[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AFFAD5CGGKPA4BC686J75A":3,"skill-same:01M6AFFAD5CGGKPA4BC686J75A":101},{"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":31,"publishedAt":54,"linkOnly":55,"markdownContent":56,"markdownBody":57,"frontMatter":58,"refName":59,"commitSha":60,"skillDirectory":61,"forksCount":62,"repositoryHtmlUrl":63,"repositoryHomepageUrl":64,"ownerHtmlUrl":65,"ownerBlogUrl":66,"ownerDescription":67,"updatedAt":68,"install":69,"resources":82},"01M6AFFAD5CGGKPA4BC686J75A","kegg-database",null,"Direct REST API access to KEGG (academic use only). Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion. For Python workflows with multiple databases, prefer bioservices. Use this for direct HTTP\u002FREST work or KEGG-specific control.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fkegg-database\u002FSKILL.md",[18,23,26],{"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},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53],"database","KEGG","kegg database","work","gene","for","mapping","pathway","drug interactions","conversion","databases","only","use","python","direct","access","api","analysis","bioservices","REST","http","workflows","2026-11-10 10:12:30",false,"---\nname: kegg-database\ndescription: \"Direct REST API access to KEGG (academic use only). Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion. For Python workflows with multiple databases, prefer bioservices. Use this for direct HTTP\u002FREST work or KEGG-specific control.\"\n---\n\n# KEGG Database\n\n## Overview\n\nKEGG (Kyoto Encyclopedia of Genes and Genomes) is a comprehensive bioinformatics resource for biological pathway analysis and molecular interaction networks.\n\n**Important**: KEGG API is made available only for academic use by academic users.\n\n## When to Use This Skill\n\nThis skill should be used when querying pathways, genes, compounds, enzymes, diseases, and drugs across multiple organisms using KEGG's REST API.\n\n## Quick Start\n\nThe skill provides:\n1. Python helper functions (`scripts\u002Fkegg_api.py`) for all KEGG REST API operations\n2. Comprehensive reference documentation (`references\u002Fkegg_reference.md`) with detailed API specifications\n\nWhen users request KEGG data, determine which operation is needed and use the appropriate function from `scripts\u002Fkegg_api.py`.\n\n## Core Operations\n\n### 1. Database Information (`kegg_info`)\n\nRetrieve metadata and statistics about KEGG databases.\n\n**When to use**: Understanding database structure, checking available data, getting release information.\n\n**Usage**:\n```python\nfrom scripts.kegg_api import kegg_info\n\n# Get pathway database info\ninfo = kegg_info('pathway')\n\n# Get organism-specific info\nhsa_info = kegg_info('hsa')  # Human genome\n```\n\n**Common databases**: `kegg`, `pathway`, `module`, `brite`, `genes`, `genome`, `compound`, `glycan`, `reaction`, `enzyme`, `disease`, `drug`\n\n### 2. Listing Entries (`kegg_list`)\n\nList entry identifiers and names from KEGG databases.\n\n**When to use**: Getting all pathways for an organism, listing genes, retrieving compound catalogs.\n\n**Usage**:\n```python\nfrom scripts.kegg_api import kegg_list\n\n# List all reference pathways\npathways = kegg_list('pathway')\n\n# List human-specific pathways\nhsa_pathways = kegg_list('pathway', 'hsa')\n\n# List specific genes (max 10)\ngenes = kegg_list('hsa:10458+hsa:10459')\n```\n\n**Common organism codes**: `hsa` (human), `mmu` (mouse), `dme` (fruit fly), `sce` (yeast), `eco` (E. coli)\n\n### 3. Searching (`kegg_find`)\n\nSearch KEGG databases by keywords or molecular properties.