[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BY1DPNEWG9P6B8982JN093":3,"skill-same:01M7BY1DPNEWG9P6B8982JN093":109},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":80,"commitSha":81,"skillDirectory":82,"forksCount":83,"repositoryHtmlUrl":84,"repositoryHomepageUrl":6,"ownerHtmlUrl":85,"ownerBlogUrl":86,"ownerDescription":87,"updatedAt":88,"install":89,"resources":102},"01M7BY1DPNEWG9P6B8982JN093","create-a-backend",null,"Backend architecture guidance. Use when planning, building, or migrating an API or backend; choosing between Functions, Services, containers, Workflow, Queues, and Marketplace databases; or selecting a supported backend framework or runtime.","CognitionAI\u002Fdevin-marketplace","CognitionAI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F163493330?v=4","01M7BVSRD98NC4FG8T3EZS6V5M","Cognition","01M7BVSRDX111C2XPWJ0E6MY26",29,"MIT","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fcreate-a-backend\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: create-a-backend\ndescription: Backend architecture guidance. Use when planning, building, or migrating an API or backend; choosing between Functions, Services, containers, Workflow, Queues, and Marketplace databases; or selecting a supported backend framework or runtime.\nsummary: Match backend workloads to the right architecture\nmetadata:\n  priority: 7\n  docs:\n    - \"https:\u002F\u002Fvercel.com\u002Fdocs\u002Fframeworks\u002Fbackend\"\n    - \"https:\u002F\u002Fvercel.com\u002Fdocs\u002Ffunctions\"\n    - \"https:\u002F\u002Fvercel.com\u002Fdocs\u002Fservices\"\n    - \"https:\u002F\u002Fvercel.com\u002Fdocs\u002Fqueues\"\n    - \"https:\u002F\u002Fvercel.com\u002Fdocs\u002Fworkflow\"\n    - \"https:\u002F\u002Fvercel.com\u002Fdocs\u002Fstorage\"\n  sitemap: \"https:\u002F\u002Fvercel.com\u002Fsitemap.xml\"\n  pathPatterns:\n    - 'Dockerfile.vercel'\n    - 'Containerfile.vercel'\n  promptSignals:\n    phrases:\n      - \"backend on vercel\"\n      - \"vercel backend\"\n      - \"build a backend\"\n      - \"create a backend\"\n      - \"deploy my backend\"\n      - \"backend architecture\"\n    allOf:\n      - [backend, vercel]\n      - [backend, docker]\n      - [backend, node]\n      - [backend, python]\n      - [backend, queue]\n    anyOf:\n      - \"api\"\n      - \"database\"\n      - \"service\"\n      - \"workflow\"\n    noneOf: []\n    minScore: 6\nretrieval:\n  aliases:\n    - Vercel backend\n    - backend architecture\n    - backend framework\n  intents:\n    - build a backend\n    - choose backend products\n    - deploy an existing API or server\n    - select a Node.js or Python backend framework\n  entities:\n    - Vercel Functions\n    - Vercel Services\n    - Vercel Queues\n    - Vercel Workflow\n    - Vercel Marketplace\n    - container images\n---\n\n# Create a Backend\n\nHelp the user create a backend by choosing an architecture before reaching for implementation details. Start from the workload, not the programming language. Vercel runs complex backend applications, not just frontends.\n\n## Product map\n\n| Need | Vercel product |\n| --- | --- |\n| HTTP APIs, webhooks, streaming, or framework server code | **[Vercel Functions](https:\u002F\u002Fvercel.com\u002Fdocs\u002Ffunctions) with [Fluid compute](https:\u002F\u002Fvercel.com\u002Fdocs\u002Ffluid-compute)** |\n| Bidirectional realtime connections (WebSockets) | **[Vercel Functions with Fluid compute](https:\u002F\u002Fvercel.com\u002Fdocs\u002Ffunctions\u002Fwebsockets)**; no separate realtime service required |\n| A frontend and one or more backends (API endpoints) that deploy together | **[Vercel Services](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fservices)** |\n| An existing Dockerfile, custom runtime, or system dependencies | **[Container images](https:\u002F\u002Fvercel.com\u002Fdocs\u002Ffunctions\u002Fcontainer-images)** on Vercel Functions, optionally composed with Services |\n| Durable multi-step work with retries, sleeps, or external events | **[Vercel Workflow](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fworkflow)** |\n| Background jobs, buffering, fan-out, or direct message routing | **[Vercel Queues](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fqueues)** |\n| Scheduled HTTP work | **[Vercel Cron