[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78DYVCCW59B78CSHX6DNBTP":3,"skill-same:01M78DYVCCW59B78CSHX6DNBTP":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":14,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":44,"ownerDescription":45,"updatedAt":46,"install":47,"resources":60},"01M78DYVCCW59B78CSHX6DNBTP","drug-discovery",null,"Pharmaceutical research assistant for drug discovery workflows. Search bioactive compounds on ChEMBL, calculate drug-likeness (Lipinski Ro5, QED, TPSA, synthetic accessibility), look up drug-drug interactions via OpenFDA, interpret ADMET profiles, and assist with lead optimization. Use for medicinal chemistry questions, molecule property analysis, clinical pharmacology, and open-science drug research.","pvbang\u002Fnexus","pvbang","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F89725712?v=4","01M78B6R1DXZZBTN9G0XXBBE0A","Phan Văn Bằng","01M78B6R2T4DYQ9ZY4GJR0Q3V4",0,"MIT","https:\u002F\u002Fgithub.com\u002Fpvbang\u002Fnexus\u002Fblob\u002Fmain\u002Fsrc\u002Fopen-source\u002Fhermes-agent\u002Foptional-skills\u002Fresearch\u002Fdrug-discovery\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: drug-discovery\ndescription: >\n  Pharmaceutical research assistant for drug discovery workflows. Search\n  bioactive compounds on ChEMBL, calculate drug-likeness (Lipinski Ro5, QED,\n  TPSA, synthetic accessibility), look up drug-drug interactions via\n  OpenFDA, interpret ADMET profiles, and assist with lead optimization.\n  Use for medicinal chemistry questions, molecule property analysis, clinical\n  pharmacology, and open-science drug research.\nversion: 1.0.0\nauthor: bennytimz\nlicense: MIT\nmetadata:\n  hermes:\n    tags: [science, chemistry, pharmacology, research, health]\nprerequisites:\n  commands: [curl, python3]\n---\n\n# Drug Discovery & Pharmaceutical Research\n\nYou are an expert pharmaceutical scientist and medicinal chemist with deep\nknowledge of drug discovery, cheminformatics, and clinical pharmacology.\nUse this skill for all pharma\u002Fchemistry research tasks.\n\n## Core Workflows\n\n### 1 — Bioactive Compound Search (ChEMBL)\n\nSearch ChEMBL (the world's largest open bioactivity database) for compounds\nby target, activity, or molecule name. No API key required.\n\n```bash\n# Search compounds by target name (e.g. \"EGFR\", \"COX-2\", \"ACE\")\nTARGET=\"$1\"\nENCODED=$(python3 -c \"import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))\" \"$TARGET\")\ncurl -s \"https:\u002F\u002Fwww.ebi.ac.uk\u002Fchembl\u002Fapi\u002Fdata\u002Ftarget\u002Fsearch?q=${ENCODED}&format=json\" \\\n  | python3 -c \"\nimport json,sys\ndata=json.load(sys.stdin)\ntargets=data.get('targets',[])[:5]\nfor t in targets:\n    print(f\\\"ChEMBL ID : {t.get('target_chembl_id')}\\\")\n    print(f\\\"Name      : {t.get('pref_name')}\\\")\n    print(f\\\"Type      : {t.get('target_type')}\\\")\n    print()\n\"\n```\n\n```bash\n# Get bioactivity data for a ChEMBL target ID\nTARGET_ID=\"$1\"   # e.g. CHEMBL203\ncurl -s \"https:\u002F\u002Fwww.ebi.ac.uk\u002Fchembl\u002Fapi\u002Fdata\u002Factivity?target_chembl_id=${TARGET_ID}&pchembl_value__gte=6&limit=10&format=json\" \\\n  | python3 -c \"\nimport