[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72BFSYHTFJXV1DGPVW80HMS":3,"skill-same:01M72BFSYHTFJXV1DGPVW80HMS":53},{"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":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M72BFSYHTFJXV1DGPVW80HMS","ena-database",null,"Access European Nucleotide Archive via API\u002FFTP. Retrieve DNA\u002FRNA sequences, raw reads (FASTQ), genome assemblies by accession, for genomics and bioinformatics pipelines. Supports multiple formats.","Sansar35\u002Fclaude-agent","Sansar35","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F145020281?v=4","01M724CQ2SCC86MGNSD87D0D4K","01M724CQ3965G9WJ3QXE3AJ5YY",1,"MIT","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fena-database\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: ena-database\ndescription: \"Access European Nucleotide Archive via API\u002FFTP. Retrieve DNA\u002FRNA sequences, raw reads (FASTQ), genome assemblies by accession, for genomics and bioinformatics pipelines. Supports multiple formats.\"\n---\n\n# ENA Database\n\n## Overview\n\nThe European Nucleotide Archive (ENA) is a comprehensive public repository for nucleotide sequence data and associated metadata. Access and query DNA\u002FRNA sequences, raw reads, genome assemblies, and functional annotations through REST APIs and FTP for genomics and bioinformatics pipelines.\n\n## When to Use This Skill\n\nThis skill should be used when:\n\n- Retrieving nucleotide sequences or raw sequencing reads by accession\n- Searching for samples, studies, or assemblies by metadata criteria\n- Downloading FASTQ files or genome assemblies for analysis\n- Querying taxonomic information for organisms\n- Accessing sequence annotations and functional data\n- Integrating ENA data into bioinformatics pipelines\n- Performing cross-reference searches to related databases\n- Bulk downloading datasets via FTP or Aspera\n\n## Core Capabilities\n\n### 1. Data Types and Structure\n\nENA organizes data into hierarchical object types:\n\n**Studies\u002FProjects** - Group related data and control release dates. Studies are the primary unit for citing archived data.\n\n**Samples** - Represent units of biomaterial from which sequencing libraries were produced. Samples must be registered before submitting most data types.\n\n**Raw Reads** - Consist of:\n- **Experiments**: Metadata about sequencing methods, library preparation, and instrument details\n- **Runs**: References to data files containing raw sequencing reads from a single sequencing run\n\n**Assemblies** - Genome, transcriptome, metagenome, or metatranscriptome assemblies at various completion levels.\n\n**Sequences** - Assembled and annotated sequences stored in the EMBL Nucleotide Sequence Database, including coding\u002Fnon-coding regions and functional annotations.\n\n**Analyses** - Results from computational analyses of sequence data.\n\n**Taxonomy Records** - Taxonomic information including lineage and rank.\n\n### 2. Programmatic Access\n\nENA provides multiple REST APIs for data access. Consult `references\u002Fapi_reference.md` for detailed endpoint documentation.\n\n**Key APIs:**\n\n**ENA Portal API** - Advanced search functionality across all ENA data types\n- Documentation: https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fportal\u002Fapi\u002Fdoc\n- Use for complex queries and metadata searches\n\n**ENA Browser API** - Direct retrieval of records and metadata\n- Documentation: https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fbrowser\u002Fapi\u002Fdoc\n- Use for downloading specific records by accession\n- Returns data in XML format\n\n**ENA Taxonomy REST API** - Query taxonomic information\n- Access lineage, rank, and related taxonomic data\n\n**ENA Cross Reference Service** - Access related records from external databases\n- Endpoint: https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fxref\u002Frest\u002F\n\n**CRAM Reference Registry** - Retrieve reference sequences\n- Endpoint: https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fcram\u002F\n- Query by MD5 or SHA1 checksums\n\n**Rate Limiting**: All APIs have a rate limit of 50 requests per second. Exceeding this returns HTTP 429 (Too Many Requests).