\n\n**When to use**: Finding genes by name\u002Fdescription, searching compounds by formula or mass, discovering entries by keywords.\n\n**Usage**:\n```python\nfrom scripts.kegg_api import kegg_find\n\n# Keyword search\nresults = kegg_find('genes', 'p53')\nshiga_toxin = kegg_find('genes', 'shiga toxin')\n\n# Chemical formula search (exact match)\ncompounds = kegg_find('compound', 'C7H10N4O2', 'formula')\n\n# Molecular weight range search\ndrugs = kegg_find('drug', '300-310', 'exact_mass')\n```\n\n**Search options**: `formula` (exact match), `exact_mass` (range), `mol_weight` (range)\n\n### 4. Retrieving Entries (`kegg_get`)\n\nGet complete database entries or specific data formats.\n\n**When to use**: Retrieving pathway details, getting gene\u002Fprotein sequences, downloading pathway maps, accessing compound structures.\n\n**Usage**:\n```python\nfrom scripts.kegg_api import kegg_get\n\n# Get pathway entry\npathway = kegg_get('hsa00010')  # Glycolysis pathway\n\n# Get multiple entries (max 10)\ngenes = kegg_get(['hsa:10458', 'hsa:10459'])\n\n# Get protein sequence (FASTA)\nsequence = kegg_get('hsa:10458', 'aaseq')\n\n# Get nucleotide sequence\nnt_seq = kegg_get('hsa:10458', 'ntseq')\n\n# Get compound structure\nmol_file = kegg_get('cpd:C00002', 'mol')  # ATP in MOL format\n\n# Get pathway as JSON (single entry only)\npathway_json = kegg_get('hsa05130', 'json')\n\n# Get pathway image (single entry only)\npathway_img = kegg_get('hsa05130', 'image')\n```\n\n**Output formats**: `aaseq` (protein FASTA), `ntseq` (nucleotide FASTA), `mol` (MOL format), `kcf` (KCF format), `image` (PNG), `kgml` (XML), `json` (pathway JSON)\n\n**Important**: Image, KGML, and JSON formats allow only one entry at a time.\n\n### 5. ID Conversion (`kegg_conv`)\n\nConvert identifiers between KEGG and external databases.\n\n**When to use**: Integrating KEGG data with other databases, mapping gene IDs, converting compound identifiers.\n\n**Usage**:\n```python\nfrom scripts.kegg_api import kegg_conv\n\n# Convert all human genes to NCBI Gene IDs\nconversions = kegg_conv('ncbi-geneid', 'hsa')\n\n# Convert specific gene\ngene_id = kegg_conv('ncbi-geneid', 'hsa:10458')\n\n# Convert to UniProt\nuniprot_id = kegg_conv('uniprot', 'hsa:10458')\n\n# Convert compounds to PubChem\npubchem_ids = kegg_conv('pubchem', 'compound')\n\n# Reverse conversion (NCBI Gene ID to KEGG)\nkegg_id = kegg_conv('hsa', 'ncbi-geneid')\n```\n\n**Supported conversions**: `ncbi-geneid`, `ncbi-proteinid`, `uniprot`, `pubchem`, `chebi`\n\n### 6. Cross-Referencing (`kegg_link`)\n\nFind related entries within and between KEGG databases.\n\n**When to use**: Finding pathways containing genes, getting genes in a pathway, mapping genes to KO groups, finding compounds in pathways.\n\n**Usage**:\n```python\nfrom scripts.kegg_api import kegg_link\n\n# Find pathways linked to human genes\npathways = kegg_link('pathway', 'hsa')\n\n# Get genes in a specific pathway\ngenes = kegg_link('genes', 'hsa00010')  # Glycolysis genes\n\n# Find pathways containing a specific gene\ngene_pathways = kegg_link('pathway', 'hsa:10458')\n\n# Find compounds in a pathway\ncompounds = kegg_link('compound', 'hsa00010')\n\n# Map genes to KO (orthology) groups\nko_groups = kegg_link('ko', 'hsa:10458')\n```\n\n**Common links**: genes ↔ pathway, pathway ↔ compound, pathway ↔ enzyme, genes ↔ ko (orthology)\n\n### 7. Drug-Drug Interactions (`kegg_ddi`)\n\nCheck for drug-drug interactions.\n\n**When to use**: Analyzing drug combinations, checking for contraindications, pharmacological research.