Jobs](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fcron-jobs)**; use Workflow when the job itself must be durable |\n| Postgres, Redis, NoSQL, vector, or other application data | **[Storage integrations from the Vercel Marketplace](https:\u002F\u002Fvercel.com\u002Fmarketplace\u002Fcategory\u002Fstorage)** |\n| Files and user uploads | **[Vercel Blob](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fstorage\u002Fvercel-blob)** |\n| Global, read-heavy configuration | **[Global Config](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fglobal-config)** |\n\nUse Functions for the normal request\u002Fresponse backend. Use Services when independently built components should share one deployment, routing layer, preview URL, and rollback. Use separate Vercel projects when components need independent release cycles.\n\nPrefer a native Functions runtime for supported frameworks. Use container images when the application already has a Dockerfile or requires a custom runtime or system dependencies. They run as autoscaling, stateless Functions rather than always-on container hosts.\n\nChoose Queues for background jobs, buffering, fan-out, and message routing. Choose Workflow for durable multi-step business logic.\n\n## Databases and data stores\n\nProvision data stores through the Marketplace so credentials are injected into the project and environments stay connected. Check the current catalog before choosing a provider.\n\n- **Postgres:** Neon, Supabase, AWS\u002FAurora, Nile, Prisma\n- **MySQL:** AWS\u002FAurora\n- **Redis and key-value:** Upstash, Redis\n- **Document and NoSQL:** MongoDB Atlas, AWS\n- **SQLite:** Turso\n- **Realtime application backend:** Convex\n- **Analytics:** MotherDuck\n\nKeep the database close to the Functions region and use a serverless-compatible connection or pool.\n\n## Backend frameworks\n\nVercel provides first-class [backend examples and integrations](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fframeworks\u002Fbackend) for these frameworks:\n\n- **Node.js and TypeScript:** Elysia, Express, Fastify, H3, Hono, Koa, NestJS, Nitro, and xmcp. Next.js Route Handlers are the natural choice when the backend belongs to a Next.js application.\n- **Python:** FastAPI, Flask, and Django. Other WSGI or ASGI applications can run when they export a compatible `app`, with additional configuration as needed.\n- **Go:** supported as a Vercel Functions runtime.\n\nFrontend and backend combinations, for example a Next.js\u002FVite\u002FSvelteKit frontend with a FastAPI\u002FFlask\u002FExpress\u002FGo backend, can be deployed together in one project using Services.\n\nPrefer the user's existing framework. For a new project, choose based on ecosystem and application needs.\n\n## Work sequence\n\n1. Identify synchronous requests, asynchronous work, persistent data, and independently deployed components.\n2. Select the products from the map, then select the framework.\n3. Load the focused skill for implementation: `vercel-functions`, `vercel-services`, `workflow`, `vercel-storage`, or `marketplace`.\n4. Confirm function limits, regions, environment variables, observability, and current product availability in the official docs before deployment.\n","# Create a Backend\n\nHelp the user create a backend by choosing an architecture before reaching for implementation details. Start from the workload, not the programming language. Vercel runs complex backend applications, not just frontends.\n\n## Product map\n\n| Need | Vercel product |\n| --- | --- |\n| HTTP APIs, webhooks, streaming, or framework server code | **[Vercel Functions](https:\u002F\u002Fvercel.com\u002Fdocs\u002Ffunctions) with [Fluid compute](https:\u002F\u002Fvercel.com\u002Fdocs\u002Ffluid-compute)** |\n| Bidirectional realtime connections (WebSockets) | **[Vercel Functions with Fluid compute](https:\u002F\u002Fvercel.com\u002Fdocs\u002Ffunctions\u002Fwebsockets)**; no separate realtime service required |\n| A frontend and one or more backends (API endpoints) that deploy together | **[Vercel Services](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fservices)** |\n| An existing Dockerfile, custom runtime, or system dependencies | **[Container images](https:\u002F\u002Fvercel.com\u002Fdocs\u002Ffunctions\u002Fcontainer-images)** on Vercel