\n\n### 3. Searching and Retrieving Data\n\n**Browser-Based Search:**\n- Free text search across all fields\n- Sequence similarity search (BLAST integration)\n- Cross-reference search to find related records\n- Advanced search with Rulespace query builder\n\n**Programmatic Queries:**\n- Use Portal API for advanced searches at scale\n- Filter by data type, date range, taxonomy, or metadata fields\n- Download results as tabulated metadata summaries or XML records\n\n**Example API Query Pattern:**\n```python\nimport requests\n\n# Search for samples from a specific study\nbase_url = \"https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fportal\u002Fapi\u002Fsearch\"\nparams = {\n    \"result\": \"sample\",\n    \"query\": \"study_accession=PRJEB1234\",\n    \"format\": \"json\",\n    \"limit\": 100\n}\n\nresponse = requests.get(base_url, params=params)\nsamples = response.json()\n```\n\n### 4. Data Retrieval Formats\n\n**Metadata Formats:**\n- XML (native ENA format)\n- JSON (via Portal API)\n- TSV\u002FCSV (tabulated summaries)\n\n**Sequence Data:**\n- FASTQ (raw reads)\n- BAM\u002FCRAM (aligned reads)\n- FASTA (assembled sequences)\n- EMBL flat file format (annotated sequences)\n\n**Download Methods:**\n- Direct API download (small files)\n- FTP for bulk data transfer\n- Aspera for high-speed transfer of large datasets\n- enaBrowserTools command-line utility for bulk downloads\n\n### 5. Common Use Cases\n\n**Retrieve raw sequencing reads by accession:**\n```python\n# Download run files using Browser API\naccession = \"ERR123456\"\nurl = f\"https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fbrowser\u002Fapi\u002Fxml\u002F{accession}\"\n```\n\n**Search for all samples in a study:**\n```python\n# Use Portal API to list samples\nstudy_id = \"PRJNA123456\"\nurl = f\"https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fportal\u002Fapi\u002Fsearch?result=sample&query=study_accession={study_id}&format=tsv\"\n```\n\n**Find assemblies for a specific organism:**\n```python\n# Search assemblies by taxonomy\norganism = \"Escherichia coli\"\nurl = f\"https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fportal\u002Fapi\u002Fsearch?result=assembly&query=tax_tree({organism})&format=json\"\n```\n\n**Get taxonomic lineage:**\n```python\n# Query taxonomy API\ntaxon_id = \"562\"  # E. coli\nurl = f\"https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Ftaxonomy\u002Frest\u002Ftax-id\u002F{taxon_id}\"\n```\n\n### 6. Integration with Analysis Pipelines\n\n**Bulk Download Pattern:**\n1. Search for accessions matching criteria using Portal API\n2. Extract file URLs from search results\n3. Download files via FTP or using enaBrowserTools\n4. Process downloaded data in pipeline\n\n**BLAST Integration:**\nIntegrate with EBI's NCBI BLAST service (REST\u002FSOAP API) for sequence similarity searches against ENA sequences.\n\n### 7. Best Practices\n\n**Rate Limiting:**\n- Implement exponential backoff when receiving HTTP 429 responses\n- Batch requests when possible to stay within 50 req\u002Fsec limit\n- Use bulk download tools for large datasets instead of iterating API calls\n\n**Data Citation:**\n- Always cite using Study\u002FProject accessions when publishing\n- Include accession numbers for specific samples, runs, or assemblies used\n\n**API Response Handling:**\n- Check HTTP status codes before processing responses\n- Parse XML responses using proper XML libraries (not regex)\n- Handle pagination for large result sets\n\n**Performance:**\n- Use FTP\u002FAspera for downloading large files (>100MB)\n- Prefer TSV\u002FJSON formats over XML when only metadata is needed\n- Cache taxonomy lookups locally when processing many records\n\n## Resources\n\nThis skill includes detailed reference documentation for working with ENA:\n\n### references\u002F\n\n**api_reference.md** - Comprehensive API endpoint documentation including:\n- Detailed parameters for Portal API and Browser API\n- Response format specifications\n- Advanced query syntax and operators\n- Field names for filtering and searching\n- Common API patterns and examples\n\nLoad this reference when constructing complex API queries, debugging API responses, or needing specific parameter details.\n","# ENA Database\n\n## Overview\n\nThe European Nucleotide Archive (ENA) is a comprehensive public repository for nucleotide sequence data and associated metadata. Access and query DNA\u002FRNA sequences, raw reads, genome assemblies, and functional annotations through REST APIs and FTP for genomics and bioinformatics pipelines.