[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71G4QCJDMHD5AM7VHVM1HB2":3,"skill-same:01M71G4QCJDMHD5AM7VHVM1HB2":75},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":48,"install":49,"resources":62},"01M71G4QCJDMHD5AM7VHVM1HB2","chembl-database",null,"Query ChEMBL's bioactive molecules and drug discovery data. Search compounds by structure\u002Fproperties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry.","JSGforever\u002Fskillguard","JSGforever","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85541948?v=4","01M71FQD3E132VMR5F4TAYX3YS","01M71FQD4DYW0XJ4XQ4YQH75Y9",2,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fchembl-database\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36],"chembl database","database","chembl","search","query","structure","data","for","discovery","sar","properties","find","drug discovery","Molecules","2026-11-10 10:12:30",false,"---\nname: chembl-database\ndescription: \"Query ChEMBL's bioactive molecules and drug discovery data. Search compounds by structure\u002Fproperties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry.\"\n---\n\n# ChEMBL Database\n\n## Overview\n\nChEMBL is a manually curated database of bioactive molecules maintained by the European Bioinformatics Institute (EBI), containing over 2 million compounds, 19 million bioactivity measurements, 13,000+ drug targets, and data on approved drugs and clinical candidates. Access and query this data programmatically using the ChEMBL Python client for drug discovery and medicinal chemistry research.\n\n## When to Use This Skill\n\nThis skill should be used when:\n\n- **Compound searches**: Finding molecules by name, structure, or properties\n- **Target information**: Retrieving data about proteins, enzymes, or biological targets\n- **Bioactivity data**: Querying IC50, Ki, EC50, or other activity measurements\n- **Drug information**: Looking up approved drugs, mechanisms, or indications\n- **Structure searches**: Performing similarity or substructure searches\n- **Cheminformatics**: Analyzing molecular properties and drug-likeness\n- **Target-ligand relationships**: Exploring compound-target interactions\n- **Drug discovery**: Identifying inhibitors, agonists, or bioactive molecules\n\n## Installation and Setup\n\n### Python Client\n\nThe ChEMBL Python client is required for programmatic access:\n\n```bash\nuv pip install chembl_webresource_client\n```\n\n### Basic Usage Pattern\n\n```python\nfrom chembl_webresource_client.new_client import new_client\n\n# Access different endpoints\nmolecule = new_client.molecule\ntarget = new_client.target\nactivity = new_client.activity\ndrug = new_client.drug\n```\n\n## Core Capabilities\n\n### 1. Molecule Queries\n\n**Retrieve by ChEMBL ID:**\n```python\nmolecule = new_client.molecule\naspirin = molecule.get('CHEMBL25')\n```\n\n**Search by name:**\n```python\nresults = molecule.filter(pref_name__icontains='aspirin')\n```\n\n**Filter by properties:**\n```python\n# Find small molecules (MW \u003C= 500) with favorable LogP\nresults = molecule.filter(\n    molecule_properties__mw_freebase__lte=500,\n    molecule_properties__alogp__lte=5\n)\n```\n\n### 2. Target Queries\n\n**Retrieve target information:**\n```python\ntarget = new_client.target\negfr = target.get('CHEMBL203')\n```\n\n**Search for specific target types:**\n```python\n# Find all kinase targets\nkinases = target.filter(\n    target_type='SINGLE PROTEIN',\n    pref_name__icontains='kinase'\n)\n```\n\n### 3. Bioactivity Data\n\n**Query activities for a target:**\n```python\nactivity = new_client.activity\n# Find potent EGFR inhibitors\nresults = activity.filter(\n    target_chembl_id='CHEMBL203',\n    standard_type='IC50',\n    standard_value__lte=100,\n    standard_units='nM'\n)\n```\n\n**Get all activities for a compound:**\n```python\ncompound_activities = activity.filter(\n    molecule_chembl_id='CHEMBL25',\n    