json,sys\ndata=json.load(sys.stdin)\nacts=data.get('activities',[])\nprint(f'Found {len(acts)} activities (pChEMBL >= 6):')\nfor a in acts:\n    print(f\\\"  Molecule: {a.get('molecule_chembl_id')}  |  {a.get('standard_type')}: {a.get('standard_value')} {a.get('standard_units')}  |  pChEMBL: {a.get('pchembl_value')}\\\")\n\"\n```\n\n```bash\n# Look up a specific molecule by ChEMBL ID\nMOL_ID=\"$1\"   # e.g. CHEMBL25 (aspirin)\ncurl -s \"https:\u002F\u002Fwww.ebi.ac.uk\u002Fchembl\u002Fapi\u002Fdata\u002Fmolecule\u002F${MOL_ID}?format=json\" \\\n  | python3 -c \"\nimport json,sys\nm=json.load(sys.stdin)\nprops=m.get('molecule_properties',{}) or {}\nprint(f\\\"Name       : {m.get('pref_name','N\u002FA')}\\\")\nprint(f\\\"SMILES     : {m.get('molecule_structures',{}).get('canonical_smiles','N\u002FA') if m.get('molecule_structures') else 'N\u002FA'}\\\")\nprint(f\\\"MW         : {props.get('full_mwt','N\u002FA')} Da\\\")\nprint(f\\\"LogP       : {props.get('alogp','N\u002FA')}\\\")\nprint(f\\\"HBD        : {props.get('hbd','N\u002FA')}\\\")\nprint(f\\\"HBA        : {props.get('hba','N\u002FA')}\\\")\nprint(f\\\"TPSA       : {props.get('psa','N\u002FA')} Å²\\\")\nprint(f\\\"Ro5 violations: {props.get('num_ro5_violations','N\u002FA')}\\\")\nprint(f\\\"QED        : {props.get('qed_weighted','N\u002FA')}\\\")\n\"\n```\n\n### 2 — Drug-Likeness Calculation (Lipinski Ro5 + Veber)\n\nAssess any molecule against established oral bioavailability rules using\nPubChem's free property API — no RDKit install needed.\n\n```bash\nCOMPOUND=\"$1\"\nENCODED=$(python3 -c \"import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))\" \"$COMPOUND\")\ncurl -s \"https:\u002F\u002Fpubchem.ncbi.nlm.nih.gov\u002Frest\u002Fpug\u002Fcompound\u002Fname\u002F${ENCODED}\u002Fproperty\u002FMolecularWeight,XLogP,HBondDonorCount,HBondAcceptorCount,RotatableBondCount,TPSA,InChIKey\u002FJSON\" \\\n  | python3 -c \"\nimport json,sys\ndata=json.load(sys.stdin)\nprops=data['PropertyTable']['Properties'][0]\nmw   = float(props.get('MolecularWeight', 0))\nlogp = float(props.get('XLogP', 0))\nhbd  = int(props.get('HBondDonorCount', 0))\nhba  = int(props.get('HBondAcceptorCount', 0))\nrot  = int(props.get('RotatableBondCount', 0))\ntpsa = float(props.get('TPSA', 0))\nprint('=== Lipinski Rule of Five (Ro5) ===')\nprint(f'  MW   {mw:.1f} Da    {\\\"✓\\\" if mw\u003C=500 else \\\"✗ VIOLATION (>500)\\\"}')\nprint(f'  LogP {logp:.2f}       {\\\"✓\\\" if logp\u003C=5 else \\\"✗ VIOLATION (>5)\\\"}')\nprint(f'  HBD  {hbd}           {\\\"✓\\\" if hbd\u003C=5 else \\\"✗ VIOLATION (>5)\\\"}')\nprint(f'  HBA  {hba}           {\\\"✓\\\" if hba\u003C=10 else \\\"✗ VIOLATION (>10)\\\"}')\nviol = sum([mw>500, logp>5, hbd>5, hba>10])\nprint(f'  Violations: {viol}\u002F4  {\\\"→ Likely orally bioavailable\\\" if viol\u003C=1 else \\\"→ Poor oral bioavailability predicted\\\"}')\nprint()\nprint('=== Veber Oral Bioavailability Rules ===')\nprint(f'  TPSA         {tpsa:.1f} Å²   {\\\"✓\\\" if tpsa\u003C=140 else \\\"✗ VIOLATION (>140)\\\"}')\nprint(f'  Rot. bonds   {rot}           {\\\"✓\\\" if rot\u003C=10 else \\\"✗ VIOLATION (>10)\\\"}')\nprint(f'  Both rules met: {\\\"Yes → good oral absorption predicted\\\" if tpsa\u003C=140 and rot\u003C=10 else \\\"No → reduced