\n\n## When to Use This Skill\n\nThis skill should be used when:\n\n- Retrieving nucleotide sequences or raw sequencing reads by accession\n- Searching for samples, studies, or assemblies by metadata criteria\n- Downloading FASTQ files or genome assemblies for analysis\n- Querying taxonomic information for organisms\n- Accessing sequence annotations and functional data\n- Integrating ENA data into bioinformatics pipelines\n- Performing cross-reference searches to related databases\n- Bulk downloading datasets via FTP or Aspera\n\n## Core Capabilities\n\n### 1. Data Types and Structure\n\nENA organizes data into hierarchical object types:\n\n**Studies\u002FProjects** - Group related data and control release dates. Studies are the primary unit for citing archived data.\n\n**Samples** - Represent units of biomaterial from which sequencing libraries were produced. Samples must be registered before submitting most data types.\n\n**Raw Reads** - Consist of:\n- **Experiments**: Metadata about sequencing methods, library preparation, and instrument details\n- **Runs**: References to data files containing raw sequencing reads from a single sequencing run\n\n**Assemblies** - Genome, transcriptome, metagenome, or metatranscriptome assemblies at various completion levels.\n\n**Sequences** - Assembled and annotated sequences stored in the EMBL Nucleotide Sequence Database, including coding\u002Fnon-coding regions and functional annotations.\n\n**Analyses** - Results from computational analyses of sequence data.\n\n**Taxonomy Records** - Taxonomic information including lineage and rank.\n\n### 2. Programmatic Access\n\nENA provides multiple REST APIs for data access. Consult `references\u002Fapi_reference.md` for detailed endpoint documentation.\n\n**Key APIs:**\n\n**ENA Portal API** - Advanced search functionality across all ENA data types\n- Documentation: https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fportal\u002Fapi\u002Fdoc\n- Use for complex queries and metadata searches\n\n**ENA Browser API** - Direct retrieval of records and metadata\n- Documentation: https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fbrowser\u002Fapi\u002Fdoc\n- Use for downloading specific records by accession\n- Returns data in XML format\n\n**ENA Taxonomy REST API** - Query taxonomic information\n- Access lineage, rank, and related taxonomic data\n\n**ENA Cross Reference Service** - Access related records from external databases\n- Endpoint: https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fxref\u002Frest\u002F\n\n**CRAM Reference Registry** - Retrieve reference sequences\n- Endpoint: https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fcram\u002F\n- Query by MD5 or SHA1 checksums\n\n**Rate Limiting**: All APIs have a rate limit of 50 requests per second. Exceeding this returns HTTP 429 (Too Many Requests).\n\n### 3. Searching and Retrieving Data\n\n**Browser-Based Search:**\n- Free text search across all fields\n- Sequence similarity search (BLAST integration)\n- Cross-reference search to find related records\n- Advanced search with Rulespace query builder\n\n**Programmatic Queries:**\n- Use Portal API for advanced searches at scale\n- Filter by data type, date range, taxonomy, or metadata fields\n- Download results as tabulated metadata summaries or XML records\n\n**Example API Query Pattern:**\n```python\nimport requests\n\n# Search for samples from a specific study\nbase_url = \"https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fportal\u002Fapi\u002Fsearch\"\nparams = {\n    \"result\": \"sample\",\n    \"query\": \"study_accession=PRJEB1234\",\n    \"format\": \"json\",\n    \"limit\": 100\n}\n\nresponse = requests.get(base_url, params=params)\nsamples = response.json()\n```\n\n### 4. Data Retrieval Formats\n\n**Metadata Formats:**\n- XML (native ENA format)\n- JSON (via Portal API)\n- TSV\u002FCSV (tabulated summaries)\n\n**Sequence Data:**\n- FASTQ (raw reads)\n- BAM\u002FCRAM (aligned reads)\n- FASTA (assembled sequences)\n- EMBL flat file format (annotated sequences)\n\n**Download Methods:**\n- Direct API download (small files)\n- FTP for bulk data transfer\n- Aspera for high-speed transfer of large datasets\n- enaBrowserTools command-line utility for bulk downloads\n\n### 5. Common Use Cases\n\n**Retrieve raw sequencing reads by accession:**\n```python\n# Download run files using Browser API\naccession = \"ERR123456\"\nurl = f\"https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fbrowser\u002Fapi\u002Fxml\u002F{accession}\"\n```\n\n**Search for all samples in a study:**\n```python\n# Use Portal API to list samples\nstudy_id = \"PRJNA123456\"\nurl = f\"https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fportal\u002Fapi\u002Fsearch?result=sample&query=study_accession={study_id}&format=tsv\"\n```\n\n**Find assemblies for a specific organism:**\n```python\n# Search assemblies by taxonomy\norganism = \"Escherichia