pchembl_value__isnull=False\n)\n```\n\n### 4. Structure-Based Searches\n\n**Similarity search:**\n```python\nsimilarity = new_client.similarity\n# Find compounds similar to aspirin\nsimilar = similarity.filter(\n    smiles='CC(=O)Oc1ccccc1C(=O)O',\n    similarity=85  # 85% similarity threshold\n)\n```\n\n**Substructure search:**\n```python\nsubstructure = new_client.substructure\n# Find compounds containing benzene ring\nresults = substructure.filter(smiles='c1ccccc1')\n```\n\n### 5. Drug Information\n\n**Retrieve drug data:**\n```python\ndrug = new_client.drug\ndrug_info = drug.get('CHEMBL25')\n```\n\n**Get mechanisms of action:**\n```python\nmechanism = new_client.mechanism\nmechanisms = mechanism.filter(molecule_chembl_id='CHEMBL25')\n```\n\n**Query drug indications:**\n```python\ndrug_indication = new_client.drug_indication\nindications = drug_indication.filter(molecule_chembl_id='CHEMBL25')\n```\n\n## Query Workflow\n\n### Workflow 1: Finding Inhibitors for a Target\n\n1. **Identify the target** by searching by name:\n   ```python\n   targets = new_client.target.filter(pref_name__icontains='EGFR')\n   target_id = targets[0]['target_chembl_id']\n   ```\n\n2. **Query bioactivity data** for that target:\n   ```python\n   activities = new_client.activity.filter(\n       target_chembl_id=target_id,\n       standard_type='IC50',\n       standard_value__lte=100\n   )\n   ```\n\n3. **Extract compound IDs** and retrieve details:\n   ```python\n   compound_ids = [act['molecule_chembl_id'] for act in activities]\n   compounds = [new_client.molecule.get(cid) for cid in compound_ids]\n   ```\n\n### Workflow 2: Analyzing a Known Drug\n\n1. **Get drug information**:\n   ```python\n   drug_info = new_client.drug.get('CHEMBL1234')\n   ```\n\n2. **Retrieve mechanisms**:\n   ```python\n   mechanisms = new_client.mechanism.filter(molecule_chembl_id='CHEMBL1234')\n   ```\n\n3. **Find all bioactivities**:\n   ```python\n   activities = new_client.activity.filter(molecule_chembl_id='CHEMBL1234')\n   ```\n\n### Workflow 3: Structure-Activity Relationship (SAR) Study\n\n1. **Find similar compounds**:\n   ```python\n   similar = new_client.similarity.filter(smiles='query_smiles', similarity=80)\n   ```\n\n2. **Get activities for each compound**:\n   ```python\n   for compound in similar:\n       activities = new_client.activity.filter(\n           molecule_chembl_id=compound['molecule_chembl_id']\n       )\n   ```\n\n3. **Analyze property-activity relationships** using molecular properties from results.\n\n## Filter Operators\n\nChEMBL supports Django-style query filters:\n\n- `__exact` - Exact match\n- `__iexact` - Case-insensitive exact match\n- `__contains` \u002F `__icontains` - Substring matching\n- `__startswith` \u002F `__endswith` - Prefix\u002Fsuffix matching\n- `__gt`, `__gte`, `__lt`, `__lte` - Numeric comparisons\n- `__range` - Value in range\n- `__in` - Value in list\n- `__isnull` - Null\u002Fnot null check\n\n## Data Export and Analysis\n\nConvert results to pandas DataFrame for analysis:\n\n```python\nimport pandas as pd\n\nactivities = new_client.activity.filter(target_chembl_id='CHEMBL203')\ndf = pd.DataFrame(list(activities))\n\n# Analyze results\nprint(df['standard_value'].describe())\nprint(df.groupby('standard_type').size())\n```\n\n## Performance Optimization\n\n### Caching\n\nThe client automatically caches results for 24 hours. Configure caching:\n\n```python\nfrom chembl_webresource_client.settings import Settings\n\n# Disable caching\nSettings.Instance().CACHING = False\n\n# Adjust cache expiration (seconds)\nSettings.Instance().CACHE_EXPIRE = 86400\n```\n\n### Lazy Evaluation\n\nQueries execute only when data is accessed. Convert to list to force execution:\n\n```python\n# Query is not executed yet\nresults = molecule.filter(pref_name__icontains='aspirin')\n\n# Force execution\nresults_list = list(results)\n```\n\n### Pagination\n\nResults are paginated automatically. Iterate through all results:\n\n```python\nfor activity in new_client.activity.filter(target_chembl_id='CHEMBL203'):\n    # Process each activity\n    print(activity['molecule_chembl_id'])\n```\n\n## Common Use Cases\n\n### Find Kinase Inhibitors\n\n```python\n# Identify kinase targets\nkinases = new_client.target.filter(\n    target_type='SINGLE PROTEIN',\n    pref_name__icontains='kinase'\n)\n\n# Get potent inhibitors\nfor kinase in kinases[:5]:  # First 5 kinases\n    activities = new_client.activity.filter(\n        target_chembl_id=kinase['target_chembl_id'],\n        standard_type='IC50',\n        standard_value__lte=50\n    )\n```\n\n### Explore Drug Repurposing\n\n```python\n# Get approved drugs\ndrugs = new_client.drug.filter()\n\n# For each drug, find all targets\nfor drug in drugs[:10]:\n    mechanisms = new_client.mechanism.filter(\n        molecule_chembl_id=drug['molecule_chembl_id']\n    )\n```\n\n### Virtual Screening\n\n```python\n# Find compounds with desired properties\ncandidates = new_client.molecule.filter(\n    molecule_properties__mw_freebase__range=[300, 500],\n    molecule_properties__alogp__lte=5,\n    molecule_properties__hba__lte=10,\n    molecule_properties__hbd__lte=5\n)\n```\n\n## Resources\n\n### scripts\u002Fexample_queries.py\n\nReady-to-use Python functions demonstrating common ChEMBL query patterns:\n\n- `get_molecule_info()` - Retrieve molecule details by ID\n- `search_molecules_by_name()` - Name-based molecule search\n- `find_molecules_by_properties()` - Property-based filtering\n- `get_bioactivity_data()` - Query bioactivities for targets\n- `find_similar_compounds()` - Similarity searching\n- `substructure_search()` - Substructure matching\n- `get_drug_info()` - Retrieve drug information\n- `find_kinase_inhibitors()` - Specialized kinase inhibitor search\n- `export_to_dataframe()` - Convert results to pandas DataFrame\n\nConsult this script for implementation details and usage examples.\n\n### references\u002Fapi_reference.md\n\nComprehensive API documentation including:\n\n- Complete endpoint listing (molecule, target, activity, assay, drug, etc.)\n- All filter operators and query patterns\n- Molecular properties and bioactivity fields\n- Advanced query examples\n- Configuration and performance tuning\n- Error handling and rate limiting\n\nRefer to this document when detailed API information is needed or when troubleshooting queries.\n\n## Important Notes\n\n### Data Reliability\n\n- ChEMBL data is manually curated but may contain inconsistencies\n- Always check `data_validity_comment` field in activity records\n- Be aware of `potential_duplicate` flags\n\n### Units and Standards\n\n- Bioactivity values use standard units (nM, uM, etc.)\n- `pchembl_value` provides normalized activity (-log scale)\n- Check `standard_type` to understand measurement type (IC50, Ki, EC50, etc.)\n\n### Rate Limiting\n\n- Respect ChEMBL's fair usage policies\n- Use caching to minimize repeated requests\n- Consider bulk downloads for large datasets\n- Avoid hammering the API with rapid consecutive requests\n\n### Chemical Structure Formats\n\n- SMILES strings are the primary structure format\n- InChI keys available for compounds\n- SVG images can be generated via the image endpoint\n\n## Additional Resources\n\n- ChEMBL website: https:\u002F\u002Fwww.ebi.ac.uk\u002Fchembl\u002F\n- API documentation: https:\u002F\u002Fwww.ebi.ac.uk\u002Fchembl\u002Fapi\u002Fdata\u002Fdocs\n- Python client GitHub: https:\u002F\u002Fgithub.com\u002Fchembl\u002Fchembl_webresource_client\n- Interface documentation: https:\u002F\u002Fchembl.gitbook.io\u002Fchembl-interface-documentation\u002F\n- Example notebooks: https:\u002F\u002Fgithub.com\u002Fchembl\u002Fnotebooks\n","# ChEMBL Database\n\n## Overview\n\nChEMBL is a manually curated database of bioactive molecules maintained by the European Bioinformatics Institute (EBI), containing over 2 million compounds, 19 million bioactivity measurements, 13,000+ drug targets, and data on approved drugs and clinical candidates. Access and query this data programmatically using the ChEMBL Python client for drug discovery and medicinal chemistry research.