[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71G9SP7QKP2B35CM916JY15":3,"skill-same:01M71G9SP7QKP2B35CM916JY15":73},{"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":17,"publishedAt":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":42,"install":43,"resources":56},"01M71G9SP7QKP2B35CM916JY15","medchem",null,"Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.","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\u002Fmedchem\u002FSKILL.md",[],[5,18,19,20,21,22,23,24,25,26,27,28,29,30],"complexity","structural","filters","prioritization","alerts","library","metrics","likeness","for","filtering","Rules","apply","compound","2026-11-10 10:12:30",false,"---\nname: medchem\ndescription: \"Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.\"\n---\n\n# Medchem\n\n## Overview\n\nMedchem is a Python library for molecular filtering and prioritization in drug discovery workflows. Apply hundreds of well-established and novel molecular filters, structural alerts, and medicinal chemistry rules to efficiently triage and prioritize compound libraries at scale. Rules and filters are context-specific—use as guidelines combined with domain expertise.\n\n## When to Use This Skill\n\nThis skill should be used when:\n- Applying drug-likeness rules (Lipinski, Veber, etc.) to compound libraries\n- Filtering molecules by structural alerts or PAINS patterns\n- Prioritizing compounds for lead optimization\n- Assessing compound quality and medicinal chemistry properties\n- Detecting reactive or problematic functional groups\n- Calculating molecular complexity metrics\n\n## Installation\n\n```bash\nuv pip install medchem\n```\n\n## Core Capabilities\n\n### 1. Medicinal Chemistry Rules\n\nApply established drug-likeness rules to molecules using the `medchem.rules` module.\n\n**Available Rules:**\n- Rule of Five (Lipinski)\n- Rule of Oprea\n- Rule of CNS\n- Rule of leadlike (soft and strict)\n- Rule of three\n- Rule of Reos\n- Rule of drug\n- Rule of Veber\n- Golden triangle\n- PAINS filters\n\n**Single Rule Application:**\n\n```python\nimport medchem as mc\n\n# Apply Rule of Five to a SMILES string\nsmiles = \"CC(=O)OC1=CC=CC=C1C(=O)O\"  # Aspirin\npasses = mc.rules.basic_rules.rule_of_five(smiles)\n# Returns: True\n\n# Check specific rules\npasses_oprea = mc.rules.basic_rules.rule_of_oprea(smiles)\npasses_cns = mc.rules.basic_rules.rule_of_cns(smiles)\n```\n\n**Multiple Rules with RuleFilters:**\n\n```python\nimport datamol as dm\nimport medchem as mc\n\n# Load molecules\nmols = [dm.to_mol(smiles) for smiles in smiles_list]\n\n# Create filter with multiple rules\nrfilter = mc.rules.RuleFilters(\n    rule_list=[\n        \"rule_of_five\",\n        \"rule_of_oprea\",\n        \"rule_of_cns\",\n        \"rule_of_leadlike_soft\"\n    ]\n)\n\n# Apply filters with parallelization\nresults = rfilter(\n    mols=mols,\n    n_jobs=-1,  # Use all CPU cores\n    progress=True\n)\n```\n\n**Result Format:**\nResults are returned as dictionaries with pass\u002Ffail status and detailed information for each rule.\n\n### 2. Structural Alert Filters\n\nDetect potentially problematic structural patterns using the `medchem.structural` module.\n\n**Available Filters:**\n\n1. **Common Alerts** - General structural alerts derived from ChEMBL curation and literature\n2. **NIBR Filters** - Novartis Institutes for BioMedical Research filter set\n3. **Lilly Demerits** - Eli Lilly's demerit-based system (275 rules, molecules rejected at >100 demerits)\n\n**Common Alerts:**\n\n```python\nimport medchem as mc\n\n# Create filter\nalert_filter = mc.structural.CommonAlertsFilters()\n\n# Check single molecule\nmol = dm.to_mol(\"c1ccccc1\")\nhas_alerts, details = alert_filter.check_mol(mol)\n\n# Batch filtering with parallelization\nresults = alert_filter(\n    mols=mol_list,\n    n_jobs=-1,\n    progress=True\n)\n```\n\n**NIBR Filters:**\n\n```python\nimport medchem as mc\n\n# Apply NIBR filters\nnibr_filter = mc.structural.NIBRFilters()\nresults = nibr_filter(mols=mol_list, n_jobs=-1)\n```\n\n**Lilly Demerits:**\n\n```python\nimport medchem as mc\n\n# Calculate Lilly demerits\nlilly = mc.structural.LillyDemeritsFilters()\nresults = lilly(mols=mol_list, n_jobs=-1)\n\n# Each result includes demerit score and whether it passes (≤100 demerits)\n```\n\n### 3. Functional API for High-Level Operations\n\nThe `medchem.functional` module provides convenient functions for common workflows.