\n\n**Usage**:\n```python\nfrom scripts.kegg_api import kegg_ddi\n\n# Check single drug\ninteractions = kegg_ddi('D00001')\n\n# Check multiple drugs (max 10)\ninteractions = kegg_ddi(['D00001', 'D00002', 'D00003'])\n```\n\n## Common Analysis Workflows\n\n### Workflow 1: Gene to Pathway Mapping\n\n**Use case**: Finding pathways associated with genes of interest (e.g., for pathway enrichment analysis).\n\n```python\nfrom scripts.kegg_api import kegg_find, kegg_link, kegg_get\n\n# Step 1: Find gene ID by name\ngene_results = kegg_find('genes', 'p53')\n\n# Step 2: Link gene to pathways\npathways = kegg_link('pathway', 'hsa:7157')  # TP53 gene\n\n# Step 3: Get detailed pathway information\nfor pathway_line in pathways.split('\\n'):\n    if pathway_line:\n        pathway_id = pathway_line.split('\\t')[1].replace('path:', '')\n        pathway_info = kegg_get(pathway_id)\n        # Process pathway information\n```\n\n### Workflow 2: Pathway Enrichment Context\n\n**Use case**: Getting all genes in organism pathways for enrichment analysis.\n\n```python\nfrom scripts.kegg_api import kegg_list, kegg_link\n\n# Step 1: List all human pathways\npathways = kegg_list('pathway', 'hsa')\n\n# Step 2: For each pathway, get associated genes\nfor pathway_line in pathways.split('\\n'):\n    if pathway_line:\n        pathway_id = pathway_line.split('\\t')[0]\n        genes = kegg_link('genes', pathway_id)\n        # Process genes for enrichment analysis\n```\n\n### Workflow 3: Compound to Pathway Analysis\n\n**Use case**: Finding metabolic pathways containing compounds of interest.\n\n```python\nfrom scripts.kegg_api import kegg_find, kegg_link, kegg_get\n\n# Step 1: Search for compound\ncompound_results = kegg_find('compound', 'glucose')\n\n# Step 2: Link compound to reactions\nreactions = kegg_link('reaction', 'cpd:C00031')  # Glucose\n\n# Step 3: Link reactions to pathways\npathways = kegg_link('pathway', 'rn:R00299')  # Specific reaction\n\n# Step 4: Get pathway details\npathway_info = kegg_get('map00010')  # Glycolysis\n```\n\n### Workflow 4: Cross-Database Integration\n\n**Use case**: Integrating KEGG data with UniProt, NCBI, or PubChem databases.\n\n```python\nfrom scripts.kegg_api import kegg_conv, kegg_get\n\n# Step 1: Convert KEGG gene IDs to external database IDs\nuniprot_map = kegg_conv('uniprot', 'hsa')\nncbi_map = kegg_conv('ncbi-geneid', 'hsa')\n\n# Step 2: Parse conversion results\nfor line in uniprot_map.split('\\n'):\n    if line:\n        kegg_id, uniprot_id = line.split('\\t')\n        # Use external IDs for integration\n\n# Step 3: Get sequences using KEGG\nsequence = kegg_get('hsa:10458', 'aaseq')\n```\n\n### Workflow 5: Organism-Specific Pathway Analysis\n\n**Use case**: Comparing pathways across different organisms.\n\n```python\nfrom scripts.kegg_api import kegg_list, kegg_get\n\n# Step 1: List pathways for multiple organisms\nhuman_pathways = kegg_list('pathway', 'hsa')\nmouse_pathways = kegg_list('pathway', 'mmu')\nyeast_pathways = kegg_list('pathway', 'sce')\n\n# Step 2: Get reference pathway for comparison\nref_pathway = kegg_get('map00010')  # Reference glycolysis\n\n# Step 3: Get organism-specific versions\nhsa_glycolysis = kegg_get('hsa00010')\nmmu_glycolysis = kegg_get('mmu00010')\n```\n\n## Pathway Categories\n\nKEGG organizes pathways into seven major categories. When interpreting pathway IDs or recommending pathways to users:\n\n1. **Metabolism** (e.g., `map00010` - Glycolysis, `map00190` - Oxidative phosphorylation)\n2. **Genetic Information Processing** (e.g., `map03010` - Ribosome, `map03040` - Spliceosome)\n3. **Environmental Information Processing** (e.g., `map04010` - MAPK signaling, `map02010` - ABC transporters)\n4. **Cellular Processes** (e.g., `map04140` - Autophagy, `map04210` - Apoptosis)\n5. **Organismal Systems** (e.g., `map04610` - Complement cascade, `map04910` - Insulin signaling)\n6. **Human Diseases** (e.g., `map05200` - Pathways in cancer, `map05010` - Alzheimer disease)\n7. **Drug Development** (chronological and target-based classifications)\n\nReference `references\u002Fkegg_reference.md` for detailed pathway lists and classifications.