[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DPNA5J0NTSG2R1YCC5PS7R":3,"skill-same:01M6DPNA5J0NTSG2R1YCC5PS7R":169},{"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":26,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":52,"commitSha":53,"skillDirectory":5,"forksCount":14,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":56,"install":57,"resources":70},"01M6DPNA5J0NTSG2R1YCC5PS7R","pdb",null,"Fetch and analyze protein structures from RCSB PDB. Use this skill when: (1) Need to download a structure by PDB ID, (2) Search for similar structures, (3) Prepare target for binder design, (4) Extract specific chains or domains, (5) Get structure metadata.\nFor sequence lookup, use uniprot. For binder design workflow, use binder-design.","huamu668\u002Fclawhub-openclaw-medical","huamu668","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F202473531?v=4","01M6DK1V7D7VP9PJ06Z1VXVK13","huamu","01M6DK1VBYG1BX5FT154AFZHAS",0,"MIT","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fpdb\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[5,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"fetch","binder design","binder","id","get","structure","use","extract","design","analyze","download","lookup","metadata","search","database","prepare","workflow","2026-11-10 10:12:30",false,"---\nname: pdb\ndescription: >\n  Fetch and analyze protein structures from RCSB PDB. Use this skill when:\n  (1) Need to download a structure by PDB ID,\n  (2) Search for similar structures,\n  (3) Prepare target for binder design,\n  (4) Extract specific chains or domains,\n  (5) Get structure metadata.\n\n  For sequence lookup, use uniprot.\n  For binder design workflow, use binder-design.\nlicense: MIT\ncategory: utilities\ntags: [database, structure, fetch]\n---\n\n# PDB Database Access\n\n**Note**: This skill uses the RCSB PDB web API directly. No Modal deployment needed - all operations run locally via HTTP requests.\n\n## Fetching Structures\n\n### By PDB ID\n```bash\n# Download PDB file\ncurl -o 1alu.pdb \"https:\u002F\u002Ffiles.rcsb.org\u002Fdownload\u002F1ALU.pdb\"\n\n# Download mmCIF\ncurl -o 1alu.cif \"https:\u002F\u002Ffiles.rcsb.org\u002Fdownload\u002F1ALU.cif\"\n```\n\n### Using Python\n```python\nfrom Bio.PDB import PDBList\n\npdbl = PDBList()\npdbl.retrieve_pdb_file(\"1ABC\", pdir=\"structures\u002F\", file_format=\"pdb\")\n```\n\n### Using RCSB API\n```python\nimport requests\n\ndef fetch_pdb(pdb_id: str, format: str = \"pdb\") -> str:\n    \"\"\"Fetch structure from RCSB PDB.\"\"\"\n    url = f\"https:\u002F\u002Ffiles.rcsb.org\u002Fdownload\u002F{pdb_id}.{format}\"\n    response = requests.get(url)\n    response.raise_for_status()\n    return response.text\n\ndef fetch_fasta(pdb_id: str) -> str:\n    \"\"\"Fetch sequence in FASTA format.\"\"\"\n    url = f\"https:\u002F\u002Fwww.rcsb.org\u002Ffasta\u002Fentry\u002F{pdb_id}\"\n    return requests.get(url).text\n\n# Example usage\npdb_content = fetch_pdb(\"1ALU\")\nwith open(\"1ALU.pdb\", \"w\") as f:\n    f.write(pdb_content)\n```\n\n## Structure Preparation\n\n### Selecting Chains\n```python\nfrom Bio.PDB import PDBParser, PDBIO, Select\n\nclass ChainSelect(Select):\n    def __init__(self, chain_id):\n        self.chain_id = chain_id\n\n    def accept_chain(self, chain):\n        return chain.id == self.chain_id\n\n# Extract chain A\nparser = PDBParser()\nstructure = parser.get_structure(\"protein\", \"1abc.pdb\")\nio = PDBIO()\nio.set_structure(structure)\nio.save(\"chain_A.pdb\", ChainSelect(\"A\"))\n```\n\n### Trimming to Binding Region\n```python\ndef trim_around_residues(pdb_file, center_residues, buffer=10.0):\n    \"\"\"Trim structure to region around specified residues.\"\"\"\n    parser = PDBParser()\n    structure = parser.get_structure(\"protein\", pdb_file)\n\n    # Get center coordinates\n    center_coords = []\n    for res in structure.get_residues():\n        if res.id[1] in center_residues:\n            center_coords.extend([a.coord for a in res.get_atoms()])\n\n    center = np.mean(center_coords, axis=0)\n\n    # Keep residues within buffer\n    class RegionSelect(Select):\n        def accept_residue(self, res):\n            for atom in res.get_atoms():\n                if np.linalg.norm(atom.coord - center) \u003C buffer:\n                    return True\n            return False\n\n    io = PDBIO()\n    io.set_structure(structure)\n    io.save(\"trimmed.pdb\", RegionSelect())\n```\n\n## Searching PDB\n\n### RCSB Search API\n```python\nimport requests\n\nquery = {\n    \"query\": {\n        \"type\": \"terminal\",\n        \"service\": \"full_text\",\n        \"parameters\": {\n            \"value\": \"EGFR kinase domain\"\n        }\n    },\n    \"return_type\": \"entry\"\n}\n\nresponse = requests.post(\n    \"https:\u002F\u002Fsearch.rcsb.org\u002Frcsbsearch\u002Fv2\u002Fquery\",\n    json=query\n)\nresults = response.json()\n```\n\n### By Sequence Similarity\n```python\nquery = {\n    \"query\": {\n        \"type\": \"terminal\",\n        \"service\": \"sequence\",\n        \"parameters\": {\n            \"value\": \"MKTAYIAKQRQISFVK...