{"about":"Paste a part's sentence into any AI agent; it installs what that tool's makers built for AI, then proves it works.","source":"https://github.com/SolenixAI/agents-marketplace","specs":{"skills":"https://agentskills.io/specification","mcp":"https://modelcontextprotocol.io/specification/latest","plugin":"https://github.com/agentplugins/agent-plugins-spec"},"read":"2026-10-19T11:26:26.567Z","parts":[{"id":"toolkit","part":"toolkit","name":"Core toolkit","maker":"Solenix","for":"The tools every AI needs to succeed.","site":"https://github.com/SolenixAI/agents-marketplace","sentence":"Set up the Solenix core toolkit for me. Run `npx skills add SolenixAI/agents-marketplace --skill toolkit`, then follow the toolkit skill.","setup":"https://github.com/SolenixAI/agents-marketplace/blob/main/skills/toolkit/SKILL.md","page":"https://solenix.dev/agents?world=toolkit","maker_source":{"blurb":"Hand-picked agent tools that install into any AI agent with one line, and uninstall with one line.","repo":{"slug":"SolenixAI/agents-marketplace","stars":1,"forks":0,"license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/332700673?v=4"},"version":null,"updated":"2026-10-12T20:37:16Z","weekly":null,"contents":[],"items":[],"parts":[],"gives":null,"refs":[{"label":"The steps your AI follows","href":"https://github.com/SolenixAI/agents-marketplace/blob/main/skills/toolkit/SKILL.md"}],"id":"maker","kind":"maker","name":"Solenix","href":"https://github.com/SolenixAI/agents-marketplace"},"pieces":[{"blurb":"The open agent skills tool - npx skills","repo":{"slug":"vercel-labs/skills","stars":35578,"forks":3035,"license":"MIT","avatar":"https://avatars.githubusercontent.com/u/108547162?v=4"},"version":"v1.7.2","updated":"2026-10-09T16:46:55Z","weekly":2665382,"contents":[],"items":["find-skills"],"parts":[{"id":"find-skills","kind":"skill","name":"Find skills","blurb":"Helps users discover and install agent skills when they ask questions like \"how do I do X\", \"find a skill for X\", \"is there a skill that can...\", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.","href":"https://github.com/vercel-labs/skills/blob/HEAD/skills/find-skills/SKILL.md"}],"gives":"Your AI finds and installs the right skill for anything you ask.","refs":[{"label":"skills.sh","href":"https://skills.sh"},{"label":"Docs","href":"https://skills.sh/docs"},{"label":"Package page","href":"https://www.npmjs.com/package/skills"},{"label":"How skills work","href":"https://agentskills.io/specification"}],"id":"skills","kind":"tool","name":"Skills","href":"https://skills.sh"}]},{"id":"vercel","part":"world","name":"Vercel","maker":"Vercel","for":"Put your website online. Your AI ships it and fixes it.","site":"https://vercel.com","sentence":"Set up Vercel for me. Run `npx skills add SolenixAI/agents-marketplace --skill vercel`, then follow the vercel skill.","setup":"https://github.com/SolenixAI/agents-marketplace/blob/main/skills/vercel/SKILL.md","page":"https://solenix.dev/agents?world=vercel","maker_source":{"blurb":"Develop. Preview. Ship.","repo":{"slug":"vercel/vercel","stars":16410,"forks":3860,"license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/14985020?v=4"},"version":null,"updated":"2026-10-18T22:06:05Z","weekly":null,"contents":[],"items":[],"parts":[],"gives":null,"refs":[{"label":"vercel.com","href":"https://vercel.com"},{"label":"The steps your AI follows","href":"https://github.com/SolenixAI/agents-marketplace/blob/main/skills/vercel/SKILL.md"}],"id":"maker","kind":"maker","name":"Vercel","href":"https://vercel.com"},"pieces":[{"blurb":"Comprehensive Vercel ecosystem plugin — relational knowledge graph, skills for every major product, specialized agents, and Vercel conventions. Turns any AI agent into a Vercel expert.","repo":{"slug":"vercel/vercel-plugin","stars":310,"forks":69,"license":null,"avatar":"https://avatars.githubusercontent.com/u/14985020?v=4"},"version":"0.54.1","updated":"2026-10-19T11:20:16Z","weekly":null,"contents":[{"label":"skills","n":35},{"label":"agents","n":3},{"label":"commands","n":5},{"label":"connector","n":1},{"label":"hooks","n":1}],"items":[],"parts":[{"id":"ai-architect","kind":"agent","name":"Ai architect","blurb":"Specializes in architecting AI-powered applications on Vercel — choosing between AI SDK patterns, configuring providers, building agents, setting up durable workflows, and integrating MCP servers. Use when designing AI features, building chatbots, or creating agentic applications.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/agents/ai-architect.md"},{"id":"deployment-expert","kind":"agent","name":"Deployment expert","blurb":"Specializes in Vercel deployment strategies, CI/CD pipelines, preview URLs, production promotions, rollbacks, environment variables, and domain configuration. Use when troubleshooting deployments, setting up CI/CD, or optimizing the deploy pipeline.