coli\"\nurl = f\"https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Fportal\u002Fapi\u002Fsearch?result=assembly&query=tax_tree({organism})&format=json\"\n```\n\n**Get taxonomic lineage:**\n```python\n# Query taxonomy API\ntaxon_id = \"562\"  # E. coli\nurl = f\"https:\u002F\u002Fwww.ebi.ac.uk\u002Fena\u002Ftaxonomy\u002Frest\u002Ftax-id\u002F{taxon_id}\"\n```\n\n### 6. Integration with Analysis Pipelines\n\n**Bulk Download Pattern:**\n1. Search for accessions matching criteria using Portal API\n2. Extract file URLs from search results\n3. Download files via FTP or using enaBrowserTools\n4. Process downloaded data in pipeline\n\n**BLAST Integration:**\nIntegrate with EBI's NCBI BLAST service (REST\u002FSOAP API) for sequence similarity searches against ENA sequences.\n\n### 7. Best Practices\n\n**Rate Limiting:**\n- Implement exponential backoff when receiving HTTP 429 responses\n- Batch requests when possible to stay within 50 req\u002Fsec limit\n- Use bulk download tools for large datasets instead of iterating API calls\n\n**Data Citation:**\n- Always cite using Study\u002FProject accessions when publishing\n- Include accession numbers for specific samples, runs, or assemblies used\n\n**API Response Handling:**\n- Check HTTP status codes before processing responses\n- Parse XML responses using proper XML libraries (not regex)\n- Handle pagination for large result sets\n\n**Performance:**\n- Use FTP\u002FAspera for downloading large files (>100MB)\n- Prefer TSV\u002FJSON formats over XML when only metadata is needed\n- Cache taxonomy lookups locally when processing many records\n\n## Resources\n\nThis skill includes detailed reference documentation for working with ENA:\n\n### references\u002F\n\n**api_reference.md** - Comprehensive API endpoint documentation including:\n- Detailed parameters for Portal API and Browser API\n- Response format specifications\n- Advanced query syntax and operators\n- Field names for filtering and searching\n- Common API patterns and examples\n\nLoad this reference when constructing complex API queries, debugging API responses, or needing specific parameter details.\n",{"name":5,"description":7},"main","d046d088ce5a79a083f0abc0fe1b7ded73bc5b1f","claude-config\u002Fskills\u002Fena-database","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent","https:\u002F\u002Fgithub.com\u002FSansar35","2026-05-10 16:04:53",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add Sansar35\u002Fclaude-agent --skill ena-database",{"tool":35,"command":36},"bunx","bunx skills add Sansar35\u002Fclaude-agent --skill ena-database",{"tool":38,"command":39},"pnpm","pnpm dlx skills add Sansar35\u002Fclaude-agent --skill ena-database","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fena-database\u002FSKILL.md",true,[43,49],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},".skill-source.json","REFERENCE","参考文档",421,"https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fena-database\u002F.skill-source.json",{"path":50,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi_reference.md",13339,"https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fena-database\u002Freferences\u002Fapi_reference.md",[54,61,68,75,82,90],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":18},"01M72DVAN1JYEA302MT0C5MGD6","zustand-store-ts","Create Zustand stores following established patterns with proper TypeScript types and middleware.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M72DV8J5NBRRM4RPDFRV95N7","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzod-validation-expert\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M72DV5EMHW0BHP9BZ167MDCB","zinc-database","Access ZINC (230M+ purchasable compounds). Search by ZINC ID\u002FSMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzinc-database\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M72DV216QY0E693ZPEVQ0DBS","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":86,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M72DTXQREMCRKA8NHCVKHN4W","zapier-workflows","Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to \"run\" any process. Also handles Perplexity-based research and Google Sheets data tracking.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-workflows\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-workflows\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M72DTT17TBSJ0Y8J2XZ4C9TZ","zapier-make-patterns","No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points.  This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-make-patterns\u002FSKILL.md",[],[]]