED 0.54Aspirin180.041.31✅ Pass (0 violations)Moderate solubility, SA 1.58 (easy), QED 0.55Sotorasib560.234.48✅ Pass (1 violation: MW)Low solubility, CYP3A4 risk, high PPBMetformin129.10-1.03✅ Pass (0 violations)High solubility, low BBB, QED 0.25Invalid SMILES———Graceful JSON errorEmpty input———Graceful JSON error"
      },
      {
        "title": "Error Handling",
        "body": "Invalid SMILES: Returns status: \"error\" with descriptive warning\nMissing input: Clear error message requesting smiles or name\nAll errors produce valid JSON (never crashes)"
      },
      {
        "title": "Resources",
        "body": "references/api_reference.md — API and methodology references"
      },
      {
        "title": "Changelog",
        "body": "v1.1.0 (2026-02-14)\n\nInitial production release with full ADME profiling\nLipinski, Veber, QED, SA Score, PAINS\nBBB, solubility, GI absorption, CYP3A4, P-gp, PPB predictions\nAutomated risk assessment\nStandard chain output schema\nComprehensive error handling\nEnd-to-end tested with diverse molecules"
      }
    ],
    "body": "Pharma Pharmacology Agent v1.1.0\nOverview\n\nPredictive pharmacology profiling for drug candidates using RDKit descriptors and validated rule-based heuristics. Provides comprehensive ADME assessment, drug-likeness scoring, and risk flagging — all from a SMILES string.\n\nKey capabilities:\n\nDrug-likeness: Lipinski Rule of Five, Veber oral bioavailability rules\nScores: QED (Quantitative Estimate of Drug-likeness), SA Score (Synthetic Accessibility)\nADME predictions: BBB permeability, aqueous solubility (ESOL), GI absorption (Egan), CYP3A4 inhibition risk, P-glycoprotein substrate, plasma protein binding\nSafety: PAINS (Pan-Assay Interference) filter alerts\nRisk assessment: Automated flagging of pharmacological concerns\nStandard chain output: JSON schema compatible with all downstream agents\nQuick Start\n# Profile a molecule from SMILES\nexec python scripts/chain_entry.py --input-json '{\"smiles\": \"CC(=O)Oc1ccccc1C(=O)O\", \"context\": \"user\"}'\n\n# Chain from chemistry-query output\nexec python scripts/chain_entry.py --input-json '{\"smiles\": \"<canonical_smiles>\", \"context\": \"from_chemistry\"}'\n\nScripts\nscripts/chain_entry.py\n\nMain entry point. Accepts JSON with smiles field, returns full pharmacology profile.\n\nInput:\n\n{\"smiles\": \"CN1C=NC2=C1C(=O)N(C(=O)N2C)C\", \"context\": \"user\"}\n\n\nOutput schema:\n\n{\n  \"agent\": \"pharma-pharmacology\",\n  \"version\": \"1.1.0\",\n  \"smiles\": \"<canonical>\",\n  \"status\": \"success|error\",\n  \"report\": {\n    \"descriptors\": {\"mw\": 194.08, \"logp\": -1.03, \"tpsa\": 61.82, \"hbd\": 0, \"hba\": 6, \"rotb\": 0, \"arom_rings\": 2, \"heavy_atoms\": 14, \"mr\": 51.2},\n    \"lipinski\": {\"pass\": true, \"violations\": 0, \"details\": {...}},\n    \"veber\": {\"pass\": true, \"tpsa\": {...}, \"rotatable_bonds\": {...}},\n    \"qed\": 0.5385,\n    \"sa_score\": 2.3,\n    \"adme\": {\n      \"bbb\": {\"prediction\": \"moderate\", \"confidence\": \"medium\", \"rationale\": \"...\"},\n      \"solubility\": {\"logS_estimate\": -1.87, \"class\": \"high\", \"rationale\": \"...\"},\n      \"gi_absorption\": {\"prediction\": \"high\", \"rationale\": \"...\"},\n      \"cyp3a4_inhibition\": {\"risk\": \"low\", \"rationale\": \"...\"},\n      \"pgp_substrate\": {\"prediction\": \"unlikely\", \"rationale\": \"...\"},\n      \"plasma_protein_binding\": {\"prediction\": \"moderate-low\", \"rationale\": \"...\"}\n    },\n    \"pains\": {\"alert\": false}\n  },\n  \"risks\": [],\n  \"recommend_next\": [\"toxicology\", \"ip-expansion\"],\n  \"confidence\": 0.85,\n  \"warnings\": [],\n  \"timestamp\": \"ISO8601\"\n}\n\nADME Prediction Rules\nProperty\tMethod\tThresholds\nBBB permeability\tClark's rules (TPSA/logP)\tTPSA<60+logP 1-3 = high; TPSA<90 = moderate\nSolubility\tESOL approximation\tlogS > -2 high; > -4 moderate; else low\nGI absorption\tEgan egg model\tlogP<5.6 and TPSA<131.6 = high\nCYP3A4 inhibition\tRule-based\tlogP>3 and MW>300 = high risk\nP-gp substrate\tRule-based\tMW>400 and HBD>2 = likely\nPlasma protein binding\tlogP correlation\tlogP>3 = high (>90%)\nChaining\n\nThis agent is designed to receive output from chemistry-query:\n\nchemistry-query (name→SMILES+props) → pharma-pharmacology (ADME profile) → toxicology / ip-expansion\n\n\nThe recommend_next field always includes [\"toxicology\", \"ip-expansion\"] for pipeline continuation.\n\nTested With\n\nAll features verified end-to-end with RDKit 2024.03+:\n\nMolecule\tMW\tlogP\tLipinski\tKey Findings\nCaffeine\t194.08\t-1.03\t✅ Pass (0 violations)\tHigh solubility, moderate BBB, QED 0.54\nAspirin\t180.04\t1.31\t✅ Pass (0 violations)\tModerate solubility, SA 1.58 (easy), QED 0.55\nSotorasib\t560.23\t4.48\t✅ Pass (1 violation: MW)\tLow solubility, CYP3A4 risk, high PPB\nMetformin\t129.10\t-1.03\t✅ Pass (0 violations)\tHigh solubility, low BBB, QED 0.25\nInvalid SMILES\t—\t—\t—\tGraceful JSON error\nEmpty input\t—\t—\t—\tGraceful JSON error\nError Handling\nInvalid SMILES: Returns status: \"error\" with descriptive warning\nMissing input: Clear error message requesting smiles or name\nAll errors produce valid JSON (never crashes)\nResources\nreferences/api_reference.md — API and methodology references\nChangelog\n\nv1.1.0 (2026-02-14)\n\nInitial production release with full ADME profiling\nLipinski, Veber, QED, SA Score, PAINS\nBBB, solubility, GI absorption, CYP3A4, P-gp, PPB predictions\nAutomated risk assessment\nStandard chain output schema\nComprehensive error handling\nEnd-to-end tested with diverse molecules"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Cheminem/pharma-pharmacology-agent",
    "publisherUrl": "https://clawhub.ai/Cheminem/pharma-pharmacology-agent",
    "owner": "Cheminem",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/pharma-pharmacology-agent",
    "downloadUrl": "https://openagent3.xyz/downloads/pharma-pharmacology-agent",
    "agentUrl": "https://openagent3.xyz/skills/pharma-pharmacology-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pharma-pharmacology-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pharma-pharmacology-agent/agent.md"
  }
}