\n\n**Quick Filtering:**\n\n```python\nimport medchem as mc\n\n# Apply NIBR filters to a list\nfilter_ok = mc.functional.nibr_filter(\n    mols=mol_list,\n    n_jobs=-1\n)\n\n# Apply common alerts\nalert_results = mc.functional.common_alerts_filter(\n    mols=mol_list,\n    n_jobs=-1\n)\n```\n\n### 4. Chemical Groups Detection\n\nIdentify specific chemical groups and functional groups using `medchem.groups`.\n\n**Available Groups:**\n- Hinge binders\n- Phosphate binders\n- Michael acceptors\n- Reactive groups\n- Custom SMARTS patterns\n\n**Usage:**\n\n```python\nimport medchem as mc\n\n# Create group detector\ngroup = mc.groups.ChemicalGroup(groups=[\"hinge_binders\"])\n\n# Check for matches\nhas_matches = group.has_match(mol_list)\n\n# Get detailed match information\nmatches = group.get_matches(mol)\n```\n\n### 5. Named Catalogs\n\nAccess curated collections of chemical structures through `medchem.catalogs`.\n\n**Available Catalogs:**\n- Functional groups\n- Protecting groups\n- Common reagents\n- Standard fragments\n\n**Usage:**\n\n```python\nimport medchem as mc\n\n# Access named catalogs\ncatalogs = mc.catalogs.NamedCatalogs\n\n# Use catalog for matching\ncatalog = catalogs.get(\"functional_groups\")\nmatches = catalog.get_matches(mol)\n```\n\n### 6. Molecular Complexity\n\nCalculate complexity metrics that approximate synthetic accessibility using `medchem.complexity`.\n\n**Common Metrics:**\n- Bertz complexity\n- Whitlock complexity\n- Barone complexity\n\n**Usage:**\n\n```python\nimport medchem as mc\n\n# Calculate complexity\ncomplexity_score = mc.complexity.calculate_complexity(mol)\n\n# Filter by complexity threshold\ncomplex_filter = mc.complexity.ComplexityFilter(max_complexity=500)\nresults = complex_filter(mols=mol_list)\n```\n\n### 7. Constraints Filtering\n\nApply custom property-based constraints using `medchem.constraints`.\n\n**Example Constraints:**\n- Molecular weight ranges\n- LogP bounds\n- TPSA limits\n- Rotatable bond counts\n\n**Usage:**\n\n```python\nimport medchem as mc\n\n# Define constraints\nconstraints = mc.constraints.Constraints(\n    mw_range=(200, 500),\n    logp_range=(-2, 5),\n    tpsa_max=140,\n    rotatable_bonds_max=10\n)\n\n# Apply constraints\nresults = constraints(mols=mol_list, n_jobs=-1)\n```\n\n### 8. Medchem Query Language\n\nUse a specialized query language for complex filtering criteria.\n\n**Query Examples:**\n```\n# Molecules passing Ro5 AND not having common alerts\n\"rule_of_five AND NOT common_alerts\"\n\n# CNS-like molecules with low complexity\n\"rule_of_cns AND complexity \u003C 400\"\n\n# Leadlike molecules without Lilly demerits\n\"rule_of_leadlike AND lilly_demerits == 0\"\n```\n\n**Usage:**\n\n```python\nimport medchem as mc\n\n# Parse and apply query\nquery = mc.query.parse(\"rule_of_five AND NOT common_alerts\")\nresults = query.apply(mols=mol_list, n_jobs=-1)\n```\n\n## Workflow Patterns\n\n### Pattern 1: Initial Triage of Compound Library\n\nFilter a large compound collection to identify drug-like candidates.\n\n```python\nimport datamol as dm\nimport medchem as mc\nimport pandas as pd\n\n# Load compound library\ndf = pd.read_csv(\"compounds.csv\")\nmols = [dm.to_mol(smi) for smi in df[\"smiles\"]]\n\n# Apply primary filters\nrule_filter = mc.rules.RuleFilters(rule_list=[\"rule_of_five\", \"rule_of_veber\"])\nrule_results = rule_filter(mols=mols, n_jobs=-1, progress=True)\n\n# Apply structural alerts\nalert_filter = mc.structural.CommonAlertsFilters()\nalert_results = alert_filter(mols=mols, n_jobs=-1, progress=True)\n\n# Combine results\ndf[\"passes_rules\"] = rule_results[\"pass\"]\ndf[\"has_alerts\"] = alert_results[\"has_alerts\"]\ndf[\"drug_like\"] = df[\"passes_rules\"] & ~df[\"has_alerts\"]\n\n# Save filtered compounds\nfiltered_df = df[df[\"drug_like\"]]\nfiltered_df.to_csv(\"filtered_compounds.csv\", index=False)\n```\n\n### Pattern 2: Lead Optimization Filtering\n\nApply stricter criteria during lead optimization.