\n\n## When to Use This Skill\n\nThis skill should be used when:\n\n- **Compound searches**: Finding molecules by name, structure, or properties\n- **Target information**: Retrieving data about proteins, enzymes, or biological targets\n- **Bioactivity data**: Querying IC50, Ki, EC50, or other activity measurements\n- **Drug information**: Looking up approved drugs, mechanisms, or indications\n- **Structure searches**: Performing similarity or substructure searches\n- **Cheminformatics**: Analyzing molecular properties and drug-likeness\n- **Target-ligand relationships**: Exploring compound-target interactions\n- **Drug discovery**: Identifying inhibitors, agonists, or bioactive molecules\n\n## Installation and Setup\n\n### Python Client\n\nThe ChEMBL Python client is required for programmatic access:\n\n```bash\nuv pip install chembl_webresource_client\n```\n\n### Basic Usage Pattern\n\n```python\nfrom chembl_webresource_client.new_client import new_client\n\n# Access different endpoints\nmolecule = new_client.molecule\ntarget = new_client.target\nactivity = new_client.activity\ndrug = new_client.drug\n```\n\n## Core Capabilities\n\n### 1. Molecule Queries\n\n**Retrieve by ChEMBL ID:**\n```python\nmolecule = new_client.molecule\naspirin = molecule.get('CHEMBL25')\n```\n\n**Search by name:**\n```python\nresults = molecule.filter(pref_name__icontains='aspirin')\n```\n\n**Filter by properties:**\n```python\n# Find small molecules (MW \u003C= 500) with favorable LogP\nresults = molecule.filter(\n    molecule_properties__mw_freebase__lte=500,\n    molecule_properties__alogp__lte=5\n)\n```\n\n### 2. Target Queries\n\n**Retrieve target information:**\n```python\ntarget = new_client.target\negfr = target.get('CHEMBL203')\n```\n\n**Search for specific target types:**\n```python\n# Find all kinase targets\nkinases = target.filter(\n    target_type='SINGLE PROTEIN',\n    pref_name__icontains='kinase'\n)\n```\n\n### 3. Bioactivity Data\n\n**Query activities for a target:**\n```python\nactivity = new_client.activity\n# Find potent EGFR inhibitors\nresults = activity.filter(\n    target_chembl_id='CHEMBL203',\n    standard_type='IC50',\n    standard_value__lte=100,\n    standard_units='nM'\n)\n```\n\n**Get all activities for a compound:**\n```python\ncompound_activities = activity.filter(\n    molecule_chembl_id='CHEMBL25',\n    pchembl_value__isnull=False\n)\n```\n\n### 4. Structure-Based Searches\n\n**Similarity search:**\n```python\nsimilarity = new_client.similarity\n# Find compounds similar to aspirin\nsimilar = similarity.filter(\n    smiles='CC(=O)Oc1ccccc1C(=O)O',\n    similarity=85  # 85% similarity threshold\n)\n```\n\n**Substructure search:**\n```python\nsubstructure = new_client.substructure\n# Find compounds containing benzene ring\nresults = substructure.filter(smiles='c1ccccc1')\n```\n\n### 5. Drug Information\n\n**Retrieve drug data:**\n```python\ndrug = new_client.drug\ndrug_info = drug.get('CHEMBL25')\n```\n\n**Get mechanisms of action:**\n```python\nmechanism = new_client.mechanism\nmechanisms = mechanism.filter(molecule_chembl_id='CHEMBL25')\n```\n\n**Query drug indications:**\n```python\ndrug_indication = new_client.drug_indication\nindications = drug_indication.filter(molecule_chembl_id='CHEMBL25')\n```\n\n## Query Workflow\n\n### Workflow 1: Finding Inhibitors for a Target\n\n1. **Identify the target** by searching by name:\n   ```python\n   targets = new_client.target.filter(pref_name__icontains='EGFR')\n   target_id = targets[0]['target_chembl_id']\n   ```\n\n2. **Query bioactivity data** for that target:\n   ```python\n   activities = new_client.activity.filter(\n       target_chembl_id=target_id,\n       standard_type='IC50',\n       standard_value__lte=100\n   )\n   ```\n\n3. **Extract compound IDs** and retrieve details:\n   ```python\n   compound_ids = [act['molecule_chembl_id'] for act in activities]\n   compounds = [new_client.molecule.get(cid) for cid in compound_ids]\n   ```\n\n### Workflow 2: Analyzing a Known Drug\n\n1. **Get drug information**:\n   ```python\n   drug_info = new_client.drug.get('CHEMBL1234')\n   ```\n\n2. **Retrieve mechanisms**:\n   ```python\n   mechanisms = new_client.mechanism.filter(molecule_chembl_id='CHEMBL1234')\n   ```\n\n3. **Find all bioactivities**:\n   ```python\n   activities = new_client.activity.filter(molecule_chembl_id='CHEMBL1234')\n   ```\n\n### Workflow 3: Structure-Activity Relationship (SAR) Study\n\n1. **Find similar compounds**:\n   ```python\n   similar = new_client.similarity.filter(smiles='query_smiles', similarity=80)\n   ```\n\n2. **Get activities for each compound**:\n   ```python\n   for compound in similar:\n       activities = new_client.activity.filter(\n           molecule_chembl_id=compound['molecule_chembl_id']\n       )\n   ```\n\n3. **Analyze property-activity relationships** using molecular properties from results.\n\n## Filter Operators\n\nChEMBL supports Django-style query filters:\n\n- `__exact` - Exact match\n- `__iexact` - Case-insensitive exact match\n- `__contains` \u002F `__icontains` - Substring matching\n- `__startswith` \u002F `__endswith` - Prefix\u002Fsuffix matching\n- `__gt`, `__gte`, `__lt`, `__lte` - Numeric comparisons\n- `__range` - Value in range\n- `__in` - Value in list\n- `__isnull` - Null\u002Fnot null check\n\n## Data Export and Analysis\n\nConvert results to pandas DataFrame for analysis:\n\n```python\nimport pandas as pd\n\nactivities = new_client.activity.filter(target_chembl_id='CHEMBL203')\ndf = pd.DataFrame(list(activities))\n\n# Analyze results\nprint(df['standard_value'].describe())\nprint(df.groupby('standard_type').size())\n```\n\n## Performance Optimization\n\n### Caching\n\nThe client automatically caches results for 24 hours. Configure caching:\n\n```python\nfrom chembl_webresource_client.settings import Settings\n\n# Disable caching\nSettings.Instance().CACHING = False\n\n# Adjust cache expiration (seconds)\nSettings.Instance().CACHE_EXPIRE = 86400\n```\n\n### Lazy Evaluation\n\nQueries execute only when data is accessed. Convert to list to force execution:\n\n```python\n# Query is not executed yet\nresults = molecule.filter(pref_name__icontains='aspirin')\n\n# Force execution\nresults_list = list(results)\n```\n\n### Pagination\n\nResults are paginated automatically. Iterate through all results:\n\n```python\nfor activity in new_client.activity.filter(target_chembl_id='CHEMBL203'):\n    # Process each activity\n    print(activity['molecule_chembl_id'])\n```\n\n## Common Use Cases\n\n### Find Kinase Inhibitors\n\n```python\n# Identify kinase targets\nkinases = new_client.target.filter(\n    target_type='SINGLE PROTEIN',\n    pref_name__icontains='kinase'\n)\n\n# Get potent inhibitors\nfor kinase in kinases[:5]:  # First 5 kinases\n    activities = new_client.activity.filter(\n        target_chembl_id=kinase['target_chembl_id'],\n        standard_type='IC50',\n        standard_value__lte=50\n    )\n```\n\n### Explore Drug Repurposing\n\n```python\n# Get approved drugs\ndrugs = new_client.drug.filter()\n\n# For each drug, find all targets\nfor drug in drugs[:10]:\n    mechanisms = new_client.mechanism.filter(\n        molecule_chembl_id=drug['molecule_chembl_id']\n    )\n```\n\n### Virtual Screening\n\n```python\n# Find compounds with desired properties\ncandidates = new_client.molecule.filter(\n    molecule_properties__mw_freebase__range=[300, 500],\n    