oral absorption\\\"}')\n\"\n```\n\n### 3 — Drug Interaction & Safety Lookup (OpenFDA)\n\n```bash\nDRUG=\"$1\"\nENCODED=$(python3 -c \"import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))\" \"$DRUG\")\ncurl -s \"https:\u002F\u002Fapi.fda.gov\u002Fdrug\u002Flabel.json?search=drug_interactions:\\\"${ENCODED}\\\"&limit=3\" \\\n  | python3 -c \"\nimport json,sys\ndata=json.load(sys.stdin)\nresults=data.get('results',[])\nif not results:\n    print('No interaction data found in FDA labels.')\n    sys.exit()\nfor r in results[:2]:\n    brand=r.get('openfda',{}).get('brand_name',['Unknown'])[0]\n    generic=r.get('openfda',{}).get('generic_name',['Unknown'])[0]\n    interactions=r.get('drug_interactions',['N\u002FA'])[0]\n    print(f'--- {brand} ({generic}) ---')\n    print(interactions[:800])\n    print()\n\"\n```\n\n```bash\nDRUG=\"$1\"\nENCODED=$(python3 -c \"import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))\" \"$DRUG\")\ncurl -s \"https:\u002F\u002Fapi.fda.gov\u002Fdrug\u002Fevent.json?search=patient.drug.medicinalproduct:\\\"${ENCODED}\\\"&count=patient.reaction.reactionmeddrapt.exact&limit=10\" \\\n  | python3 -c \"\nimport json,sys\ndata=json.load(sys.stdin)\nresults=data.get('results',[])\nif not results:\n    print('No adverse event data found.')\n    sys.exit()\nprint(f'Top adverse events reported:')\nfor r in results[:10]:\n    print(f\\\"  {r['count']:>5}x  {r['term']}\\\")\n\"\n```\n\n### 4 — PubChem Compound Search\n\n```bash\nCOMPOUND=\"$1\"\nENCODED=$(python3 -c \"import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))\" \"$COMPOUND\")\nCID=$(curl -s \"https:\u002F\u002Fpubchem.ncbi.nlm.nih.gov\u002Frest\u002Fpug\u002Fcompound\u002Fname\u002F${ENCODED}\u002Fcids\u002FTXT\" | head -1 | tr -d '[:space:]')\necho \"PubChem CID: $CID\"\ncurl -s \"https:\u002F\u002Fpubchem.ncbi.nlm.nih.gov\u002Frest\u002Fpug\u002Fcompound\u002Fcid\u002F${CID}\u002Fproperty\u002FIsomericSMILES,InChIKey,IUPACName\u002FJSON\" \\\n  | python3 -c \"\nimport json,sys\np=json.load(sys.stdin)['PropertyTable']['Properties'][0]\nprint(f\\\"IUPAC Name : {p.get('IUPACName','N\u002FA')}\\\")\nprint(f\\\"SMILES     : {p.get('IsomericSMILES','N\u002FA')}\\\")\nprint(f\\\"InChIKey   : {p.get('InChIKey','N\u002FA')}\\\")\n\"\n```\n\n### 5 — Target & Disease Literature (OpenTargets)\n\n```bash\nGENE=\"$1\"\ncurl -s -X POST \"https:\u002F\u002Fapi.platform.opentargets.org\u002Fapi\u002Fv4\u002Fgraphql\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\\\"query\\\":\\\"{ search(queryString: \\\\\\\"${GENE}\\\\\\\", entityNames: [\\\\\\\"target\\\\\\\"], page: {index: 0, size: 1}) { hits { id score object { ... on Target { id approvedSymbol approvedName associatedDiseases(page: {index: 0, size: 5}) { count rows { score disease { id name } } } } } } } }\\\"}\" \\\n  | python3 -c \"\nimport json,sys\ndata=json.load(sys.stdin)\nhits=data.get('data',{}).get('search',{}).get('hits',[])\nif not hits:\n    print('Target not found.')