\n\n```python\nimport medchem as mc\n\n# Create comprehensive filter\nfilters = {\n    \"rules\": mc.rules.RuleFilters(rule_list=[\"rule_of_leadlike_strict\"]),\n    \"alerts\": mc.structural.NIBRFilters(),\n    \"lilly\": mc.structural.LillyDemeritsFilters(),\n    \"complexity\": mc.complexity.ComplexityFilter(max_complexity=400)\n}\n\n# Apply all filters\nresults = {}\nfor name, filt in filters.items():\n    results[name] = filt(mols=candidate_mols, n_jobs=-1)\n\n# Identify compounds passing all filters\npasses_all = all(r[\"pass\"] for r in results.values())\n```\n\n### Pattern 3: Identify Specific Chemical Groups\n\nFind molecules containing specific functional groups or scaffolds.\n\n```python\nimport medchem as mc\n\n# Create group detector for multiple groups\ngroup_detector = mc.groups.ChemicalGroup(\n    groups=[\"hinge_binders\", \"phosphate_binders\"]\n)\n\n# Screen library\nmatches = group_detector.get_all_matches(mol_list)\n\n# Filter molecules with desired groups\nmol_with_groups = [mol for mol, match in zip(mol_list, matches) if match]\n```\n\n## Best Practices\n\n1. **Context Matters**: Don't blindly apply filters. Understand the biological target and chemical space.\n\n2. **Combine Multiple Filters**: Use rules, structural alerts, and domain knowledge together for better decisions.\n\n3. **Use Parallelization**: For large datasets (>1000 molecules), always use `n_jobs=-1` for parallel processing.\n\n4. **Iterative Refinement**: Start with broad filters (Ro5), then apply more specific criteria (CNS, leadlike) as needed.\n\n5. **Document Filtering Decisions**: Track which molecules were filtered out and why for reproducibility.\n\n6. **Validate Results**: Remember that marketed drugs often fail standard filters—use these as guidelines, not absolute rules.\n\n7. **Consider Prodrugs**: Molecules designed as prodrugs may intentionally violate standard medicinal chemistry rules.\n\n## Resources\n\n### references\u002Fapi_guide.md\nComprehensive API reference covering all medchem modules with detailed function signatures, parameters, and return types.\n\n### references\u002Frules_catalog.md\nComplete catalog of available rules, filters, and alerts with descriptions, thresholds, and literature references.\n\n### scripts\u002Ffilter_molecules.py\nProduction-ready script for batch filtering workflows. Supports multiple input formats (CSV, SDF, SMILES), configurable filter combinations, and detailed reporting.\n\n**Usage:**\n```bash\npython scripts\u002Ffilter_molecules.py input.csv --rules rule_of_five,rule_of_cns --alerts nibr --output filtered.csv\n```\n\n## Documentation\n\nOfficial documentation: https:\u002F\u002Fmedchem-docs.datamol.io\u002F\nGitHub repository: https:\u002F\u002Fgithub.com\u002Fdatamol-io\u002Fmedchem\n","# Medchem\n\n## Overview\n\nMedchem is a Python library for molecular filtering and prioritization in drug discovery workflows. Apply hundreds of well-established and novel molecular filters, structural alerts, and medicinal chemistry rules to efficiently triage and prioritize compound libraries at scale. Rules and filters are context-specific—use as guidelines combined with domain expertise.\n\n## When to Use This Skill\n\nThis skill should be used when:\n- Applying drug-likeness rules (Lipinski, Veber, etc.) to compound libraries\n- Filtering molecules by structural alerts or PAINS patterns\n- Prioritizing compounds for lead optimization\n- Assessing compound quality and medicinal chemistry properties\n- Detecting reactive or problematic functional groups\n- Calculating molecular complexity metrics\n\n## Installation\n\n```bash\nuv pip install medchem\n```\n\n## Core Capabilities\n\n### 1. Medicinal Chemistry Rules\n\nApply established drug-likeness rules to molecules using the `medchem.rules` module.