[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JM7RJ53765CXYWWTN4VNKB":3,"skill-same:01M6JM7RJ53765CXYWWTN4VNKB":95},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6JM7RJ53765CXYWWTN4VNKB","uniprot-database",null,"Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot\u002FTrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP\u002FREST work or UniProt-specific control.","transaurus\u002Fstaging-davila7-claude-code-templates","transaurus","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F210882017?v=4","01M6JH1R6ZCRXGJCTDP5ZKZBE6","Page Turner Agent","01M6JH1RBBR2P6Y0XWDGM4B0G7",0,"MIT","https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Funiprot-database\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"database","uniprot database","work","for","interface","with","retrieval","id","control","rest api","databases","use","python","access","api","bioservices","REST","services","http","workflows","2026-11-10 10:12:30",false,"---\nname: uniprot-database\ndescription: \"Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot\u002FTrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP\u002FREST work or UniProt-specific control.\"\n---\n\n# UniProt Database\n\n## Overview\n\nUniProt is the world's leading comprehensive protein sequence and functional information resource. Search proteins by name, gene, or accession, retrieve sequences in FASTA format, perform ID mapping across databases, access Swiss-Prot\u002FTrEMBL annotations via REST API for protein analysis.\n\n## When to Use This Skill\n\nThis skill should be used when:\n- Searching for protein entries by name, gene symbol, accession, or organism\n- Retrieving protein sequences in FASTA or other formats\n- Mapping identifiers between UniProt and external databases (Ensembl, RefSeq, PDB, etc.)\n- Accessing protein annotations including GO terms, domains, and functional descriptions\n- Batch retrieving multiple protein entries efficiently\n- Querying reviewed (Swiss-Prot) vs. unreviewed (TrEMBL) protein data\n- Streaming large protein datasets\n- Building custom queries with field-specific search syntax\n\n## Core Capabilities\n\n### 1. Searching for Proteins\n\nSearch UniProt using natural language queries or structured search syntax.\n\n**Common search patterns:**\n```python\n# Search by protein name\nquery = \"insulin AND organism_name:\\\"Homo sapiens\\\"\"\n\n# Search by gene name\nquery = \"gene:BRCA1 AND reviewed:true\"\n\n# Search by accession\nquery = \"accession:P12345\"\n\n# Search by sequence length\nquery = \"length:[100 TO 500]\"\n\n# Search by taxonomy\nquery = \"taxonomy_id:9606\"  # Human proteins\n\n# Search by GO term\nquery = \"go:0005515\"  # Protein binding\n```\n\nUse the API search endpoint: `https:\u002F\u002Frest.uniprot.org\u002Funiprotkb\u002Fsearch?query={query}&format={format}`\n\n**Supported formats:** JSON, TSV, Excel, XML, FASTA, RDF, TXT\n\n### 2. Retrieving Individual Protein Entries\n\nRetrieve specific protein entries by accession number.\n\n**Accession number formats:**\n- Classic: P12345, Q1AAA9, O15530 (6 characters: letter + 5 alphanumeric)\n- Extended: A0A022YWF9 (10 characters for newer entries)\n\n**Retrieve endpoint:** `https:\u002F\u002Frest.uniprot.org\u002Funiprotkb\u002F{accession}.{format}`\n\nExample: `https:\u002F\u002Frest.uniprot.org\u002Funiprotkb\u002FP12345.fasta`\n\n### 3. Batch Retrieval and ID Mapping\n\nMap protein identifiers between different database systems and retrieve multiple entries efficiently.\n\n**ID Mapping workflow:**\n1. Submit mapping job to: `https:\u002F\u002Frest.uniprot.org\u002Fidmapping\u002Frun`\n2. Check job status: `https:\u002F\u002Frest.uniprot.org\u002Fidmapping\u002Fstatus\u002F{jobId}`\n3. Retrieve results: `https:\u002F\u002Frest.uniprot.org\u002Fidmapping\u002Fresults\u002F{jobId}`\n\n**Supported databases for mapping:**\n- UniProtKB AC\u002FID\n- Gene names\n- Ensembl, RefSeq, EMBL\n- PDB, AlphaFoldDB\n- KEGG, GO terms\n- And many more (see `\u002Freferences\u002Fid_mapping_databases.md`)\n\n**Limitations:**\n- Maximum 100,000 IDs per job\n- Results stored for 7 days\n\n### 4. Streaming Large Result Sets\n\nFor large queries that exceed pagination limits, use the stream endpoint:\n\n`https:\u002F\u002Frest.uniprot.org\u002Funiprotkb\u002Fstream?query={query}&format={format}`\n\nThe stream endpoint returns all results without pagination, suitable for downloading complete datasets.