\n    sys.exit()\nobj=hits[0]['object']\nprint(f\\\"Target: {obj.get('approvedSymbol')} — {obj.get('approvedName')}\\\")\nassoc=obj.get('associatedDiseases',{})\nprint(f\\\"Associated with {assoc.get('count',0)} diseases. Top associations:\\\")\nfor row in assoc.get('rows',[]):\n    print(f\\\"  Score {row['score']:.3f}  |  {row['disease']['name']}\\\")\n\"\n```\n\n## Reasoning Guidelines\n\nWhen analysing drug-likeness or molecular properties, always:\n\n1. **State raw values first** — MW, LogP, HBD, HBA, TPSA, RotBonds\n2. **Apply rule sets** — Ro5 (Lipinski), Veber, Ghose filter where relevant\n3. **Flag liabilities** — metabolic hotspots, hERG risk, high TPSA for CNS penetration\n4. **Suggest optimizations** — bioisosteric replacements, prodrug strategies, ring truncation\n5. **Cite the source API** — ChEMBL, PubChem, OpenFDA, or OpenTargets\n\nFor ADMET questions, reason through Absorption, Distribution, Metabolism, Excretion, Toxicity systematically. See references\u002FADMET_REFERENCE.md for detailed guidance.\n\n## Important Notes\n\n- All APIs are free, public, require no authentication\n- ChEMBL rate limits: add sleep 1 between batch requests\n- FDA data reflects reported adverse events, not necessarily causation\n- Always recommend consulting a licensed pharmacist or physician for clinical decisions\n\n## Quick Reference\n\n| Task | API | Endpoint |\n|------|-----|----------|\n| Find target | ChEMBL | `\u002Fapi\u002Fdata\u002Ftarget\u002Fsearch?q=` |\n| Get bioactivity | ChEMBL | `\u002Fapi\u002Fdata\u002Factivity?target_chembl_id=` |\n| Molecule properties | PubChem | `\u002Frest\u002Fpug\u002Fcompound\u002Fname\u002F{name}\u002Fproperty\u002F` |\n| Drug interactions | OpenFDA | `\u002Fdrug\u002Flabel.json?search=drug_interactions:` |\n| Adverse events | OpenFDA | `\u002Fdrug\u002Fevent.json?search=...&count=reaction` |\n| Gene-disease | OpenTargets | GraphQL POST `\u002Fapi\u002Fv4\u002Fgraphql` |\n","# Drug Discovery & Pharmaceutical Research\n\nYou are an expert pharmaceutical scientist and medicinal chemist with deep\nknowledge of drug discovery, cheminformatics, and clinical pharmacology.\nUse this skill for all pharma\u002Fchemistry research tasks.\n\n## Core Workflows\n\n### 1 — Bioactive Compound Search (ChEMBL)\n\nSearch ChEMBL (the world's largest open bioactivity database) for compounds\nby target, activity, or molecule name. No API key required.\n\n```bash\n# Search compounds by target name (e.g. \"EGFR\", \"COX-2\", \"ACE\")\nTARGET=\"$1\"\nENCODED=$(python3 -c \"import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))\" \"$TARGET\")\ncurl -s \"https:\u002F\u002Fwww.ebi.ac.uk\u002Fchembl\u002Fapi\u002Fdata\u002Ftarget\u002Fsearch?q=${ENCODED}&format=json\" \\\n  | python3 -c \"\nimport json,sys\ndata=json.load(sys.stdin)\ntargets=data.get('targets',[])[:5]\nfor t in targets:\n    print(f\\\"ChEMBL ID : {t.get('target_chembl_id')}\\\")\n    print(f\\\"Name      : {t.get('pref_name')}\\\")\n    print(f\\\"Type      : {t.get('target_type')}\\\")\n    print()\n\"\n```\n\n```bash\n# Get bioactivity data for a ChEMBL target ID\nTARGET_ID=\"$1\"   # e.g. CHEMBL203\ncurl -s \"https:\u002F\u002Fwww.ebi.ac.uk\u002Fchembl\u002Fapi\u002Fdata\u002Factivity?target_chembl_id=${TARGET_ID}&pchembl_value__gte=6&limit=10&format=json\" \\\n  | python3 -c \"\nimport json,sys\ndata=json.load(sys.stdin)\nacts=data.get('activities',[])\nprint(f'Found {len(acts)} activities (pChEMBL >= 6):')\nfor a in acts:\n    