\n\n**Available Rules:**\n- Rule of Five (Lipinski)\n- Rule of Oprea\n- Rule of CNS\n- Rule of leadlike (soft and strict)\n- Rule of three\n- Rule of Reos\n- Rule of drug\n- Rule of Veber\n- Golden triangle\n- PAINS filters\n\n**Single Rule Application:**\n\n```python\nimport medchem as mc\n\n# Apply Rule of Five to a SMILES string\nsmiles = \"CC(=O)OC1=CC=CC=C1C(=O)O\"  # Aspirin\npasses = mc.rules.basic_rules.rule_of_five(smiles)\n# Returns: True\n\n# Check specific rules\npasses_oprea = mc.rules.basic_rules.rule_of_oprea(smiles)\npasses_cns = mc.rules.basic_rules.rule_of_cns(smiles)\n```\n\n**Multiple Rules with RuleFilters:**\n\n```python\nimport datamol as dm\nimport medchem as mc\n\n# Load molecules\nmols = [dm.to_mol(smiles) for smiles in smiles_list]\n\n# Create filter with multiple rules\nrfilter = mc.rules.RuleFilters(\n    rule_list=[\n        \"rule_of_five\",\n        \"rule_of_oprea\",\n        \"rule_of_cns\",\n        \"rule_of_leadlike_soft\"\n    ]\n)\n\n# Apply filters with parallelization\nresults = rfilter(\n    mols=mols,\n    n_jobs=-1,  # Use all CPU cores\n    progress=True\n)\n```\n\n**Result Format:**\nResults are returned as dictionaries with pass\u002Ffail status and detailed information for each rule.\n\n### 2. Structural Alert Filters\n\nDetect potentially problematic structural patterns using the `medchem.structural` module.\n\n**Available Filters:**\n\n1. **Common Alerts** - General structural alerts derived from ChEMBL curation and literature\n2. **NIBR Filters** - Novartis Institutes for BioMedical Research filter set\n3. **Lilly Demerits** - Eli Lilly's demerit-based system (275 rules, molecules rejected at >100 demerits)\n\n**Common Alerts:**\n\n```python\nimport medchem as mc\n\n# Create filter\nalert_filter = mc.structural.CommonAlertsFilters()\n\n# Check single molecule\nmol = dm.to_mol(\"c1ccccc1\")\nhas_alerts, details = alert_filter.check_mol(mol)\n\n# Batch filtering with parallelization\nresults = alert_filter(\n    mols=mol_list,\n    n_jobs=-1,\n    progress=True\n)\n```\n\n**NIBR Filters:**\n\n```python\nimport medchem as mc\n\n# Apply NIBR filters\nnibr_filter = mc.structural.NIBRFilters()\nresults = nibr_filter(mols=mol_list, n_jobs=-1)\n```\n\n**Lilly Demerits:**\n\n```python\nimport medchem as mc\n\n# Calculate Lilly demerits\nlilly = mc.structural.LillyDemeritsFilters()\nresults = lilly(mols=mol_list, n_jobs=-1)\n\n# Each result includes demerit score and whether it passes (≤100 demerits)\n```\n\n### 3. Functional API for High-Level Operations\n\nThe `medchem.functional` module provides convenient functions for common workflows.\n\n**Quick Filtering:**\n\n```python\nimport medchem as mc\n\n# Apply NIBR filters to a list\nfilter_ok = mc.functional.nibr_filter(\n    mols=mol_list,\n    n_jobs=-1\n)\n\n# Apply common alerts\nalert_results = mc.functional.common_alerts_filter(\n    mols=mol_list,\n    n_jobs=-1\n)\n```\n\n### 4. Chemical Groups Detection\n\nIdentify specific chemical groups and functional groups using `medchem.groups`.\n\n**Available Groups:**\n- Hinge binders\n- Phosphate binders\n- Michael acceptors\n- Reactive groups\n- Custom SMARTS patterns\n\n**Usage:**\n\n```python\nimport medchem as mc\n\n# Create group detector\ngroup = mc.groups.ChemicalGroup(groups=[\"hinge_binders\"])\n\n# Check for matches\nhas_matches = group.has_match(mol_list)\n\n# Get detailed match information\nmatches = group.get_matches(mol)\n```\n\n### 5. Named Catalogs\n\nAccess curated collections of chemical structures through `medchem.catalogs`.\n\n**Available Catalogs:**\n- Functional groups\n- Protecting groups\n- Common reagents\n- Standard fragments\n\n**Usage:**\n\n```python\nimport medchem as mc\n\n# Access named catalogs\ncatalogs = mc.catalogs.NamedCatalogs\n\n# Use catalog for matching\ncatalog = catalogs.get(\"functional_groups\")\nmatches = catalog.get_matches(mol)\n```\n\n### 6. Molecular Complexity\n\nCalculate complexity metrics that approximate synthetic accessibility using `medchem.complexity`.