\n\n## Important Identifiers and Formats\n\n### Pathway IDs\n- `map#####` - Reference pathway (generic, not organism-specific)\n- `hsa#####` - Human pathway\n- `mmu#####` - Mouse pathway\n\n### Gene IDs\n- Format: `organism:gene_number` (e.g., `hsa:10458`)\n\n### Compound IDs\n- Format: `cpd:C#####` (e.g., `cpd:C00002` for ATP)\n\n### Drug IDs\n- Format: `dr:D#####` (e.g., `dr:D00001`)\n\n### Enzyme IDs\n- Format: `ec:EC_number` (e.g., `ec:1.1.1.1`)\n\n### KO (KEGG Orthology) IDs\n- Format: `ko:K#####` (e.g., `ko:K00001`)\n\n## API Limitations\n\nRespect these constraints when using the KEGG API:\n\n1. **Entry limits**: Maximum 10 entries per operation (except image\u002Fkgml\u002Fjson: 1 entry only)\n2. **Academic use**: API is for academic use only; commercial use requires licensing\n3. **HTTP status codes**: Check for 200 (success), 400 (bad request), 404 (not found)\n4. **Rate limiting**: No explicit limit, but avoid rapid-fire requests\n\n## Detailed Reference\n\nFor comprehensive API documentation, database specifications, organism codes, and advanced usage, refer to `references\u002Fkegg_reference.md`. This includes:\n\n- Complete list of KEGG databases\n- Detailed API operation syntax\n- All organism codes\n- HTTP status codes and error handling\n- Integration with Biopython and R\u002FBioconductor\n- Best practices for API usage\n\n## Troubleshooting\n\n**404 Not Found**: Entry or database doesn't exist; verify IDs and organism codes\n**400 Bad Request**: Syntax error in API call; check parameter formatting\n**Empty results**: Search term may not match entries; try broader keywords\n**Image\u002FKGML errors**: These formats only work with single entries; remove batch processing\n\n## Additional Tools\n\nFor interactive pathway visualization and annotation:\n- **KEGG Mapper**: https:\u002F\u002Fwww.kegg.jp\u002Fkegg\u002Fmapper\u002F\n- **BlastKOALA**: Automated genome annotation\n- **GhostKOALA**: Metagenome\u002Fmetatranscriptome annotation\n","# KEGG Database\n\n## Overview\n\nKEGG (Kyoto Encyclopedia of Genes and Genomes) is a comprehensive bioinformatics resource for biological pathway analysis and molecular interaction networks.\n\n**Important**: KEGG API is made available only for academic use by academic users.\n\n## When to Use This Skill\n\nThis skill should be used when querying pathways, genes, compounds, enzymes, diseases, and drugs across multiple organisms using KEGG's REST API.\n\n## Quick Start\n\nThe skill provides:\n1. Python helper functions (`scripts\u002Fkegg_api.py`) for all KEGG REST API operations\n2. Comprehensive reference documentation (`references\u002Fkegg_reference.md`) with detailed API specifications\n\nWhen users request KEGG data, determine which operation is needed and use the appropriate function from `scripts\u002Fkegg_api.py`.\n\n## Core Operations\n\n### 1. Database Information (`kegg_info`)\n\nRetrieve metadata and statistics about KEGG databases.\n\n**When to use**: Understanding database structure, checking available data, getting release information.