\n\n### 5. Customizing Retrieved Fields\n\nSpecify exactly which fields to retrieve for efficient data transfer.\n\n**Common fields:**\n- `accession` - UniProt accession number\n- `id` - Entry name\n- `gene_names` - Gene name(s)\n- `organism_name` - Organism\n- `protein_name` - Protein names\n- `sequence` - Amino acid sequence\n- `length` - Sequence length\n- `go_*` - Gene Ontology annotations\n- `cc_*` - Comment fields (function, interaction, etc.)\n- `ft_*` - Feature annotations (domains, sites, etc.)\n\n**Example:** `https:\u002F\u002Frest.uniprot.org\u002Funiprotkb\u002Fsearch?query=insulin&fields=accession,gene_names,organism_name,length,sequence&format=tsv`\n\nSee `\u002Freferences\u002Fapi_fields.md` for complete field list.\n\n## Python Implementation\n\nFor programmatic access, use the provided helper script `scripts\u002Funiprot_client.py` which implements:\n\n- `search_proteins(query, format)` - Search UniProt with any query\n- `get_protein(accession, format)` - Retrieve single protein entry\n- `map_ids(ids, from_db, to_db)` - Map between identifier types\n- `batch_retrieve(accessions, format)` - Retrieve multiple entries\n- `stream_results(query, format)` - Stream large result sets\n\n**Alternative Python packages:**\n- **Unipressed**: Modern, typed Python client for UniProt REST API\n- **bioservices**: Comprehensive bioinformatics web services client\n\n## Query Syntax Examples\n\n**Boolean operators:**\n```\nkinase AND organism_name:human\n(diabetes OR insulin) AND reviewed:true\ncancer NOT lung\n```\n\n**Field-specific searches:**\n```\ngene:BRCA1\naccession:P12345\norganism_id:9606\ntaxonomy_name:\"Homo sapiens\"\nannotation:(type:signal)\n```\n\n**Range queries:**\n```\nlength:[100 TO 500]\nmass:[50000 TO 100000]\n```\n\n**Wildcards:**\n```\ngene:BRCA*\nprotein_name:kinase*\n```\n\nSee `\u002Freferences\u002Fquery_syntax.md` for comprehensive syntax documentation.\n\n## Best Practices\n\n1. **Use reviewed entries when possible**: Filter with `reviewed:true` for Swiss-Prot (manually curated) entries\n2. **Specify format explicitly**: Choose the most appropriate format (FASTA for sequences, TSV for tabular data, JSON for programmatic parsing)\n3. **Use field selection**: Only request fields you need to reduce bandwidth and processing time\n4. **Handle pagination**: For large result sets, implement proper pagination or use the stream endpoint\n5. **Cache results**: Store frequently accessed data locally to minimize API calls\n6. **Rate limiting**: Be respectful of API resources; implement delays for large batch operations\n7. **Check data quality**: TrEMBL entries are computational predictions; Swiss-Prot entries are manually reviewed\n\n## Resources\n\n### scripts\u002F\n`uniprot_client.py` - Python client with helper functions for common UniProt operations including search, retrieval, ID mapping, and streaming.\n\n### references\u002F\n- `api_fields.md` - Complete list of available fields for customizing queries\n- `id_mapping_databases.md` - Supported databases for ID mapping operations\n- `query_syntax.md` - Comprehensive query syntax with advanced examples\n- `api_examples.md` - Code examples in multiple languages (Python, curl, R)\n\n## Additional Resources\n\n- **API Documentation**: https:\u002F\u002Fwww.uniprot.org\u002Fhelp\u002Fapi\n- **Interactive API Explorer**: https:\u002F\u002Fwww.uniprot.org\u002Fapi-documentation\n- **REST Tutorial**: https:\u002F\u002Fwww.uniprot.org\u002Fhelp\u002Funiprot_rest_tutorial\n- **Query Syntax Help**: https:\u002F\u002Fwww.uniprot.org\u002Fhelp\u002Fquery-fields\n- **SPARQL Endpoint**: https:\u002F\u002Fsparql.uniprot.org\u002F (for advanced graph queries)\n","# UniProt Database\n\n## Overview\n\nUniProt is the world's leading comprehensive protein sequence and functional information resource. Search proteins by name, gene, or accession, retrieve sequences in FASTA format, perform ID mapping across databases, access Swiss-Prot\u002FTrEMBL annotations via REST API for protein analysis.