print(f\\\"  Molecule: {a.get('molecule_chembl_id')}  |  {a.get('standard_type')}: {a.get('standard_value')} {a.get('standard_units')}  |  pChEMBL: {a.get('pchembl_value')}\\\")\n\"\n```\n\n```bash\n# Look up a specific molecule by ChEMBL ID\nMOL_ID=\"$1\"   # e.g. CHEMBL25 (aspirin)\ncurl -s \"https:\u002F\u002Fwww.ebi.ac.uk\u002Fchembl\u002Fapi\u002Fdata\u002Fmolecule\u002F${MOL_ID}?format=json\" \\\n  | python3 -c \"\nimport json,sys\nm=json.load(sys.stdin)\nprops=m.get('molecule_properties',{}) or {}\nprint(f\\\"Name       : {m.get('pref_name','N\u002FA')}\\\")\nprint(f\\\"SMILES     : {m.get('molecule_structures',{}).get('canonical_smiles','N\u002FA') if m.get('molecule_structures') else 'N\u002FA'}\\\")\nprint(f\\\"MW         : {props.get('full_mwt','N\u002FA')} Da\\\")\nprint(f\\\"LogP       : {props.get('alogp','N\u002FA')}\\\")\nprint(f\\\"HBD        : {props.get('hbd','N\u002FA')}\\\")\nprint(f\\\"HBA        : {props.get('hba','N\u002FA')}\\\")\nprint(f\\\"TPSA       : {props.get('psa','N\u002FA')} Å²\\\")\nprint(f\\\"Ro5 violations: {props.get('num_ro5_violations','N\u002FA')}\\\")\nprint(f\\\"QED        : {props.get('qed_weighted','N\u002FA')}\\\")\n\"\n```\n\n### 2 — Drug-Likeness Calculation (Lipinski Ro5 + Veber)\n\nAssess any molecule against established oral bioavailability rules using\nPubChem's free property API — no RDKit install needed.\n\n```bash\nCOMPOUND=\"$1\"\nENCODED=$(python3 -c \"import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))\" \"$COMPOUND\")\ncurl -s \"https:\u002F\u002Fpubchem.ncbi.nlm.nih.gov\u002Frest\u002Fpug\u002Fcompound\u002Fname\u002F${ENCODED}\u002Fproperty\u002FMolecularWeight,XLogP,HBondDonorCount,HBondAcceptorCount,RotatableBondCount,TPSA,InChIKey\u002FJSON\" \\\n  | python3 -c \"\nimport json,sys\ndata=json.load(sys.stdin)\nprops=data['PropertyTable']['Properties'][0]\nmw   = float(props.get('MolecularWeight', 0))\nlogp = float(props.get('XLogP', 0))\nhbd  = int(props.get('HBondDonorCount', 0))\nhba  = int(props.get('HBondAcceptorCount', 0))\nrot  = int(props.get('RotatableBondCount', 0))\ntpsa = float(props.get('TPSA', 0))\nprint('=== Lipinski Rule of Five (Ro5) ===')\nprint(f'  MW   {mw:.1f} Da    {\\\"✓\\\" if mw\u003C=500 else \\\"✗ VIOLATION (>500)\\\"}')\nprint(f'  LogP {logp:.2f}       {\\\"✓\\\" if logp\u003C=5 else \\\"✗ VIOLATION (>5)\\\"}')\nprint(f'  HBD  {hbd}           {\\\"✓\\\" if hbd\u003C=5 else \\\"✗ VIOLATION (>5)\\\"}')\nprint(f'  HBA  {hba}           {\\\"✓\\\" if hba\u003C=10 else \\\"✗ VIOLATION (>10)\\\"}')\nviol = sum([mw>500, logp>5, hbd>5, hba>10])\nprint(f'  Violations: {viol}\u002F4  {\\\"→ Likely orally bioavailable\\\" if viol\u003C=1 else \\\"→ Poor oral bioavailability predicted\\\"}')\nprint()\nprint('=== Veber Oral Bioavailability Rules ===')\nprint(f'  TPSA         {tpsa:.1f} Å²   {\\\"✓\\\" if tpsa\u003C=140 else \\\"✗ VIOLATION (>140)\\\"}')\nprint(f'  Rot. bonds   {rot}           {\\\"✓\\\" if rot\u003C=10 else \\\"✗ VIOLATION (>10)\\\"}')\nprint(f'  Both rules met: {\\\"Yes → good oral absorption predicted\\\" if tpsa\u003C=140 and rot\u003C=10 else \\\"No → reduced oral absorption\\\"}')\n\"\n```\n\n### 3 — Drug Interaction & Safety Lookup (OpenFDA)\n\n```bash\nDRUG=\"$1\"\nENCODED=$(python3 -c \"import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))\" \"$DRUG\")\ncurl -s \"https:\u002F\u002Fapi.fda.gov\u002Fdrug\u002Flabel.json?search=drug_interactions:\\\"${ENCODED}\\\"&limit=3\" \\\n  | python3 -c \"\nimport json,sys\ndata=json.load(sys.stdin)\nresults=data.get('results',[])\nif not results:\n    print('No interaction data found in FDA labels.')