\",\n            \"evalue_cutoff\": 1e-10,\n            \"identity_cutoff\": 0.9\n        }\n    }\n}\n```\n\n## Structure Analysis\n\n### Get Chain Info\n```python\ndef get_structure_info(pdb_file):\n    parser = PDBParser(QUIET=True)\n    structure = parser.get_structure(\"protein\", pdb_file)\n\n    info = {\n        \"chains\": [],\n        \"total_residues\": 0\n    }\n\n    for model in structure:\n        for chain in model:\n            residues = list(chain.get_residues())\n            info[\"chains\"].append({\n                \"id\": chain.id,\n                \"length\": len(residues),\n                \"first_res\": residues[0].id[1],\n                \"last_res\": residues[-1].id[1]\n            })\n            info[\"total_residues\"] += len(residues)\n\n    return info\n```\n\n### Find Interface Residues\n```python\ndef find_interface_residues(pdb_file, chain_a, chain_b, distance=4.0):\n    \"\"\"Find residues at interface between two chains.\"\"\"\n    parser = PDBParser(QUIET=True)\n    structure = parser.get_structure(\"complex\", pdb_file)\n\n    interface_a = set()\n    interface_b = set()\n\n    for res_a in structure[0][chain_a].get_residues():\n        for res_b in structure[0][chain_b].get_residues():\n            for atom_a in res_a.get_atoms():\n                for atom_b in res_b.get_atoms():\n                    if atom_a - atom_b \u003C distance:\n                        interface_a.add(res_a.id[1])\n                        interface_b.add(res_b.id[1])\n\n    return interface_a, interface_b\n```\n\n## Common Tasks for Binder Design\n\n### Target Preparation Checklist\n1. Download structure: `curl -o target.pdb \"https:\u002F\u002Ffiles.rcsb.org\u002Fdownload\u002FXXXX.pdb\"`\n2. Identify target chain\n3. Remove waters and ligands (if needed)\n4. Trim to binding region + buffer\n5. Identify potential hotspots\n6. Renumber if needed\n\n## Troubleshooting\n\n**Structure not found**: Check PDB ID format (4 characters)\n**Multiple models**: Select first model for design\n**Missing residues**: Check for gaps in structure\n\n---\n\n**Next**: Use structure with `boltzgen` (recommended) or `rfdiffusion` for design.\n","# PDB Database Access\n\n**Note**: This skill uses the RCSB PDB web API directly. No Modal deployment needed - all operations run locally via HTTP requests.\n\n## Fetching Structures\n\n### By PDB ID\n```bash\n# Download PDB file\ncurl -o 1alu.pdb \"https:\u002F\u002Ffiles.rcsb.org\u002Fdownload\u002F1ALU.pdb\"\n\n# Download mmCIF\ncurl -o 1alu.cif \"https:\u002F\u002Ffiles.rcsb.org\u002Fdownload\u002F1ALU.cif\"\n```\n\n### Using Python\n```python\nfrom Bio.PDB import PDBList\n\npdbl = PDBList()\npdbl.retrieve_pdb_file(\"1ABC\", pdir=\"structures\u002F\", file_format=\"pdb\")\n```\n\n### Using RCSB API\n```python\nimport requests\n\ndef fetch_pdb(pdb_id: str, format: str = \"pdb\") -> str:\n    \"\"\"Fetch structure from RCSB PDB.\"\"\"\n    url = f\"https:\u002F\u002Ffiles.rcsb.org\u002Fdownload\u002F{pdb_id}.{format}\"\n    response = requests.get(url)\n    response.raise_for_status()\n    return response.text\n\ndef fetch_fasta(pdb_id: str) -> str:\n    \"\"\"Fetch sequence in FASTA format.\"\"\"\n    url = f\"https:\u002F\u002Fwww.rcsb.org\u002Ffasta\u002Fentry\u002F{pdb_id}\"\n    return requests.get(url).text\n\n# Example usage\npdb_content = fetch_pdb(\"1ALU\")\nwith open(\"1ALU.pdb\", \"w\") as f:\n    f.write(pdb_content)\n```\n\n## Structure Preparation\n\n### Selecting Chains\n```python\nfrom Bio.PDB import PDBParser, PDBIO, Select\n\nclass ChainSelect(Select):\n    def __init__(self, chain_id):\n        self.chain_id = chain_id\n\n    def accept_chain(self, chain):\n        return chain.id == self.chain_id\n\n# Extract chain A\nparser = PDBParser()\nstructure = parser.get_structure(\"protein\", \"1abc.pdb\")\nio = PDBIO()\nio.set_structure(structure)\nio.save(\"chain_A.pdb\", ChainSelect(\"A\"))\n```\n\n### Trimming to Binding Region\n```python\ndef trim_around_residues(pdb_file, center_residues, buffer=10.0):\n    \"\"\"Trim structure to region around specified residues.