\n\n**Usage**:\n```python\nfrom scripts.kegg_api import kegg_info\n\n# Get pathway database info\ninfo = kegg_info('pathway')\n\n# Get organism-specific info\nhsa_info = kegg_info('hsa')  # Human genome\n```\n\n**Common databases**: `kegg`, `pathway`, `module`, `brite`, `genes`, `genome`, `compound`, `glycan`, `reaction`, `enzyme`, `disease`, `drug`\n\n### 2. Listing Entries (`kegg_list`)\n\nList entry identifiers and names from KEGG databases.\n\n**When to use**: Getting all pathways for an organism, listing genes, retrieving compound catalogs.\n\n**Usage**:\n```python\nfrom scripts.kegg_api import kegg_list\n\n# List all reference pathways\npathways = kegg_list('pathway')\n\n# List human-specific pathways\nhsa_pathways = kegg_list('pathway', 'hsa')\n\n# List specific genes (max 10)\ngenes = kegg_list('hsa:10458+hsa:10459')\n```\n\n**Common organism codes**: `hsa` (human), `mmu` (mouse), `dme` (fruit fly), `sce` (yeast), `eco` (E. coli)\n\n### 3. Searching (`kegg_find`)\n\nSearch KEGG databases by keywords or molecular properties.\n\n**When to use**: Finding genes by name\u002Fdescription, searching compounds by formula or mass, discovering entries by keywords.\n\n**Usage**:\n```python\nfrom scripts.kegg_api import kegg_find\n\n# Keyword search\nresults = kegg_find('genes', 'p53')\nshiga_toxin = kegg_find('genes', 'shiga toxin')\n\n# Chemical formula search (exact match)\ncompounds = kegg_find('compound', 'C7H10N4O2', 'formula')\n\n# Molecular weight range search\ndrugs = kegg_find('drug', '300-310', 'exact_mass')\n```\n\n**Search options**: `formula` (exact match), `exact_mass` (range), `mol_weight` (range)\n\n### 4. Retrieving Entries (`kegg_get`)\n\nGet complete database entries or specific data formats.\n\n**When to use**: Retrieving pathway details, getting gene\u002Fprotein sequences, downloading pathway maps, accessing compound structures.\n\n**Usage**:\n```python\nfrom scripts.kegg_api import kegg_get\n\n# Get pathway entry\npathway = kegg_get('hsa00010')  # Glycolysis pathway\n\n# Get multiple entries (max 10)\ngenes = kegg_get(['hsa:10458', 'hsa:10459'])\n\n# Get protein sequence (FASTA)\nsequence = kegg_get('hsa:10458', 'aaseq')\n\n# Get nucleotide sequence\nnt_seq = kegg_get('hsa:10458', 'ntseq')\n\n# Get compound structure\nmol_file = kegg_get('cpd:C00002', 'mol')  # ATP in MOL format\n\n# Get pathway as JSON (single entry only)\npathway_json = kegg_get('hsa05130', 'json')\n\n# Get pathway image (single entry only)\npathway_img = kegg_get('hsa05130', 'image')\n```\n\n**Output formats**: `aaseq` (protein FASTA), `ntseq` (nucleotide FASTA), `mol` (MOL format), `kcf` (KCF format), `image` (PNG), `kgml` (XML), `json` (pathway JSON)\n\n**Important**: Image, KGML, and JSON formats allow only one entry at a time.\n\n### 5. ID Conversion (`kegg_conv`)\n\nConvert identifiers between KEGG and external databases.\n\n**When to use**: Integrating KEGG data with other databases, mapping gene IDs, converting compound identifiers.\n\n**Usage**:\n```python\nfrom scripts.kegg_api import kegg_conv\n\n# Convert all human genes to NCBI Gene IDs\nconversions = kegg_conv('ncbi-geneid', 'hsa')\n\n# Convert specific gene\ngene_id = kegg_conv('ncbi-geneid', 'hsa:10458')\n\n# Convert to UniProt\nuniprot_id = kegg_conv('uniprot', 'hsa:10458')\n\n# Convert compounds to PubChem\npubchem_ids = kegg_conv('pubchem', 'compound')\n\n# Reverse conversion (NCBI Gene ID to KEGG)\nkegg_id = kegg_conv('hsa', 'ncbi-geneid')\n```\n\n**Supported conversions**: `ncbi-geneid`, `ncbi-proteinid`, `uniprot`, `pubchem`, `chebi`\n\n### 6. Cross-Referencing (`kegg_link`)\n\nFind related entries within and between KEGG databases.\n\n**When to use**: Finding pathways containing genes, getting genes in a pathway, mapping genes to KO groups, finding compounds in pathways.