\n\n**Common Metrics:**\n- Bertz complexity\n- Whitlock complexity\n- Barone complexity\n\n**Usage:**\n\n```python\nimport medchem as mc\n\n# Calculate complexity\ncomplexity_score = mc.complexity.calculate_complexity(mol)\n\n# Filter by complexity threshold\ncomplex_filter = mc.complexity.ComplexityFilter(max_complexity=500)\nresults = complex_filter(mols=mol_list)\n```\n\n### 7. Constraints Filtering\n\nApply custom property-based constraints using `medchem.constraints`.\n\n**Example Constraints:**\n- Molecular weight ranges\n- LogP bounds\n- TPSA limits\n- Rotatable bond counts\n\n**Usage:**\n\n```python\nimport medchem as mc\n\n# Define constraints\nconstraints = mc.constraints.Constraints(\n    mw_range=(200, 500),\n    logp_range=(-2, 5),\n    tpsa_max=140,\n    rotatable_bonds_max=10\n)\n\n# Apply constraints\nresults = constraints(mols=mol_list, n_jobs=-1)\n```\n\n### 8. Medchem Query Language\n\nUse a specialized query language for complex filtering criteria.\n\n**Query Examples:**\n```\n# Molecules passing Ro5 AND not having common alerts\n\"rule_of_five AND NOT common_alerts\"\n\n# CNS-like molecules with low complexity\n\"rule_of_cns AND complexity \u003C 400\"\n\n# Leadlike molecules without Lilly demerits\n\"rule_of_leadlike AND lilly_demerits == 0\"\n```\n\n**Usage:**\n\n```python\nimport medchem as mc\n\n# Parse and apply query\nquery = mc.query.parse(\"rule_of_five AND NOT common_alerts\")\nresults = query.apply(mols=mol_list, n_jobs=-1)\n```\n\n## Workflow Patterns\n\n### Pattern 1: Initial Triage of Compound Library\n\nFilter a large compound collection to identify drug-like candidates.\n\n```python\nimport datamol as dm\nimport medchem as mc\nimport pandas as pd\n\n# Load compound library\ndf = pd.read_csv(\"compounds.csv\")\nmols = [dm.to_mol(smi) for smi in df[\"smiles\"]]\n\n# Apply primary filters\nrule_filter = mc.rules.RuleFilters(rule_list=[\"rule_of_five\", \"rule_of_veber\"])\nrule_results = rule_filter(mols=mols, n_jobs=-1, progress=True)\n\n# Apply structural alerts\nalert_filter = mc.structural.CommonAlertsFilters()\nalert_results = alert_filter(mols=mols, n_jobs=-1, progress=True)\n\n# Combine results\ndf[\"passes_rules\"] = rule_results[\"pass\"]\ndf[\"has_alerts\"] = alert_results[\"has_alerts\"]\ndf[\"drug_like\"] = df[\"passes_rules\"] & ~df[\"has_alerts\"]\n\n# Save filtered compounds\nfiltered_df = df[df[\"drug_like\"]]\nfiltered_df.to_csv(\"filtered_compounds.csv\", index=False)\n```\n\n### Pattern 2: Lead Optimization Filtering\n\nApply stricter criteria during lead optimization.\n\n```python\nimport medchem as mc\n\n# Create comprehensive filter\nfilters = {\n    \"rules\": mc.rules.RuleFilters(rule_list=[\"rule_of_leadlike_strict\"]),\n    \"alerts\": mc.structural.NIBRFilters(),\n    \"lilly\": mc.structural.LillyDemeritsFilters(),\n    \"complexity\": mc.complexity.ComplexityFilter(max_complexity=400)\n}\n\n# Apply all filters\nresults = {}\nfor name, filt in filters.items():\n    results[name] = filt(mols=candidate_mols, n_jobs=-1)\n\n# Identify compounds passing all filters\npasses_all = all(r[\"pass\"] for r in results.values())\n```\n\n### Pattern 3: Identify Specific Chemical Groups\n\nFind molecules containing specific functional groups or scaffolds.\n\n```python\nimport medchem as mc\n\n# Create group detector for multiple groups\ngroup_detector = mc.groups.ChemicalGroup(\n    groups=[\"hinge_binders\", \"phosphate_binders\"]\n)\n\n# Screen library\nmatches = group_detector.get_all_matches(mol_list)\n\n# Filter molecules with desired groups\nmol_with_groups = [mol for mol, match in zip(mol_list, matches) if match]\n```\n\n## Best Practices\n\n1. **Context Matters**: Don't blindly apply filters. Understand the biological target and chemical space.\n\n2. **Combine Multiple Filters**: Use rules, structural alerts, and domain knowledge together for better decisions.