[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CJ5TYNZ0DS4ZF2C3G5DNHV":3,"skill-same:01M6CJ5TYNZ0DS4ZF2C3G5DNHV":74},{"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":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":6,"updatedAt":59,"install":60,"resources":73},"01M6CJ5TYNZ0DS4ZF2C3G5DNHV","ai-ml-api-automation",null,"Automate AI ML API tasks via Rube MCP (Composio). Always search tools first for current schemas.","openteams-lab\u002Fopenteams","openteams-lab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F260174438?v=4","01M6CJ3RQG7RNB6WD3MZHXA49K","Open Teams","01M6CJ3RVFC9PN20ARS8AP0S0R",588,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fopenteams-lab\u002Fopenteams\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fai-ml-api-automation\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],"automation","ml","api","ai ml","ai ml api automation","MCP","tasks","search","Tools","first","automate","2026-11-10 10:12:30",false,"---\nname: ai-ml-api-automation\ndescription: \"Automate AI ML API tasks via Rube MCP (Composio). Always search tools first for current schemas.\"\nrequires:\n  mcp: [rube]\n---\n\n# AI ML API Automation via Rube MCP\n\nAutomate AI ML API operations through Composio's AI ML API toolkit via Rube MCP.\n\n**Toolkit docs**: [composio.dev\u002Ftoolkits\u002Fai_ml_api](https:\u002F\u002Fcomposio.dev\u002Ftoolkits\u002Fai_ml_api)\n\n## Prerequisites\n\n- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)\n- Active AI ML API connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `ai_ml_api`\n- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas\n\n## Setup\n\n**Get Rube MCP**: Add `https:\u002F\u002Frube.app\u002Fmcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.\n\n1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds\n2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `ai_ml_api`\n3. If connection is not ACTIVE, follow the returned auth link to complete setup\n4. Confirm connection status shows ACTIVE before running any workflows\n\n## Tool Discovery\n\nAlways discover available tools before executing workflows:\n\n```\nRUBE_SEARCH_TOOLS\nqueries: [{use_case: \"AI ML API operations\", known_fields: \"\"}]\nsession: {generate_id: true}\n```\n\nThis returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.\n\n## Core Workflow Pattern\n\n### Step 1: Discover Available Tools\n\n```\nRUBE_SEARCH_TOOLS\nqueries: [{use_case: \"your specific AI ML API task\"}]\nsession: {id: \"existing_session_id\"}\n```\n\n### Step 2: Check Connection\n\n```\nRUBE_MANAGE_CONNECTIONS\ntoolkits: [\"ai_ml_api\"]\nsession_id: \"your_session_id\"\n```\n\n### Step 3: Execute Tools\n\n```\nRUBE_MULTI_EXECUTE_TOOL\ntools: [{\n  tool_slug: \"TOOL_SLUG_FROM_SEARCH\",\n  arguments: {\u002F* schema-compliant args from search results *\u002F}\n}]\nmemory: {}\nsession_id: \"your_session_id\"\n```\n\n## Known Pitfalls\n\n- **Always search first**: Tool schemas change. Never hardcode tool slugs or arguments without calling `RUBE_SEARCH_TOOLS`\n- **Check connection**: Verify `RUBE_MANAGE_CONNECTIONS` shows ACTIVE status before executing tools\n- **Schema compliance**: Use exact field names and types from the search results\n- **Memory parameter**: Always include `memory` in `RUBE_MULTI_EXECUTE_TOOL` calls, even if empty (`{}`)\n- **Session reuse**: Reuse session IDs within a workflow. Generate new ones for new workflows\n- **Pagination**: Check responses for pagination tokens and continue fetching until complete\n\n## Quick Reference\n\n| Operation | Approach |\n|-----------|----------|\n| Find tools | `RUBE_SEARCH_TOOLS` with AI ML API-specific use case |\n| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `ai_ml_api` |\n| Execute | `RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs |\n| Bulk ops | `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` |\n| Full schema | `RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef` |\n\n---\n*Powered by [Composio](https:\u002F\u002Fcomposio.dev)*\n","# AI ML API Automation via Rube MCP\n\nAutomate AI ML API operations through Composio's AI ML API toolkit via Rube MCP.\n\n**Toolkit docs**: [composio.dev\u002Ftoolkits\u002Fai_ml_api](https:\u002F\u002Fcomposio.dev\u002Ftoolkits\u002Fai_ml_api)\n\n## Prerequisites\n\n- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)\n- Active AI ML API connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `ai_ml_api`\n- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas\n\n## Setup\n\n**Get Rube MCP**: Add `https:\u002F\u002Frube.app\u002Fmcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.\n\n1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds\n2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `ai_ml_api`\n3. If connection is not ACTIVE, follow the returned auth link to complete setup\n4. Confirm connection status shows ACTIVE before running any workflows\n\n## Tool Discovery\n\nAlways discover available tools before executing workflows:\n\n```\nRUBE_SEARCH_TOOLS\nqueries: [{use_case: \"AI ML API operations\", known_fields: \"\"}]\nsession: {generate_id: true}\n```\n\nThis returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.