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/agents/deployment-expert.md"},{"id":"performance-optimizer","kind":"agent","name":"Performance optimizer","blurb":"Specializes in optimizing Vercel application performance — Core Web Vitals, rendering strategies, caching, image optimization, font loading, edge computing, and bundle size. Use when investigating slow pages, improving Lighthouse scores, or optimizing loading performance.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/agents/performance-optimizer.md"},{"id":"_conventions","kind":"command","name":"Conventions","blurb":null,"href":"https://github.com/vercel/vercel-plugin/blob/HEAD/commands/_conventions.md"},{"id":"bootstrap","kind":"command","name":"Bootstrap","blurb":"Bootstrap a repository with Vercel-linked resources by running preflight checks, provisioning integrations, verifying env keys, and then executing db/dev startup commands safely.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/commands/bootstrap.md"},{"id":"deploy","kind":"command","name":"Deploy","blurb":"Deploy the current project to Vercel. Pass \"prod\" or \"production\" as argument to deploy to production. Default is preview deployment.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/commands/deploy.md"},{"id":"env","kind":"command","name":"Env","blurb":"Manage Vercel environment variables. Commands include list, pull, add, remove, and diff. Use to sync environment variables between Vercel and your local development environment.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/commands/env.md"},{"id":"status","kind":"command","name":"Status","blurb":"Show the status of the current Vercel project — recent deployments, linked project info, and environment overview.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/commands/status.md"},{"id":"access-protected-vercel-deployment","kind":"skill","name":"Access protected vercel deployment","blurb":"Access and test Vercel deployments protected by Vercel Authentication, SSO, or Deployment Protection. Use when curl, agent-browser, Playwright, or another automated request reaches a Vercel login or protection page; when a protected preview or production URL returns 401 or 403; when TRUSTED_SOURCES_ENVIRONMENT_MISMATCH appears; or when choosing between `vercel curl` and the `x-vercel-trusted-oidc-idp-token` header.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/access-protected-vercel-deployment/SKILL.md"},{"id":"ai-gateway","kind":"skill","name":"Ai gateway","blurb":"Vercel AI Gateway guidance for setup, model discovery, authentication, routing, fallbacks, virtual models, evaluation models, BYOK, budgets, spend reporting, observability, compatible APIs, and coding-agent configuration. Use when adding AI Gateway to an app, migrating provider calls, choosing models or providers, centralizing model configuration, evaluating application state, debugging gateway requests, or running `vercel ai-gateway` commands.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/ai-gateway/SKILL.md"},{"id":"ai-sdk","kind":"skill","name":"Ai sdk","blurb":"Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/ai-sdk/SKILL.md"},{"id":"auth","kind":"skill","name":"Auth","blurb":"Authentication integration guidance — Clerk (native Vercel Marketplace), Better Auth, Descope, and Auth0 setup for Next.js applications, plus Sign in with Vercel, Vercel Passport, and Vercel KMS. Covers server config, route handlers, proxy.ts auth patterns, sign-in/sign-up flows, and Marketplace provisioning. Use when implementing user authentication, sessions, protected routes, or protecting deployments.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/auth/SKILL.md"},{"id":"bootstrap","kind":"skill","name":"Bootstrap","blurb":"Project bootstrapping orchestrator for repos that depend on Vercel-linked resources (databases, auth, and managed integrations). Use when setting up or repairing a repository so linking, environment provisioning, env pulls, and first-run db/dev commands happen in the correct safe order.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/bootstrap/SKILL.md"},{"id":"build-agents","kind":"skill","name":"Build agents","blurb":"Default guidance for building AI agents. Use for generic requests to build, create, scaffold, design, architect, or implement an AI agent, agent app, tool-calling agent, durable agent, multi-agent system, or scheduled agent.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/build-agents/SKILL.md"},{"id":"cdn-caching","kind":"skill","name":"Cdn caching","blurb":"Debug Vercel CDN caching — cache hit rate, stale content, revalidation behavior, ISR + PPR, per-request cache reasons (cacheReason) and PPR state (ppr_state), and costs.