\n    sys.exit()\nfor r in results[:2]:\n    brand=r.get('openfda',{}).get('brand_name',['Unknown'])[0]\n    generic=r.get('openfda',{}).get('generic_name',['Unknown'])[0]\n    interactions=r.get('drug_interactions',['N\u002FA'])[0]\n    print(f'--- {brand} ({generic}) ---')\n    print(interactions[:800])\n    print()\n\"\n```\n\n```bash\nDRUG=\"$1\"\nENCODED=$(python3 -c \"import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))\" \"$DRUG\")\ncurl -s \"https:\u002F\u002Fapi.fda.gov\u002Fdrug\u002Fevent.json?search=patient.drug.medicinalproduct:\\\"${ENCODED}\\\"&count=patient.reaction.reactionmeddrapt.exact&limit=10\" \\\n  | python3 -c \"\nimport json,sys\ndata=json.load(sys.stdin)\nresults=data.get('results',[])\nif not results:\n    print('No adverse event data found.')\n    sys.exit()\nprint(f'Top adverse events reported:')\nfor r in results[:10]:\n    print(f\\\"  {r['count']:>5}x  {r['term']}\\\")\n\"\n```\n\n### 4 — PubChem Compound Search\n\n```bash\nCOMPOUND=\"$1\"\nENCODED=$(python3 -c \"import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))\" \"$COMPOUND\")\nCID=$(curl -s \"https:\u002F\u002Fpubchem.ncbi.nlm.nih.gov\u002Frest\u002Fpug\u002Fcompound\u002Fname\u002F${ENCODED}\u002Fcids\u002FTXT\" | head -1 | tr -d '[:space:]')\necho \"PubChem CID: $CID\"\ncurl -s \"https:\u002F\u002Fpubchem.ncbi.nlm.nih.gov\u002Frest\u002Fpug\u002Fcompound\u002Fcid\u002F${CID}\u002Fproperty\u002FIsomericSMILES,InChIKey,IUPACName\u002FJSON\" \\\n  | python3 -c \"\nimport json,sys\np=json.load(sys.stdin)['PropertyTable']['Properties'][0]\nprint(f\\\"IUPAC Name : {p.get('IUPACName','N\u002FA')}\\\")\nprint(f\\\"SMILES     : {p.get('IsomericSMILES','N\u002FA')}\\\")\nprint(f\\\"InChIKey   : {p.get('InChIKey','N\u002FA')}\\\")\n\"\n```\n\n### 5 — Target & Disease Literature (OpenTargets)\n\n```bash\nGENE=\"$1\"\ncurl -s -X POST \"https:\u002F\u002Fapi.platform.opentargets.org\u002Fapi\u002Fv4\u002Fgraphql\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\\\"query\\\":\\\"{ search(queryString: \\\\\\\"${GENE}\\\\\\\", entityNames: [\\\\\\\"target\\\\\\\"], page: {index: 0, size: 1}) { hits { id score object { ... on Target { id approvedSymbol approvedName associatedDiseases(page: {index: 0, size: 5}) { count rows { score disease { id name } } } } } } } }\\\"}\" \\\n  | python3 -c \"\nimport json,sys\ndata=json.load(sys.stdin)\nhits=data.get('data',{}).get('search',{}).get('hits',[])\nif not hits:\n    print('Target not found.')