Functions, optionally composed with Services |\n| Durable multi-step work with retries, sleeps, or external events | **[Vercel Workflow](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fworkflow)** |\n| Background jobs, buffering, fan-out, or direct message routing | **[Vercel Queues](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fqueues)** |\n| Scheduled HTTP work | **[Vercel Cron Jobs](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fcron-jobs)**; use Workflow when the job itself must be durable |\n| Postgres, Redis, NoSQL, vector, or other application data | **[Storage integrations from the Vercel Marketplace](https:\u002F\u002Fvercel.com\u002Fmarketplace\u002Fcategory\u002Fstorage)** |\n| Files and user uploads | **[Vercel Blob](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fstorage\u002Fvercel-blob)** |\n| Global, read-heavy configuration | **[Global Config](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fglobal-config)** |\n\nUse Functions for the normal request\u002Fresponse backend. Use Services when independently built components should share one deployment, routing layer, preview URL, and rollback. Use separate Vercel projects when components need independent release cycles.\n\nPrefer a native Functions runtime for supported frameworks. Use container images when the application already has a Dockerfile or requires a custom runtime or system dependencies. They run as autoscaling, stateless Functions rather than always-on container hosts.\n\nChoose Queues for background jobs, buffering, fan-out, and message routing. Choose Workflow for durable multi-step business logic.\n\n## Databases and data stores\n\nProvision data stores through the Marketplace so credentials are injected into the project and environments stay connected. Check the current catalog before choosing a provider.\n\n- **Postgres:** Neon, Supabase, AWS\u002FAurora, Nile, Prisma\n- **MySQL:** AWS\u002FAurora\n- **Redis and key-value:** Upstash, Redis\n- **Document and NoSQL:** MongoDB Atlas, AWS\n- **SQLite:** Turso\n- **Realtime application backend:** Convex\n- **Analytics:** MotherDuck\n\nKeep the database close to the Functions region and use a serverless-compatible connection or pool.\n\n## Backend frameworks\n\nVercel provides first-class [backend examples and integrations](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fframeworks\u002Fbackend) for these frameworks:\n\n- **Node.js and TypeScript:** Elysia, Express, Fastify, H3, Hono, Koa, NestJS, Nitro, and xmcp. Next.js Route Handlers are the natural choice when the backend belongs to a Next.js application.\n- **Python:** FastAPI, Flask, and Django. Other WSGI or ASGI applications can run when they export a compatible `app`, with additional configuration as needed.\n- **Go:** supported as a Vercel Functions runtime.\n\nFrontend and backend combinations, for example a Next.js\u002FVite\u002FSvelteKit frontend with a FastAPI\u002FFlask\u002FExpress\u002FGo backend, can be deployed together in one project using Services.\n\nPrefer the user's existing framework. For a new project, choose based on ecosystem and application needs.\n\n## Work sequence\n\n1. Identify synchronous requests, asynchronous work, persistent data, and independently deployed components.\n2. Select the products from the map, then select the framework.\n3. Load the focused skill for implementation: `vercel-functions`, `vercel-services`, `workflow`, `vercel-storage`, or `marketplace`.\n4. Confirm function limits, regions, environment variables, observability, and current product availability in the official docs before deployment.\n",{"name":5,"summary":24,"metadata":25,"retrieval":65,"description":7},"Match backend workloads to the right architecture",{"docs":26,"sitemap":33,"priority":34,"pathPatterns":35,"promptSignals":38},[27,28,29,30,31,32],"https:\u002F\u002Fvercel.com\u002Fdocs\u002Fframeworks\u002Fbackend","https:\u002F\u002Fvercel.com\u002Fdocs\u002Ffunctions","https:\u002F\u002Fvercel.com\u002Fdocs\u002Fservices","https:\u002F\u002Fvercel.com\u002Fdocs\u002Fqueues","https:\u002F\u002Fvercel.com\u002Fdocs\u002Fworkflow","https:\u002F\u002Fvercel.com\u002Fdocs\u002Fstorage","https:\u002F\u002Fvercel.com\u002Fsitemap.xml",7,[36,37],"Dockerfile.vercel","Containerfile.vercel",{"allOf":39,"anyOf":51,"noneOf":56,"phrases":57,"minScore":64},[40,43,45,47,49],[41,42],"backend","vercel",[41,44],"docker",[41,46],"node",[41,48],"python",[41,50],"queue",[52,53,54,55],"api","database","service","workflow",[],[58,59,60,61,62,63],"backend