\n\n## Core Workflow Pattern\n\n### Step 1: Discover Available Tools\n\n```\nRUBE_SEARCH_TOOLS\nqueries: [{use_case: \"your specific AI ML API task\"}]\nsession: {id: \"existing_session_id\"}\n```\n\n### Step 2: Check Connection\n\n```\nRUBE_MANAGE_CONNECTIONS\ntoolkits: [\"ai_ml_api\"]\nsession_id: \"your_session_id\"\n```\n\n### Step 3: Execute Tools\n\n```\nRUBE_MULTI_EXECUTE_TOOL\ntools: [{\n  tool_slug: \"TOOL_SLUG_FROM_SEARCH\",\n  arguments: {\u002F* schema-compliant args from search results *\u002F}\n}]\nmemory: {}\nsession_id: \"your_session_id\"\n```\n\n## Known Pitfalls\n\n- **Always search first**: Tool schemas change. Never hardcode tool slugs or arguments without calling `RUBE_SEARCH_TOOLS`\n- **Check connection**: Verify `RUBE_MANAGE_CONNECTIONS` shows ACTIVE status before executing tools\n- **Schema compliance**: Use exact field names and types from the search results\n- **Memory parameter**: Always include `memory` in `RUBE_MULTI_EXECUTE_TOOL` calls, even if empty (`{}`)\n- **Session reuse**: Reuse session IDs within a workflow. Generate new ones for new workflows\n- **Pagination**: Check responses for pagination tokens and continue fetching until complete\n\n## Quick Reference\n\n| Operation | Approach |\n|-----------|----------|\n| Find tools | `RUBE_SEARCH_TOOLS` with AI ML API-specific use case |\n| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `ai_ml_api` |\n| Execute | `RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs |\n| Bulk ops | `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` |\n| Full schema | `RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef` |\n\n---\n*Powered by [Composio](https:\u002F\u002Fcomposio.dev)*\n",{"name":5,"requires":48,"description":7},{"mcp":49},[50],"rube","main","4180cbf3e82c49da08cab01820d0c559313b3761","assets\u002Fskills\u002Fai-ml-api-automation",76,"https:\u002F\u002Fgithub.com\u002Fopenteams-lab\u002Fopenteams","https:\u002F\u002Fopenteams-lab.com","https:\u002F\u002Fgithub.com\u002Fopenteams-lab","https:\u002F\u002Fopenteams-lab.com\u002F","2026-11-10 13:48:49",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add openteams-lab\u002Fopenteams --skill ai-ml-api-automation",{"tool":66,"command":67},"bunx","bunx skills add openteams-lab\u002Fopenteams --skill ai-ml-api-automation",{"tool":69,"command":70},"pnpm","pnpm dlx skills add openteams-lab\u002Fopenteams --skill ai-ml-api-automation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenteams-lab\u002Fopenteams\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fai-ml-api-automation\u002FSKILL.md",true,[],[75,100,125,136,145,154],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":83,"publishedAt":43},"01M6CMDVAZMAZMCWBGC2G37B4J","cloudflare","Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task.","https:\u002F\u002Fgithub.com\u002Fopenteams-lab\u002Fopenteams\u002Fblob\u002Fmain\u002Fopenteams-cli\u002Fpackages\u002Fopenteams-cli\u002Ftest\u002Ffixture\u002Fskills\u002Fcloudflare\u002FSKILL.md",[81,82],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},[77,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99],"objects","networking","task","workers","use","ddos","infrastructure-as-code","waf","terraform","code","development","infrastructure","storage","security","sdk","agents sdk",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":110,"publishedAt":43},"01M6CMDRTM6DKWD571PY87K3CC","agents-sdk","Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks.","https:\u002F\u002Fgithub.com\u002Fopenteams-lab\u002Fopenteams\u002Fblob\u002Fmain\u002Fopenteams-cli\u002Fpackages\u002Fopenteams-cli\u002Ftest\u002Ffixture\u002Fskills\u002Fagents-sdk\u002FSKILL.md",[106,109],{"categoryNo":107,"categoryName":108,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[99,98,111,112,77,113,114,115,116,117,118,119,120,87,121,38,37,122,123,124],"rpc","state management","integration","websocket","real-time","mcp servers","applications","state","hooks","cloudflare workers","build","ai agents","workflows","react",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":134,"publishedAt":43},"01M6CMDP9NZPGWFJ1Q678D6RXK","zyte-api-automation","Automate Zyte API tasks via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fopenteams-lab\u002Fopenteams\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fzyte-api-automation\u002FSKILL.md",[131,132,133],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},[32,34,135,37,38,39,40,41,42],"zyte api automation",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":143,"publishedAt":43},"01M6CMDKGPNWJG6SRCNQJMPY9D","zylvie-automation","Automate Zylvie tasks via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fopenteams-lab\u002Fopenteams\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fzylvie-automation\u002FSKILL.md",[142],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[144,32,38,37,39,40,41,42],"zylvie automation",{"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":43},"01M6CMDGPT353ZHSBGKWSEAR2W","zoominfo-automation","Automate Zoominfo tasks via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fopenteams-lab\u002Fopenteams\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fzoominfo-automation\u002FSKILL.md",[151],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[32,153,37,38,39,40,41,42],"zoominfo automation",{"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":161,"publishedAt":43},"01M6CMDDV7FSVNANZ090ZWR612","zoho_mail-automation","Automate Zoho Mail tasks via Rube MCP (Composio): email sending, folders, labels, and mailbox management. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fopenteams-lab\u002Fopenteams\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fzoho_mail-automation\u002FSKILL.md",[160],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[162,163,32,37,38,39,164,40,41,42,165],"zoho mail automation","zoho","email","management"]