\n\n3. **Use Parallelization**: For large datasets (>1000 molecules), always use `n_jobs=-1` for parallel processing.\n\n4. **Iterative Refinement**: Start with broad filters (Ro5), then apply more specific criteria (CNS, leadlike) as needed.\n\n5. **Document Filtering Decisions**: Track which molecules were filtered out and why for reproducibility.\n\n6. **Validate Results**: Remember that marketed drugs often fail standard filters—use these as guidelines, not absolute rules.\n\n7. **Consider Prodrugs**: Molecules designed as prodrugs may intentionally violate standard medicinal chemistry rules.\n\n## Resources\n\n### references\u002Fapi_guide.md\nComprehensive API reference covering all medchem modules with detailed function signatures, parameters, and return types.\n\n### references\u002Frules_catalog.md\nComplete catalog of available rules, filters, and alerts with descriptions, thresholds, and literature references.\n\n### scripts\u002Ffilter_molecules.py\nProduction-ready script for batch filtering workflows. Supports multiple input formats (CSV, SDF, SMILES), configurable filter combinations, and detailed reporting.\n\n**Usage:**\n```bash\npython scripts\u002Ffilter_molecules.py input.csv --rules rule_of_five,rule_of_cns --alerts nibr --output filtered.csv\n```\n\n## Documentation\n\nOfficial documentation: https:\u002F\u002Fmedchem-docs.datamol.io\u002F\nGitHub repository: https:\u002F\u002Fgithub.com\u002Fdatamol-io\u002Fmedchem\n",{"name":5,"description":7},"main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fmedchem",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add JSGforever\u002Fskillguard --skill medchem",{"tool":49,"command":50},"bunx","bunx skills add JSGforever\u002Fskillguard --skill medchem",{"tool":52,"command":53},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill medchem","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\u002Fmedchem\u002FSKILL.md",true,[57,63,67],{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fapi_guide.md","REFERENCE","参考文档",12344,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fmedchem\u002Freferences\u002Fapi_guide.md",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Frules_catalog.md",12512,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fmedchem\u002Freferences\u002Frules_catalog.md",{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"scripts\u002Ffilter_molecules.py","SCRIPT","脚本",15696,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fmedchem\u002Fscripts\u002Ffilter_molecules.py",[74,105,121,148,170,191],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":85,"publishedAt":31},"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",[80],{"categoryNo":81,"categoryName":82,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[86,87,88,89,90,91,92,93,19,94,95,96,97,98,99,100,101,102,103,104],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","secret","prompt injection","security scanner","when","review","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":109,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":117,"publishedAt":31},"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",[112],{"categoryNo":113,"categoryName":114,"taxonomyType":115,"taxonomyTypeDesc":116},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[118,119,120],"data","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":31},"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":31},"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":83,"taxonomyTypeDesc":84},"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":31},"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":83,"taxonomyTypeDesc":84},[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":31},"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":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":201,"categoryName":202,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":81,"categoryName":82,"taxonomyType":83,"taxonomyTypeDesc":84},[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"]