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/cdn-caching/SKILL.md"},{"id":"chat-sdk","kind":"skill","name":"Chat sdk","blurb":"Vercel Chat SDK expert guidance. Use when building multi-platform chat bots — Slack, Telegram, Microsoft Teams, Discord, Google Chat, GitHub, Linear — with a single codebase. Covers the Chat class, adapters, threads, messages, cards, modals, streaming, state management, and webhook setup.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/chat-sdk/SKILL.md"},{"id":"create-a-backend","kind":"skill","name":"Create a backend","blurb":"Backend architecture guidance. Use when planning, building, or migrating an API or backend; choosing between Functions, Services, containers, Daemons, Workflow, Queues, and Marketplace databases; or selecting a supported backend framework or runtime.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/create-a-backend/SKILL.md"},{"id":"custom-metrics","kind":"skill","name":"Custom metrics","blurb":"Emit and query Vercel Custom Metrics. Use when instrumenting application or business measurements in Vercel Functions, using metric() from @vercel/functions, choosing metric names and attributes, or querying emitted values with vc metrics.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/custom-metrics/SKILL.md"},{"id":"daemons","kind":"skill","name":"Daemons","blurb":"Vercel Daemons guidance — long-running background workers built from a Dockerfile and declared under the `daemons` key in vercel.json. Use when running queue consumers, Celery/Sidekiq/BullMQ workers, workflow workers, or job runners next to an app on Vercel; configuring daemon instances per region, memory, or command; handling SIGTERM; or choosing between Daemons, Functions, Queues, and Workflows.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/daemons/SKILL.md"},{"id":"deployments-cicd","kind":"skill","name":"Deployments cicd","blurb":"Vercel deployment and CI/CD expert guidance. Use when deploying, promoting, rolling back, inspecting deployments, building with --prebuilt, or configuring CI workflow files for Vercel.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/deployments-cicd/SKILL.md"},{"id":"domains","kind":"skill","name":"Domains","blurb":"Search, register, connect, transfer, and renew domain names on Vercel using the CLI or Domains Registrar API. Use for domain availability and pricing, custom domains, DNS records, nameservers, ownership verification, and domain orders.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/domains/SKILL.md"},{"id":"env-vars","kind":"skill","name":"Env vars","blurb":"Vercel environment variable expert guidance. Use when working with .env files, vercel env commands, Secret or Config variable types, OIDC tokens, or managing environment-specific configuration.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/env-vars/SKILL.md"},{"id":"eve","kind":"skill","name":"Eve","blurb":"eve framework guidance for durable AI agents and agent-powered applications. Use when creating, editing, or debugging an eve project, when the user explicitly asks for eve, or when the build-agents skill has selected eve as the default framework. Covers eve's filesystem-first runtime, durable sessions, tools, skills, connections, channels, sandboxes, subagents, schedules, evals, frontend clients, and Agent Runs observability. Do not use for incidental agent mentions, generic agent-building prompts, or established non-eve stacks unless the user asks for comparison or migration.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/eve/SKILL.md"},{"id":"flags-sdk","kind":"skill","name":"Flags sdk","blurb":"Implement feature flags in Next.js or SvelteKit code with the Flags SDK (`flags` npm package). Use when installing or configuring the SDK, declaring flags with `flag()`, wiring a provider adapter (`@flags-sdk/vercel`, Statsig, LaunchDarkly, PostHog, GrowthBook, Global Config, OpenFeature, and others), using `identify`, `dedupe`, or `evaluate`, keeping pages static with precompute, setting up Flags Explorer, or encrypting flag values. For planning a flag, Vercel Flags rollouts and experiments, the `vercel flags` CLI, or other frameworks, use the `vercel-flags` skill.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/flags-sdk/SKILL.md"},{"id":"is-agentic","kind":"skill","name":"Is agentic","blurb":"Score how ready a website, domain, or public MCP endpoint is for AI agents using Is Agentic, and read or act on the resulting report. Use when asked to check a site's agent readiness, get its Is Agentic score, fetch a scored report as JSON, or fix the issues that lower a site's score.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/is-agentic/SKILL.md"},{"id":"knowledge-update","kind":"skill","name":"Knowledge update","blurb":"Corrects outdated LLM knowledge about the Vercel platform and introduces new products. Injected at session start.