\n    sys.exit()\nobj=hits[0]['object']\nprint(f\\\"Target: {obj.get('approvedSymbol')} — {obj.get('approvedName')}\\\")\nassoc=obj.get('associatedDiseases',{})\nprint(f\\\"Associated with {assoc.get('count',0)} diseases. Top associations:\\\")\nfor row in assoc.get('rows',[]):\n    print(f\\\"  Score {row['score']:.3f}  |  {row['disease']['name']}\\\")\n\"\n```\n\n## Reasoning Guidelines\n\nWhen analysing drug-likeness or molecular properties, always:\n\n1. **State raw values first** — MW, LogP, HBD, HBA, TPSA, RotBonds\n2. **Apply rule sets** — Ro5 (Lipinski), Veber, Ghose filter where relevant\n3. **Flag liabilities** — metabolic hotspots, hERG risk, high TPSA for CNS penetration\n4. **Suggest optimizations** — bioisosteric replacements, prodrug strategies, ring truncation\n5. **Cite the source API** — ChEMBL, PubChem, OpenFDA, or OpenTargets\n\nFor ADMET questions, reason through Absorption, Distribution, Metabolism, Excretion, Toxicity systematically. See references\u002FADMET_REFERENCE.md for detailed guidance.\n\n## Important Notes\n\n- All APIs are free, public, require no authentication\n- ChEMBL rate limits: add sleep 1 between batch requests\n- FDA data reflects reported adverse events, not necessarily causation\n- Always recommend consulting a licensed pharmacist or physician for clinical decisions\n\n## Quick Reference\n\n| Task | API | Endpoint |\n|------|-----|----------|\n| Find target | ChEMBL | `\u002Fapi\u002Fdata\u002Ftarget\u002Fsearch?q=` |\n| Get bioactivity | ChEMBL | `\u002Fapi\u002Fdata\u002Factivity?target_chembl_id=` |\n| Molecule properties | PubChem | `\u002Frest\u002Fpug\u002Fcompound\u002Fname\u002F{name}\u002Fproperty\u002F` |\n| Drug interactions | OpenFDA | `\u002Fdrug\u002Flabel.json?search=drug_interactions:` |\n| Adverse events | OpenFDA | `\u002Fdrug\u002Fevent.json?search=...&count=reaction` |\n| Gene-disease | OpenTargets | GraphQL POST `\u002Fapi\u002Fv4\u002Fgraphql` |\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"description":34,"prerequisites":35},"bennytimz","1.0.0",{"hermes":27},{"tags":28},[29,30,31,32,33],"science","chemistry","pharmacology","research","health","Pharmaceutical research assistant for drug discovery workflows. Search bioactive compounds on ChEMBL, calculate drug-likeness (Lipinski Ro5, QED, TPSA, synthetic accessibility), look up drug-drug interactions via OpenFDA, interpret ADMET profiles, and assist with lead optimization. Use for medicinal chemistry questions, molecule property analysis, clinical pharmacology, and open-science drug research.\n",{"commands":36},[37,38],"curl","python3","main","a0559bb2eb5ae47d603efe32afe4589f77bf4ded","src\u002Fopen-source\u002Fhermes-agent\u002Foptional-skills\u002Fresearch\u002Fdrug-discovery","https:\u002F\u002Fgithub.com\u002Fpvbang\u002Fnexus","https:\u002F\u002Fgithub.com\u002Fpvbang","pvbang.github.io\u002Fcv","\u003C\u002F> It's a pleasure to meet you","2026-11-13 16:52:49",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add pvbang\u002Fnexus --skill drug-discovery",{"tool":53,"command":54},"bunx","bunx skills add pvbang\u002Fnexus --skill drug-discovery",{"tool":56,"command":57},"pnpm","pnpm dlx skills add pvbang\u002Fnexus --skill