\"\"\"\n    parser = PDBParser()\n    structure = parser.get_structure(\"protein\", pdb_file)\n\n    # Get center coordinates\n    center_coords = []\n    for res in structure.get_residues():\n        if res.id[1] in center_residues:\n            center_coords.extend([a.coord for a in res.get_atoms()])\n\n    center = np.mean(center_coords, axis=0)\n\n    # Keep residues within buffer\n    class RegionSelect(Select):\n        def accept_residue(self, res):\n            for atom in res.get_atoms():\n                if np.linalg.norm(atom.coord - center) \u003C buffer:\n                    return True\n            return False\n\n    io = PDBIO()\n    io.set_structure(structure)\n    io.save(\"trimmed.pdb\", RegionSelect())\n```\n\n## Searching PDB\n\n### RCSB Search API\n```python\nimport requests\n\nquery = {\n    \"query\": {\n        \"type\": \"terminal\",\n        \"service\": \"full_text\",\n        \"parameters\": {\n            \"value\": \"EGFR kinase domain\"\n        }\n    },\n    \"return_type\": \"entry\"\n}\n\nresponse = requests.post(\n    \"https:\u002F\u002Fsearch.rcsb.org\u002Frcsbsearch\u002Fv2\u002Fquery\",\n    json=query\n)\nresults = response.json()\n```\n\n### By Sequence Similarity\n```python\nquery = {\n    \"query\": {\n        \"type\": \"terminal\",\n        \"service\": \"sequence\",\n        \"parameters\": {\n            \"value\": \"MKTAYIAKQRQISFVK...\",\n            \"evalue_cutoff\": 1e-10,\n            \"identity_cutoff\": 0.9\n        }\n    }\n}\n```\n\n## Structure Analysis\n\n### Get Chain Info\n```python\ndef get_structure_info(pdb_file):\n    parser = PDBParser(QUIET=True)\n    structure = parser.get_structure(\"protein\", pdb_file)\n\n    info = {\n        \"chains\": [],\n        \"total_residues\": 0\n    }\n\n    for model in structure:\n        for chain in model:\n            residues = list(chain.get_residues())\n            info[\"chains\"].append({\n                \"id\": chain.id,\n                \"length\": len(residues),\n                \"first_res\": residues[0].id[1],\n                \"last_res\": residues[-1].id[1]\n            })\n            info[\"total_residues\"] += len(residues)\n\n    return info\n```\n\n### Find Interface Residues\n```python\ndef find_interface_residues(pdb_file, chain_a, chain_b, distance=4.0):\n    \"\"\"Find residues at interface between two chains.\"\"\"\n    parser = PDBParser(QUIET=True)\n    structure = parser.get_structure(\"complex\", pdb_file)\n\n    interface_a = set()\n    interface_b = set()\n\n    for res_a in structure[0][chain_a].get_residues():\n        for res_b in structure[0][chain_b].get_residues():\n            for atom_a in res_a.get_atoms():\n                for atom_b in res_b.get_atoms():\n                    if atom_a - atom_b \u003C distance:\n                        interface_a.add(res_a.id[1])\n                        interface_b.add(res_b.id[1])\n\n    return interface_a, interface_b\n```\n\n## Common Tasks for Binder Design\n\n### Target Preparation Checklist\n1. Download structure: `curl -o target.pdb \"https:\u002F\u002Ffiles.rcsb.org\u002Fdownload\u002FXXXX.pdb\"`\n2. Identify target chain\n3. Remove waters and ligands (if needed)\n4. Trim to binding region + buffer\n5. Identify potential hotspots\n6. Renumber if needed\n\n## Troubleshooting\n\n**Structure not found**: Check PDB ID format (4 characters)\n**Multiple models**: Select first model for design\n**Missing residues**: Check for gaps in structure\n\n---\n\n**Next**: Use structure with `boltzgen` (recommended) or `rfdiffusion` for design.\n",{"name":5,"tags":49,"license":15,"category":50,"description":51},[41,32,27],"utilities","Fetch and analyze protein structures from RCSB PDB. Use this skill when: (1) Need to download a structure by PDB ID, (2) Search for similar structures, (3) Prepare target for binder design, (4) Extract specific chains or domains, (5) Get structure metadata.\nFor sequence lookup, use uniprot. For binder design workflow, use binder-design.