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/knowledge-update/SKILL.md"},{"id":"marketplace","kind":"skill","name":"Marketplace","blurb":"Vercel Marketplace expert guidance — discovering, installing, and managing third-party integrations via the `vercel integration` CLI. Use when building any app that needs an external capability without a dedicated skill — commerce (stores, storefronts, selling products), payments (checkout, subscriptions, billing), observability/monitoring, messaging/email, search, or CMS — or when discovering, installing, or managing integrations.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/marketplace/SKILL.md"},{"id":"microfrontends","kind":"skill","name":"Microfrontends","blurb":"Guide for building, configuring, and deploying microfrontends on Vercel. Use this skill when the user mentions microfrontends, multi-zones, splitting an app across teams, independent deployments, cross-app routing, incremental migration, composing multiple frontends under one domain, microfrontends.json, @vercel/microfrontends, the microfrontends local proxy, or path-based routing between Vercel projects. Also use when the user asks about shared layouts across projects, navigation between microfrontends, fallback environments, asset prefixes, or feature flag controlled routing.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/microfrontends/SKILL.md"},{"id":"queues","kind":"skill","name":"Queues","blurb":"Vercel Queues guidance — durable topics with at-least-once delivery, independent consumer groups, retries, delays, and idempotency keys via @vercel/queue (JS) or vercel-queue (Python). Use when deferring background work, buffering traffic, fanning out events, or choosing between Queues and Workflows.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/queues/SKILL.md"},{"id":"react-best-practices","kind":"skill","name":"React best practices","blurb":"React best-practices reviewer for TSX files. Triggers after editing multiple TSX components to run a condensed quality checklist covering component structure, hooks usage, accessibility, performance, and TypeScript patterns.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/react-best-practices/SKILL.md"},{"id":"routing-middleware","kind":"skill","name":"Routing middleware","blurb":"Vercel Routing Middleware guidance — request interception before cache, rewrites, redirects, personalization. Works with any framework. Supports Edge, Node.js, and Bun runtimes. Use when intercepting requests at the platform level.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/routing-middleware/SKILL.md"},{"id":"runtime-cache","kind":"skill","name":"Runtime cache","blurb":"Vercel Runtime Cache API guidance — ephemeral per-region key-value cache with tag-based invalidation. Shared across Functions, Routing Middleware, and Builds. Use when implementing caching strategies beyond framework-level caching.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/runtime-cache/SKILL.md"},{"id":"vercel-agent","kind":"skill","name":"Vercel agent","blurb":"Vercel Agent guidance — dashboard and Slack chat, code review, production investigation, approved actions, and product installation. Use when configuring or working with Vercel's AI assistant.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-agent/SKILL.md"},{"id":"vercel-cli","kind":"skill","name":"Vercel cli","blurb":"Vercel CLI expert guidance. Use when deploying, managing environment variables, linking projects, viewing logs, querying metrics, inspecting or searching request traces, debugging a deployed app on Vercel (errors, 5xx responses, timeouts, slow routes, or a single failing request), managing domains, managing feature flags with vercel flags, or interacting with the Vercel platform from the command line.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-cli/SKILL.md"},{"id":"vercel-connect","kind":"skill","name":"Vercel connect","blurb":"Vercel Connect expert guidance for securely obtaining scoped credentials for third-party services on behalf of apps or users. Use when wiring up provider API access, OAuth, API-key services, MCP servers, triggers, framework adapters, eve agent connections, or provider tokens for Passport-authenticated users.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-connect/SKILL.md"},{"id":"vercel-firewall","kind":"skill","name":"Vercel firewall","blurb":"Vercel Firewall expert guidance — automatic DDoS mitigation, the Vercel WAF (custom rules, IP blocking, managed rulesets, rate limiting), Attack Mode, system bypass, bot management, and the `vercel firewall` CLI. Use when configuring platform-level security, responding to attacks, or staging firewall rules.