\n\n**Usage**:\n```python\nfrom scripts.kegg_api import kegg_link\n\n# Find pathways linked to human genes\npathways = kegg_link('pathway', 'hsa')\n\n# Get genes in a specific pathway\ngenes = kegg_link('genes', 'hsa00010')  # Glycolysis genes\n\n# Find pathways containing a specific gene\ngene_pathways = kegg_link('pathway', 'hsa:10458')\n\n# Find compounds in a pathway\ncompounds = kegg_link('compound', 'hsa00010')\n\n# Map genes to KO (orthology) groups\nko_groups = kegg_link('ko', 'hsa:10458')\n```\n\n**Common links**: genes ↔ pathway, pathway ↔ compound, pathway ↔ enzyme, genes ↔ ko (orthology)\n\n### 7. Drug-Drug Interactions (`kegg_ddi`)\n\nCheck for drug-drug interactions.\n\n**When to use**: Analyzing drug combinations, checking for contraindications, pharmacological research.\n\n**Usage**:\n```python\nfrom scripts.kegg_api import kegg_ddi\n\n# Check single drug\ninteractions = kegg_ddi('D00001')\n\n# Check multiple drugs (max 10)\ninteractions = kegg_ddi(['D00001', 'D00002', 'D00003'])\n```\n\n## Common Analysis Workflows\n\n### Workflow 1: Gene to Pathway Mapping\n\n**Use case**: Finding pathways associated with genes of interest (e.g., for pathway enrichment analysis).\n\n```python\nfrom scripts.kegg_api import kegg_find, kegg_link, kegg_get\n\n# Step 1: Find gene ID by name\ngene_results = kegg_find('genes', 'p53')\n\n# Step 2: Link gene to pathways\npathways = kegg_link('pathway', 'hsa:7157')  # TP53 gene\n\n# Step 3: Get detailed pathway information\nfor pathway_line in pathways.split('\\n'):\n    if pathway_line:\n        pathway_id = pathway_line.split('\\t')[1].replace('path:', '')\n        pathway_info = kegg_get(pathway_id)\n        # Process pathway information\n```\n\n### Workflow 2: Pathway Enrichment Context\n\n**Use case**: Getting all genes in organism pathways for enrichment analysis.\n\n```python\nfrom scripts.kegg_api import kegg_list, kegg_link\n\n# Step 1: List all human pathways\npathways = kegg_list('pathway', 'hsa')\n\n# Step 2: For each pathway, get associated genes\nfor pathway_line in pathways.split('\\n'):\n    if pathway_line:\n        pathway_id = pathway_line.split('\\t')[0]\n        genes = kegg_link('genes', pathway_id)\n        # Process genes for enrichment analysis\n```\n\n### Workflow 3: Compound to Pathway Analysis\n\n**Use case**: Finding metabolic pathways containing compounds of interest.\n\n```python\nfrom scripts.kegg_api import kegg_find, kegg_link, kegg_get\n\n# Step 1: Search for compound\ncompound_results = kegg_find('compound', 'glucose')\n\n# Step 2: Link compound to reactions\nreactions = kegg_link('reaction', 'cpd:C00031')  # Glucose\n\n# Step 3: Link reactions to pathways\npathways = kegg_link('pathway', 'rn:R00299')  # Specific reaction\n\n# Step 4: Get pathway details\npathway_info = kegg_get('map00010')  # Glycolysis\n```\n\n### Workflow 4: Cross-Database Integration\n\n**Use case**: Integrating KEGG data with UniProt, NCBI, or PubChem databases.\n\n```python\nfrom scripts.kegg_api import kegg_conv, kegg_get\n\n# Step 1: Convert KEGG gene IDs to external database IDs\nuniprot_map = kegg_conv('uniprot', 'hsa')\nncbi_map = kegg_conv('ncbi-geneid', 'hsa')\n\n# Step 2: Parse conversion results\nfor line in uniprot_map.split('\\n'):\n    if line:\n        kegg_id, uniprot_id = line.split('\\t')\n        # Use external IDs for integration\n\n# Step 3: Get sequences using KEGG\nsequence = kegg_get('hsa:10458', 'aaseq')\n```\n\n### Workflow 5: Organism-Specific Pathway Analysis\n\n**Use case**: Comparing pathways across different organisms.