\n","main","d3998984163a67a891ee8397e35adf79b14e872d","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical","https:\u002F\u002Fgithub.com\u002Fhuamu668","2026-03-12 11:49:42",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add huamu668\u002Fclawhub-openclaw-medical --skill pdb",{"tool":63,"command":64},"bunx","bunx skills add huamu668\u002Fclawhub-openclaw-medical --skill pdb",{"tool":66,"command":67},"pnpm","pnpm dlx skills add huamu668\u002Fclawhub-openclaw-medical --skill pdb","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fpdb\u002FSKILL.md",true,[71,77,81,85,89,93,99,105,109,113,117,121,125,129,133,137,141,145,149,153,157,161,165],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"extract_pdf\u002F__init__.py","SCRIPT","脚本",246,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fextract_pdf\u002F__init__.py",{"path":78,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":79,"sourceHtmlUrl":80},"extract_pdf\u002Fcascade\u002F__init__.py",253,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fextract_pdf\u002Fcascade\u002F__init__.py",{"path":82,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":83,"sourceHtmlUrl":84},"extract_pdf\u002Fcascade\u002Fwiring.py",17224,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fextract_pdf\u002Fcascade\u002Fwiring.py",{"path":86,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":87,"sourceHtmlUrl":88},"extract_pdf\u002Fmain.py",7786,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fextract_pdf\u002Fmain.py",{"path":90,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":91,"sourceHtmlUrl":92},"extract_pdf\u002Fpipeline_adapter.py",13664,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fextract_pdf\u002Fpipeline_adapter.py",{"path":94,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":97,"sourceHtmlUrl":98},"policy.yaml","REFERENCE","参考文档",1286,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fpolicy.yaml",{"path":100,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":103,"sourceHtmlUrl":104},"pyproject.toml","OTHER","其他",284,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fpyproject.toml",{"path":106,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":107,"sourceHtmlUrl":108},"run.sh",3268,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Frun.sh",{"path":110,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":111,"sourceHtmlUrl":112},"sanity.sh",3976,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fsanity.sh",{"path":114,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":115,"sourceHtmlUrl":116},"viewer\u002Findex.html",367,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fviewer\u002Findex.html",{"path":118,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":119,"sourceHtmlUrl":120},"viewer\u002Frun.sh",24,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fviewer\u002Frun.sh",{"path":122,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":123,"sourceHtmlUrl":124},"viewer\u002Fsrc\u002FApp.tsx",2932,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fviewer\u002Fsrc\u002FApp.tsx",{"path":126,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":127,"sourceHtmlUrl":128},"viewer\u002Fsrc\u002Fcomponents\u002FTaxonomyChip.tsx",1569,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fviewer\u002Fsrc\u002Fcomponents\u002FTaxonomyChip.tsx",{"path":130,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":131,"sourceHtmlUrl":132},"viewer\u002Fsrc\u002Findex.css",23,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fviewer\u002Fsrc\u002Findex.css",{"path":134,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":135,"sourceHtmlUrl":136},"viewer\u002Fsrc\u002Floader.ts",2383,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fviewer\u002Fsrc\u002Floader.ts",{"path":138,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":139,"sourceHtmlUrl":140},"viewer\u002Fsrc\u002Fmain.tsx",230,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fviewer\u002Fsrc\u002Fmain.tsx",{"path":142,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":143,"sourceHtmlUrl":144},"viewer\u002Fsrc\u002Ftypes.ts",2217,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fviewer\u002Fsrc\u002Ftypes.ts",{"path":146,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":147,"sourceHtmlUrl":148},"viewer\u002Fsrc\u002Ftypes\u002Fd3-force-shim.d.ts",1989,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fviewer\u002Fsrc\u002Ftypes\u002Fd3-force-shim.d.ts",{"path":150,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":151,"sourceHtmlUrl":152},"viewer\u002Fsrc\u002Fviews\u002FBatchView.tsx",17790,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fviewer\u002Fsrc\u002Fviews\u002FBatchView.tsx",{"path":154,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":155,"sourceHtmlUrl":156},"viewer\u002Fsrc\u002Fviews\u002FCascadeView.tsx",13040,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fviewer\u002Fsrc\u002Fviews\u002