molecule_properties__alogp__lte=5,\n    molecule_properties__hba__lte=10,\n    molecule_properties__hbd__lte=5\n)\n```\n\n## Resources\n\n### scripts\u002Fexample_queries.py\n\nReady-to-use Python functions demonstrating common ChEMBL query patterns:\n\n- `get_molecule_info()` - Retrieve molecule details by ID\n- `search_molecules_by_name()` - Name-based molecule search\n- `find_molecules_by_properties()` - Property-based filtering\n- `get_bioactivity_data()` - Query bioactivities for targets\n- `find_similar_compounds()` - Similarity searching\n- `substructure_search()` - Substructure matching\n- `get_drug_info()` - Retrieve drug information\n- `find_kinase_inhibitors()` - Specialized kinase inhibitor search\n- `export_to_dataframe()` - Convert results to pandas DataFrame\n\nConsult this script for implementation details and usage examples.\n\n### references\u002Fapi_reference.md\n\nComprehensive API documentation including:\n\n- Complete endpoint listing (molecule, target, activity, assay, drug, etc.)\n- All filter operators and query patterns\n- Molecular properties and bioactivity fields\n- Advanced query examples\n- Configuration and performance tuning\n- Error handling and rate limiting\n\nRefer to this document when detailed API information is needed or when troubleshooting queries.\n\n## Important Notes\n\n### Data Reliability\n\n- ChEMBL data is manually curated but may contain inconsistencies\n- Always check `data_validity_comment` field in activity records\n- Be aware of `potential_duplicate` flags\n\n### Units and Standards\n\n- Bioactivity values use standard units (nM, uM, etc.)\n- `pchembl_value` provides normalized activity (-log scale)\n- Check `standard_type` to understand measurement type (IC50, Ki, EC50, etc.)\n\n### Rate Limiting\n\n- Respect ChEMBL's fair usage policies\n- Use caching to minimize repeated requests\n- Consider bulk downloads for large datasets\n- Avoid hammering the API with rapid consecutive requests\n\n### Chemical Structure Formats\n\n- SMILES strings are the primary structure format\n- InChI keys available for compounds\n- SVG images can be generated via the image endpoint\n\n## Additional Resources\n\n- ChEMBL website: https:\u002F\u002Fwww.ebi.ac.uk\u002Fchembl\u002F\n- API documentation: https:\u002F\u002Fwww.ebi.ac.uk\u002Fchembl\u002Fapi\u002Fdata\u002Fdocs\n- Python client GitHub: https:\u002F\u002Fgithub.com\u002Fchembl\u002Fchembl_webresource_client\n- Interface documentation: https:\u002F\u002Fchembl.gitbook.io\u002Fchembl-interface-documentation\u002F\n- Example notebooks: https:\u002F\u002Fgithub.com\u002Fchembl\u002Fnotebooks\n",{"name":5,"description":7},"main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fchembl-database",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add JSGforever\u002Fskillguard --skill chembl-database",{"tool":55,"command":56},"bunx","bunx skills add JSGforever\u002Fskillguard --skill chembl-database",{"tool":58,"command":59},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill chembl-database","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fchembl-database\u002FSKILL.md",true,[63,69],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fapi_reference.md","REFERENCE","参考文档",6879,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fchembl-database\u002Freferences\u002Fapi_reference.