\n\n## When to Use This Skill\n\nThis skill should be used when:\n- Searching for protein entries by name, gene symbol, accession, or organism\n- Retrieving protein sequences in FASTA or other formats\n- Mapping identifiers between UniProt and external databases (Ensembl, RefSeq, PDB, etc.)\n- Accessing protein annotations including GO terms, domains, and functional descriptions\n- Batch retrieving multiple protein entries efficiently\n- Querying reviewed (Swiss-Prot) vs. unreviewed (TrEMBL) protein data\n- Streaming large protein datasets\n- Building custom queries with field-specific search syntax\n\n## Core Capabilities\n\n### 1. Searching for Proteins\n\nSearch UniProt using natural language queries or structured search syntax.\n\n**Common search patterns:**\n```python\n# Search by protein name\nquery = \"insulin AND organism_name:\\\"Homo sapiens\\\"\"\n\n# Search by gene name\nquery = \"gene:BRCA1 AND reviewed:true\"\n\n# Search by accession\nquery = \"accession:P12345\"\n\n# Search by sequence length\nquery = \"length:[100 TO 500]\"\n\n# Search by taxonomy\nquery = \"taxonomy_id:9606\"  # Human proteins\n\n# Search by GO term\nquery = \"go:0005515\"  # Protein binding\n```\n\nUse the API search endpoint: `https:\u002F\u002Frest.uniprot.org\u002Funiprotkb\u002Fsearch?query={query}&format={format}`\n\n**Supported formats:** JSON, TSV, Excel, XML, FASTA, RDF, TXT\n\n### 2. Retrieving Individual Protein Entries\n\nRetrieve specific protein entries by accession number.\n\n**Accession number formats:**\n- Classic: P12345, Q1AAA9, O15530 (6 characters: letter + 5 alphanumeric)\n- Extended: A0A022YWF9 (10 characters for newer entries)\n\n**Retrieve endpoint:** `https:\u002F\u002Frest.uniprot.org\u002Funiprotkb\u002F{accession}.{format}`\n\nExample: `https:\u002F\u002Frest.uniprot.org\u002Funiprotkb\u002FP12345.fasta`\n\n### 3. Batch Retrieval and ID Mapping\n\nMap protein identifiers between different database systems and retrieve multiple entries efficiently.\n\n**ID Mapping workflow:**\n1. Submit mapping job to: `https:\u002F\u002Frest.uniprot.org\u002Fidmapping\u002Frun`\n2. Check job status: `https:\u002F\u002Frest.uniprot.org\u002Fidmapping\u002Fstatus\u002F{jobId}`\n3. Retrieve results: `https:\u002F\u002Frest.uniprot.org\u002Fidmapping\u002Fresults\u002F{jobId}`\n\n**Supported databases for mapping:**\n- UniProtKB AC\u002FID\n- Gene names\n- Ensembl, RefSeq, EMBL\n- PDB, AlphaFoldDB\n- KEGG, GO terms\n- And many more (see `\u002Freferences\u002Fid_mapping_databases.md`)\n\n**Limitations:**\n- Maximum 100,000 IDs per job\n- Results stored for 7 days\n\n### 4. Streaming Large Result Sets\n\nFor large queries that exceed pagination limits, use the stream endpoint:\n\n`https:\u002F\u002Frest.uniprot.org\u002Funiprotkb\u002Fstream?query={query}&format={format}`\n\nThe stream endpoint returns all results without pagination, suitable for downloading complete datasets.\n\n### 5. Customizing Retrieved Fields\n\nSpecify exactly which fields to retrieve for efficient data transfer.\n\n**Common fields:**\n- `accession` - UniProt accession number\n- `id` - Entry name\n- `gene_names` - Gene name(s)\n- `organism_name` - Organism\n- `protein_name` - Protein names\n- `sequence` - Amino acid sequence\n- `length` - Sequence length\n- `go_*` - Gene Ontology annotations\n- `cc_*` - Comment fields (function, interaction, etc.)\n- `ft_*` - Feature annotations (domains, sites, etc.)\n\n**Example:** `https:\u002F\u002Frest.uniprot.org\u002Funiprotkb\u002Fsearch?query=insulin&fields=accession,gene_names,organism_name,length,sequence&format=tsv`\n\nSee `\u002Freferences\u002Fapi_fields.md` for complete field list.