FCascadeView.tsx",{"path":158,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":159,"sourceHtmlUrl":160},"viewer\u002Fsrc\u002Fviews\u002FCompareView.tsx",17849,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fviewer\u002Fsrc\u002Fviews\u002FCompareView.tsx",{"path":162,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":163,"sourceHtmlUrl":164},"viewer\u002Fsrc\u002Fviews\u002FDocumentView.tsx",12018,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fviewer\u002Fsrc\u002Fviews\u002FDocumentView.tsx",{"path":166,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":167,"sourceHtmlUrl":168},"viewer\u002Fvite.config.ts",694,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fextract-pdf\u002Fviewer\u002Fvite.config.ts",[170,190,218,238,252,278],{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":44},"01M6DR3JGAEX5G5FR7TK3D8NS8","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fzarr-python\u002FSKILL.md",[],[177,178,179,180,181,182,183,184,185,186,187,188,189],"python","zarr python","storage","scientific computing","numpy","arrays","pipelines","parallel","dask","cloud","gcs","s3","integration",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":199,"publishedAt":44},"01M6DR101MEDE5XT2ZZ5VBEAA5","vaex","Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV\u002FHDF5\u002FArrow\u002FParquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fvaex\u002FSKILL.md",[196],{"categoryNo":197,"categoryName":198,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",[192,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,33,216,217],"machine learning","in memory","learning","csv","visualization","create","core","ml","big data","memory","visualizations","fit","statistics","do","build","files","operations","work",{"skillNo":219,"name":220,"nameZh":6,"description":221,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":222,"categories":223,"keywords":224,"publishedAt":44},"01M6DQVMB0GBKF2W44FKXVD1P7","torch-geometric","Graph Neural Networks (PyG). Node\u002Fgraph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Ftorch-geometric\u002FSKILL.md",[],[225,202,226,227,228,229,230,231,232,233,234,235,236,237],"torch geometric","node","Neural","link","gat","molecular","graphs","deep","networks","graph","neural networks","deep learning","classification",{"skillNo":239,"name":240,"nameZh":6,"description":241,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":242,"categories":243,"keywords":244,"publishedAt":44},"01M6DQH2GZPZKEQ140GRCJ9746","tiledbvcf","Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF\u002FBCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Ftiledbvcf\u002FSKILL.md",[],[240,245,246,247,248,249,250,184,251,179],"data","genomics","sample","queries","ingestion","export","capabilities",{"skillNo":253,"name":254,"nameZh":6,"description":255,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":256,"categories":257,"keywords":264,"publishedAt":44},"01M6DQD9G958EM6NHJ994D0SK1","solublempnn","Solubility-optimized protein sequence design using SolubleMPNN. Use this skill when: (1) Designing for E. coli expression, (2) Optimizing solubility of designed proteins, (3) Reducing aggregation propensity, (4) Need high-yield expression, (5) Avoiding inclusion body formation.\nFor standard design, use proteinmpnn. For ligand-aware design, use ligandmpnn.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fsolublempnn\u002FSKILL.md",[258,259],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":260,"categoryName":261,"taxonomyType":262,"taxonomyTypeDesc":263},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[254,265,266,33,267,268,269,35,270,271,272,273,274,275,276,277],"inclusion","yield","modal","Tools","aggregation","proteins","solubility","proteinmpnn","ligandmpnn","ligand-aware","inverse-folding","expression","sequence-design",{"skillNo":279,"name":280,"nameZh":6,"description":281,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":282,"licenseFileUrl":6,"sourceHtmlUrl":283,"categories":284,"keywords":285,"publishedAt":44},"01M6DQ8W91A93MGGCEEW949HBC","scvelo","RNA velocity analysis with scVelo. Estimate cell state transitions from unspliced\u002Fspliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy\u002FscVI-tools for trajectory inference.","BSD-3-Clause","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fscvelo\u002FSKILL.md",[],[280,286,287,288,289,290,291,292,293,294,295,268,245,296,297],"RNA","single-cell","infer","cell","transitions","time","compute","velocity","scanpy","analysis","state","inference"]