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fexample_queries.py","SCRIPT","脚本",7160,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fchembl-database\u002Fscripts\u002Fexample_queries.py",[76,106,121,148,170,191],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":85,"publishedAt":37},"01M71HY2SNXBA9Q00WZDTZQ31Z","skillguard-codex-scanner","Hybrid deterministic+LLM agent-skill security scanner. Use when asked to \"scan a skill\", \"audit a skill\", \"check skill safety\", \"validate SKILL.md\", \"is this skill safe to install\", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fsrc\u002Fskillguard\u002Fstatic_scanner\u002Fskillguard-codex-scanner\u002FSKILL.md",[82],{"categoryNo":83,"categoryName":84,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","when","review","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":110,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":118,"publishedAt":37},"01M71HY0SPKTT3S27BC2HPAC5M","data-exfiltrator","Analyzes data files","MIT","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Fsmoke-one-skill\u002Fasset1__cisco-ai-defense--data-exfiltrator\u002FSKILL.md",[113],{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[29,119,120],"data exfiltrator","files",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":37},"01M71HXVS9EMN44BGDW215FZ72","real-time-collaboration-engine","Build real-time collaborative editing with WebSockets, OT\u002FCRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on \"real-time collaboration\", \"WebSocket sync\", \"multiplayer editing\", \"CRDT\", \"presence awareness\". NOT for simple chat, request-response APIs, or single-user apps.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--real-time-collaboration-engine\u002FSKILL.md",[],[128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147],"time","real time collaboration engine","real time collaboration","collaboration","engine","real time","Video","reliability","video editing","performance","conflict resolution","presence","access","apps","updates","Bash","activate","optimizer","react","streaming",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":157,"publishedAt":37},"01M71HXP6CTY4KFN0QVMMN0V7J","react-performance-optimizer","Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on \"React performance\", \"slow render\", \"useMemo\", \"bundle size\", \"virtualization\". NOT for backend optimization, non-React frameworks, or premature optimization.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--react-performance-optimizer\u002FSKILL.md",[154],{"categoryNo":155,"categoryName":156,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[137,158,145,146,159,160,161,162,163,164,128,165,166,141,143,167,144,147,168,169],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","code","router","strategies",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":177,"publishedAt":37},"01M71HXH7QXSQB4QTDZ7SP7YXQ","llm-streaming-response-handler","Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI\u002FAnthropic\u002FClaude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on \"LLM streaming\", \"SSE\", \"token stream\", \"chat UI\", \"real-time AI\". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--llm-streaming-response-handler\u002FSKILL.md",[176],{"categoryNo":155,"categoryName":156,"taxonomyType":20,"taxonomyTypeDesc":21},[178,147,179,180,181,182,137,128,183,184,185,143,144,145,186,146,187,188,189,190],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","server","read",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":204,"publishedAt":37},"01M71HXCB0E1YRKYW1Y8T0Y106","github-actions-pipeline-builder","Build production CI\u002FCD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on \"GitHub Actions\", \"CI\u002FCD\", \"workflow\", \"deployment pipeline\", \"automated testing\". NOT for Jenkins\u002FCircleCI, manual deployments, or non-GitHub repositories.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--github-actions-pipeline-builder\u002FSKILL.md",[197,200,203],{"categoryNo":198,"categoryName":199,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":201,"categoryName":202,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":83,"categoryName":84,"taxonomyType":20,"taxonomyTypeDesc":21},[205,206,207,208,209,210,211,135,163,212,213,214,144,169,215,190,216,217,218,219],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","workflows","run","release","write","edit","git"]