\n\n```python\nfrom scripts.kegg_api import kegg_list, kegg_get\n\n# Step 1: List pathways for multiple organisms\nhuman_pathways = kegg_list('pathway', 'hsa')\nmouse_pathways = kegg_list('pathway', 'mmu')\nyeast_pathways = kegg_list('pathway', 'sce')\n\n# Step 2: Get reference pathway for comparison\nref_pathway = kegg_get('map00010')  # Reference glycolysis\n\n# Step 3: Get organism-specific versions\nhsa_glycolysis = kegg_get('hsa00010')\nmmu_glycolysis = kegg_get('mmu00010')\n```\n\n## Pathway Categories\n\nKEGG organizes pathways into seven major categories. When interpreting pathway IDs or recommending pathways to users:\n\n1. **Metabolism** (e.g., `map00010` - Glycolysis, `map00190` - Oxidative phosphorylation)\n2. **Genetic Information Processing** (e.g., `map03010` - Ribosome, `map03040` - Spliceosome)\n3. **Environmental Information Processing** (e.g., `map04010` - MAPK signaling, `map02010` - ABC transporters)\n4. **Cellular Processes** (e.g., `map04140` - Autophagy, `map04210` - Apoptosis)\n5. **Organismal Systems** (e.g., `map04610` - Complement cascade, `map04910` - Insulin signaling)\n6. **Human Diseases** (e.g., `map05200` - Pathways in cancer, `map05010` - Alzheimer disease)\n7. **Drug Development** (chronological and target-based classifications)\n\nReference `references\u002Fkegg_reference.md` for detailed pathway lists and classifications.\n\n## Important Identifiers and Formats\n\n### Pathway IDs\n- `map#####` - Reference pathway (generic, not organism-specific)\n- `hsa#####` - Human pathway\n- `mmu#####` - Mouse pathway\n\n### Gene IDs\n- Format: `organism:gene_number` (e.g., `hsa:10458`)\n\n### Compound IDs\n- Format: `cpd:C#####` (e.g., `cpd:C00002` for ATP)\n\n### Drug IDs\n- Format: `dr:D#####` (e.g., `dr:D00001`)\n\n### Enzyme IDs\n- Format: `ec:EC_number` (e.g., `ec:1.1.1.1`)\n\n### KO (KEGG Orthology) IDs\n- Format: `ko:K#####` (e.g., `ko:K00001`)\n\n## API Limitations\n\nRespect these constraints when using the KEGG API:\n\n1. **Entry limits**: Maximum 10 entries per operation (except image\u002Fkgml\u002Fjson: 1 entry only)\n2. **Academic use**: API is for academic use only; commercial use requires licensing\n3. **HTTP status codes**: Check for 200 (success), 400 (bad request), 404 (not found)\n4. **Rate limiting**: No explicit limit, but avoid rapid-fire requests\n\n## Detailed Reference\n\nFor comprehensive API documentation, database specifications, organism codes, and advanced usage, refer to `references\u002Fkegg_reference.md`. This includes:\n\n- Complete list of KEGG databases\n- Detailed API operation syntax\n- All organism codes\n- HTTP status codes and error handling\n- Integration with Biopython and R\u002FBioconductor\n- Best practices for API usage\n\n## Troubleshooting\n\n**404 Not Found**: Entry or database doesn't exist; verify IDs and organism codes\n**400 Bad Request**: Syntax error in API call; check parameter formatting\n**Empty results**: Search term may not match entries; try broader keywords\n**Image\u002FKGML errors**: These formats only work with single entries; remove batch processing\n\n## Additional Tools\n\nFor interactive pathway visualization and annotation:\n- **KEGG Mapper**: https:\u002F\u002Fwww.kegg.jp\u002Fkegg\u002Fmapper\u002F\n- **BlastKOALA**: Automated genome annotation\n- **GhostKOALA**: Metagenome\u002Fmetatranscriptome annotation\n",{"name":5,"description":7},"main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fkegg-database",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":70,"prompt":80,"zipAvailable":81},[71,74,77],{"tool":72,"command":73},"npx","npx skills add davila7\u002Fclaude-code-templates --skill kegg-database",{"tool":75,"command":76},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill kegg-database",{"tool":78,"command":79},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill kegg-database","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fkegg-database\u002FSKILL.md",true,[83,89,95],{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"LICENSE.txt","LICENSE","许可证",143,"https:\u002F\u002Fgithub.com\u002Fnoirelab\u002Flinux-setup\u002Fblob\u002Fmain\u002Fconfigs\u002Fcommon\u002Fclaude\u002Fskills\u002Fseo-backlinks\u002FLICENSE.txt",{"path":90,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fkegg_reference.md","REFERENCE","参考文档",10749,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fkegg-database\u002Freferences\u002Fkegg_reference.md",{"path":96,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":99,"sourceHtmlUrl":100},"scripts\u002Fkegg_api.py","SCRIPT","脚本",7697,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fkegg-database\u002Fscripts\u002Fkegg_api.py",[102,128,154,180,215,239],{"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":109,"publishedAt":54},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[108],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[110,111,112,113,114,37,115,116,44,117,118,119,120,121,122,123,124,125,126,127],"scoring","pool","wealthville pool scoring","liquidity","which","exit","now","when","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":135,"publishedAt":54},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[134],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[136,137,138,139,140,141,142,143,144,145,146,117,147,148,35,149,150,151,152,153],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","plan","focus","signals","audit","dependency",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":165,"publishedAt":54},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[160,161,162],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":163,"categoryName":164,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000033","数据分析师",[166,167,168,169,170,171,172,37,173,174,175,176,177,43,178,44,47,32,117,179],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","MCP","query",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":184,"licenseFileUrl":185,"sourceHtmlUrl":186,"categories":187,"keywords":191,"publishedAt":54},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[188],{"categoryNo":189,"categoryName":190,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,37,214],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":216,"name":217,"nameZh":6,"description":218,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":184,"licenseFileUrl":219,"sourceHtmlUrl":220,"categories":221,"keywords":226,"publishedAt":54},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[222,225],{"categoryNo":223,"categoryName":224,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":189,"categoryName":190,"taxonomyType":21,"taxonomyTypeDesc":22},[227,228,229,230,231,193,232,202,203,233,234,235,236,37,237,119,238],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":240,"name":241,"nameZh":6,"description":242,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":184,"licenseFileUrl":243,"sourceHtmlUrl":244,"categories":245,"keywords":253,"publishedAt":54},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[246,249,250],{"categoryNo":247,"categoryName":248,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":251,"categoryName":252,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000036","内容创作者",[254,255,256,257,258,259,260,261,195,262,205,147,263,264,265,266,267,43,268,117,269,49,270,271,272,125,273],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","claims","argument","assemble","recommendations"]