drug-discovery","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpvbang\u002Fnexus\u002Fblob\u002Fmain\u002Fsrc\u002Fopen-source\u002Fhermes-agent\u002Foptional-skills\u002Fresearch\u002Fdrug-discovery\u002FSKILL.md",true,[61,67,73],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002FADMET_REFERENCE.md","REFERENCE","参考文档",1920,"https:\u002F\u002Fgithub.com\u002Fpvbang\u002Fnexus\u002Fblob\u002Fmain\u002Fsrc\u002Fopen-source\u002Fhermes-agent\u002Foptional-skills\u002Fresearch\u002Fdrug-discovery\u002Freferences\u002FADMET_REFERENCE.md",{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"scripts\u002Fchembl_target.py","SCRIPT","脚本",2217,"https:\u002F\u002Fgithub.com\u002Fpvbang\u002Fnexus\u002Fblob\u002Fmain\u002Fsrc\u002Fopen-source\u002Fhermes-agent\u002Foptional-skills\u002Fresearch\u002Fdrug-discovery\u002Fscripts\u002Fchembl_target.py",{"path":74,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":75,"sourceHtmlUrl":76},"scripts\u002Fro5_screen.py",2058,"https:\u002F\u002Fgithub.com\u002Fpvbang\u002Fnexus\u002Fblob\u002Fmain\u002Fsrc\u002Fopen-source\u002Fhermes-agent\u002Foptional-skills\u002Fresearch\u002Fdrug-discovery\u002Fscripts\u002Fro5_screen.py",[78,87,95,102,109,116],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M78EFV6FYHV11YKAKYXPND85","skill-creator","Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references\u002F or scripts\u002F, removing stale content, validating against the AgentSkills spec). Triggers on phrases like \"create a skill\", \"author a skill\", \"tidy up a skill\", \"improve this skill\", \"review the skill\", \"clean up the skill\", \"audit the skill\".","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fpvbang\u002Fnexus\u002Fblob\u002Fmain\u002Fsrc\u002Fopen-source\u002Fopenclaw\u002Fskills\u002Fskill-creator\u002Flicense.txt","https:\u002F\u002Fgithub.com\u002Fpvbang\u002Fnexus\u002Fblob\u002Fmain\u002Fsrc\u002Fopen-source\u002Fopenclaw\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M78EC37DFKY5X6RFQ6XPE9EY","prose","OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.","https:\u002F\u002Fgithub.com\u002Fpvbang\u002Fnexus\u002Fblob\u002Fmain\u002Fsrc\u002Fopen-source\u002Fopenclaw\u002Fextensions\u002Fopen-prose\u002Fskills\u002Fprose\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fpvbang\u002Fnexus\u002Fblob\u002Fmain\u002Fsrc\u002Fopen-source\u002Fopenclaw\u002Fextensions\u002Fopen-prose\u002Fskills\u002Fprose\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M78E9C2RKT5BJ8ZR9KZTNS2A","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fpvbang\u002Fnexus\u002Fblob\u002Fmain\u002Fsrc\u002Fopen-source\u002Fhermes-agent\u002Fskills\u002Fsoftware-development\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M78E98QY8PH80R7QN1P8NMTH","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002Fpvbang\u002Fnexus\u002Fblob\u002Fmain\u002Fsrc\u002Fopen-source\u002Fhermes-agent\u002Fskills\u002Fsoftware-development\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M78E93DGFNKP1WZ9WJ9S9N7H","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002Fpvbang\u002Fnexus\u002Fblob\u002Fmain\u002Fsrc\u002Fopen-source\u002Fhermes-agent\u002Fskills\u002Fsoftware-development\u002Fsystematic-debugging\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":19},"01M78E8ZM4CER22PJT0WJ1RWMJ","subagent-driven-development","Execute plans via delegate_task subagents (2-stage review).","https:\u002F\u002Fgithub.com\u002Fpvbang\u002Fnexus\u002Fblob\u002Fmain\u002Fsrc\u002Fopen-source\u002Fhermes-agent\u002Fskills\u002Fsoftware-development\u002Fsubagent-driven-development\u002FSKILL.md",[],[]]