on vercel","vercel backend","build a backend","create a backend","deploy my backend","backend architecture",6,{"aliases":66,"intents":69,"entities":73},[67,63,68],"Vercel backend","backend framework",[60,70,71,72],"choose backend products","deploy an existing API or server","select a Node.js or Python backend framework",[74,75,76,77,78,79],"Vercel Functions","Vercel Services","Vercel Queues","Vercel Workflow","Vercel Marketplace","container images","main","9836d94e88404aabb682086405c2aa9cba7657ac","plugins\u002Fvercel\u002Fskills\u002Fcreate-a-backend",156,"https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace","https:\u002F\u002Fgithub.com\u002FCognitionAI","https:\u002F\u002Fcognition.ai\u002F","Makers of Devin, the AI software engineer.","2026-11-13 07:08:23",{"source":8,"skillName":5,"commands":90,"prompt":100,"zipAvailable":101},[91,94,97],{"tool":92,"command":93},"npx","npx skills add CognitionAI\u002Fdevin-marketplace --skill create-a-backend",{"tool":95,"command":96},"bunx","bunx skills add CognitionAI\u002Fdevin-marketplace --skill create-a-backend",{"tool":98,"command":99},"pnpm","pnpm dlx skills add CognitionAI\u002Fdevin-marketplace --skill create-a-backend","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fcreate-a-backend\u002FSKILL.md",true,[103],{"path":104,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":107,"sourceHtmlUrl":108},"agents\u002Fopenai.yaml","REFERENCE","参考文档",190,"https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fcreate-a-backend\u002Fagents\u002Fopenai.yaml",[110,116,122,128,135,142],{"skillNo":111,"name":112,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M7BYC4AJGM98P2G9JH7QS24Z","business-data","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fwindsor-ai\u002Fskills\u002Fbusiness-data\u002FSKILL.md",[],[],{"skillNo":117,"name":55,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":19},"01M7BYBZ0CD4CBCPZHRZ551BNK","Creates durable, resumable workflows using Vercel's Workflow SDK. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of \"workflow\", \"durable functions\", \"resumable\", \"workflow sdk\", \"queue\", \"event\", \"push\", \"subscribe\", or step-based orchestration.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fworkflow\u002Fupstream\u002FSKILL.md",[],[],{"skillNo":123,"name":55,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":19},"01M7BYB1XSZHKHD8JZTQJ62JN0","Vercel Workflow SDK expert guidance. Use when building durable workflows, long-running tasks, API routes or agents that need pause\u002Fresume, retries, step-based execution, or crash-safe orchestration with Vercel Workflow.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fworkflow\u002FSKILL.md",[],[],{"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":134,"publishedAt":19},"01M7BYASGMK935J33E21N5WTW0","verification","Full-story verification — infers what the user is building, then verifies the complete flow end-to-end: browser → API → data → response. Triggers on dev server start and 'why isn't this working' signals.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fverification\u002FSKILL.md",[],[],{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":19},"01M7BY9WJERKSKEH9HK6E71GW2","vercel-storage","Vercel storage expert guidance — Blob, Global Config (formerly Edge Config), and Marketplace storage (Neon Postgres, Upstash Redis). Use when choosing, configuring, or using data storage with Vercel applications.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fvercel-storage\u002FSKILL.md",[],[],{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":19},"01M7BY9N034894YV2J9DCRZHYS","vercel-services","Configure and troubleshoot Vercel Services for multiple frontends and backends in one project. Use when composing a polyglot or multi-service application on one Vercel deployment; defining the `services` key, service-targeted rewrites, or service bindings in `vercel.json`; or running all services with `vercel dev`.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fvercel-services\u002FSKILL.md",[],[]]