\n\n## Python Implementation\n\nFor programmatic access, use the provided helper script `scripts\u002Funiprot_client.py` which implements:\n\n- `search_proteins(query, format)` - Search UniProt with any query\n- `get_protein(accession, format)` - Retrieve single protein entry\n- `map_ids(ids, from_db, to_db)` - Map between identifier types\n- `batch_retrieve(accessions, format)` - Retrieve multiple entries\n- `stream_results(query, format)` - Stream large result sets\n\n**Alternative Python packages:**\n- **Unipressed**: Modern, typed Python client for UniProt REST API\n- **bioservices**: Comprehensive bioinformatics web services client\n\n## Query Syntax Examples\n\n**Boolean operators:**\n```\nkinase AND organism_name:human\n(diabetes OR insulin) AND reviewed:true\ncancer NOT lung\n```\n\n**Field-specific searches:**\n```\ngene:BRCA1\naccession:P12345\norganism_id:9606\ntaxonomy_name:\"Homo sapiens\"\nannotation:(type:signal)\n```\n\n**Range queries:**\n```\nlength:[100 TO 500]\nmass:[50000 TO 100000]\n```\n\n**Wildcards:**\n```\ngene:BRCA*\nprotein_name:kinase*\n```\n\nSee `\u002Freferences\u002Fquery_syntax.md` for comprehensive syntax documentation.\n\n## Best Practices\n\n1. **Use reviewed entries when possible**: Filter with `reviewed:true` for Swiss-Prot (manually curated) entries\n2. **Specify format explicitly**: Choose the most appropriate format (FASTA for sequences, TSV for tabular data, JSON for programmatic parsing)\n3. **Use field selection**: Only request fields you need to reduce bandwidth and processing time\n4. **Handle pagination**: For large result sets, implement proper pagination or use the stream endpoint\n5. **Cache results**: Store frequently accessed data locally to minimize API calls\n6. **Rate limiting**: Be respectful of API resources; implement delays for large batch operations\n7. **Check data quality**: TrEMBL entries are computational predictions; Swiss-Prot entries are manually reviewed\n\n## Resources\n\n### scripts\u002F\n`uniprot_client.py` - Python client with helper functions for common UniProt operations including search, retrieval, ID mapping, and streaming.\n\n### references\u002F\n- `api_fields.md` - Complete list of available fields for customizing queries\n- `id_mapping_databases.md` - Supported databases for ID mapping operations\n- `query_syntax.md` - Comprehensive query syntax with advanced examples\n- `api_examples.md` - Code examples in multiple languages (Python, curl, R)\n\n## Additional Resources\n\n- **API Documentation**: https:\u002F\u002Fwww.uniprot.org\u002Fhelp\u002Fapi\n- **Interactive API Explorer**: https:\u002F\u002Fwww.uniprot.org\u002Fapi-documentation\n- **REST Tutorial**: https:\u002F\u002Fwww.uniprot.org\u002Fhelp\u002Funiprot_rest_tutorial\n- **Query Syntax Help**: https:\u002F\u002Fwww.uniprot.org\u002Fhelp\u002Fquery-fields\n- **SPARQL Endpoint**: https:\u002F\u002Fsparql.uniprot.org\u002F (for advanced graph queries)\n",{"name":5,"description":7},"main","34fa6acf794b9a6310d298cbb8fb8c9420a5edcf","cli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Funiprot-database",2,"https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates","https:\u002F\u002Fgithub.com\u002Ftransaurus","Automated works of Page Turner","2026-03-28 10:12:59",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add transaurus\u002Fstaging-davila7-claude-code-templates --skill uniprot-database",{"tool":63,"command":64},"bunx","bunx skills add transaurus\u002Fstaging-davila7-claude-code-templates --skill uniprot-database",{"tool":66,"command":67},"pnpm","pnpm dlx skills add transaurus\u002Fstaging-davila7-claude-code-templates --skill uniprot-database","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Funiprot-database\u002FSKILL.md",true,[71,77,81,85,89],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fapi_examples.md","REFERENCE","参考文档",10348,"https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Funiprot-database\u002Freferences\u002Fapi_examples.md",{"path":78,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fapi_fields.md",7729,"https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Funiprot-database\u002Freferences\u002Fapi_fields.md",{"path":82,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fid_mapping_databases.md",6682,"https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Funiprot-database\u002Freferences\u002Fid_mapping_databases.md",{"path":86,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fquery_syntax.md",6833,"https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Funiprot-database\u002Freferences\u002Fquery_syntax.md",{"path":90,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":93,"sourceHtmlUrl":94},"scripts\u002Funiprot_client.py","SCRIPT","脚本",9982,"https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Funiprot-database\u002Fscripts\u002Funiprot_client.py",[96,124,145,167,187,212],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":105,"publishedAt":44},"01M6JMRJR3BE0HGWFWDZSB853S","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\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fzapier-make-patterns\u002FSKILL.md",[102],{"categoryNo":103,"categoryName":104,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[106,107,108,109,110,111,112,113,114,115,35,116,117,118,119,120,121,122,27,123],"zapier make patterns","patterns","make","zapier","writing","workflow","automation","code","integrations","business","power","complexity","platform","apps","how to","No-Code","which","spawner",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":44},"01M6JMR8YK6SWPCTG1MCQTMN9S","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fyeet\u002FSKILL.md",[],[126,131,132,133,134,135,136,137,138,139,140,141,35,142,143,144],"cli","github","commit","pull request","openai","pull","push","flow","open","gh","user","only","stage","github cli",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":152,"publishedAt":44},"01M6JMQNFE64ZASQK90HARRXW8","workflow-automation","Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off.  This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation.  Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility","https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fworkflow-automation\u002FSKILL.md",[151],{"categoryNo":103,"categoryName":104,"taxonomyType":21,"taxonomyTypeDesc":22},[111,112,153,154,155,43,156,157,158,159,160,161,162,163,164,165,166,29,27,123],"Workflow Automation","ai agents","accessibility","apache","execution","inngest","parallel","orchestrator","resume","n8n","payment","worker","scripts","temporal",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":44},"01M6JMQDYJ0XETERPHGDR3EVGN","trigger-dev","Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.","https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Ftrigger-dev\u002FSKILL.md",[],[174,175,176,177,178,43,179,156,157,180,35,181,182,183,184,185,186,29,27,123],"dev","trigger dev","trigger","design","typescript","async execution","first","async","developer experience","expert","task","background jobs","long",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":196,"publishedAt":44},"01M6JMQ5J6KK3GSX9FJCWWK6G6","planning-with-files","Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.","https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fplanning-with-files\u002FSKILL.md",[193],{"categoryNo":194,"categoryName":195,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",[197,198,199,29,200,111,201,202,203,204,205,26,35,206,207,208,209,210,211,27],"planning with files","planning","files","with files","storage","tasks","markdown","knowledge","projects","manus","structured output","progress","transforms","multi","output",{"skillNo":213,"name":214,"nameZh":6,"description":215,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":216,"categories":217,"keywords":220,"publishedAt":44},"01M6JMPWAT60RXXNEC4V9TRBRS","n8n-workflow-patterns","Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, or scheduled tasks.","https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fn8n\u002Fn8n-workflow-patterns\u002FSKILL.md",[218,219],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":103,"categoryName":104,"taxonomyType":21,"taxonomyTypeDesc":22},[111,221,162,222,107,223,224,43,225,202,198,24,38,226,227,228,229,230,231,232],"n8n workflow patterns","workflow patterns","n8n workflow","ai agent","architecture","planning workflow","structure","database operations","webhook","processing","http api","scheduled"]