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-firewall/SKILL.md"},{"id":"vercel-flags","kind":"skill","name":"Vercel flags","blurb":"Feature flags, A/B tests, and gradual rollouts with Vercel Flags, in any app or framework. Use whenever the user is planning, adding, or changing a feature flag, toggle, kill switch, experiment, percentage rollout, or targeting rule, or wants to gate or hide a feature for some users, even before a library or provider is chosen. Covers choosing an integration (Flags SDK, `@vercel/flags-core`, OpenFeature), the Vercel dashboard, the `vercel flags` CLI (create, inspect, set, split, rollout, rules, segments, evaluations, archive), OIDC vs SDK keys, `FLAGS_SECRET`, and Flags Explorer overrides. For `flag()` declarations, adapters, precompute, and the Flags Explorer endpoint in Next.js or SvelteKit code, load the `flags-sdk` skill.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-flags/SKILL.md"},{"id":"vercel-functions","kind":"skill","name":"Vercel functions","blurb":"Vercel Functions expert guidance — Node.js/Bun/Python runtimes, Fluid Compute, long-duration (30 min) functions, large functions (5 GB bundles), Docker/OCI container images, plan limits, streaming, WebSockets, and Cron Jobs. Use when configuring, debugging, or optimizing server-side code running on Vercel.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-functions/SKILL.md"},{"id":"vercel-sandbox","kind":"skill","name":"Vercel sandbox","blurb":"Vercel Sandbox guidance — ephemeral Firecracker microVMs for running untrusted code safely. Supports AI agents, code generation, and experimentation. Use when executing user-generated or AI-generated code in isolation.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-sandbox/SKILL.md"},{"id":"vercel-services","kind":"skill","name":"Vercel services","blurb":"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`.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-services/SKILL.md"},{"id":"vercel-storage","kind":"skill","name":"Vercel storage","blurb":"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.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-storage/SKILL.md"},{"id":"verification","kind":"skill","name":"Verification","blurb":"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.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/verification/SKILL.md"},{"id":"workflow","kind":"skill","name":"Workflow","blurb":"Vercel Workflow SDK expert guidance. Use when building durable workflows, long-running tasks, API routes or agents that need pause/resume, retries, step-based execution, or crash-safe orchestration with Vercel Workflow.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/workflow/SKILL.md"}],"gives":"One install gives your AI everything Vercel built for it.","refs":[{"label":"Docs","href":"https://vercel.com/docs/agent-resources/vercel-plugin"},{"label":"How add-ons work","href":"https://github.com/agentplugins/agent-plugins-spec"}],"id":"plugin","kind":"plugin","name":"Extends your AI","href":"https://github.com/vercel/vercel-plugin"},{"blurb":"Comprehensive Vercel ecosystem plugin — relational knowledge graph, skills for every major product, specialized agents, and Vercel conventions. Turns any AI agent into a Vercel expert.","repo":{"slug":"vercel/vercel-plugin","stars":310,"forks":69,"license":null,"avatar":"https://avatars.githubusercontent.com/u/14985020?v=4"},"version":null,"updated":"2026-10-19T11:20:16Z","weekly":null,"contents":[{"label":"skills","n":35}],"items":["access-protected-vercel-deployment","ai-gateway","ai-sdk","auth","bootstrap","build-agents","cdn-caching","chat-sdk","create-a-backend","custom-metrics","daemons","deployments-cicd","domains","env-vars","eve","flags-sdk","is-agentic","knowledge-update","marketplace","microfrontends","queues","react-best-practices","routing-middleware","runtime-cache","vercel-agent","vercel-cli","vercel-connect","vercel-firewall","vercel-flags","vercel-functions","vercel-sandbox","vercel-services","vercel-storage","verification","workflow"],"parts":[{"id":"access-protected-vercel-deployment","kind":"skill","name":"Access protected vercel deployment","blurb":"Access and test Vercel deployments protected by Vercel Authentication, SSO, or Deployment Protection. Use when curl, agent-browser, Playwright, or another automated request reaches a Vercel login or protection page; when a protected preview or production URL returns 401 or 403; when TRUSTED_SOURCES_ENVIRONMENT_MISMATCH appears; or when choosing between `vercel curl` and the `x-vercel-trusted-oidc-idp-token` header.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/access-protected-vercel-deployment/SKILL.md"},{"id":"ai-gateway","kind":"skill","name":"Ai gateway","blurb":"Vercel AI Gateway guidance for setup, model discovery, authentication, routing, fallbacks, virtual models, evaluation models, BYOK, budgets, spend reporting, observability, compatible APIs, and coding-agent configuration. Use when adding AI Gateway to an app, migrating provider calls, choosing models or providers, centralizing model configuration, evaluating application state, debugging gateway requests, or running `vercel ai-gateway` commands.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/ai-gateway/SKILL.md"},{"id":"ai-sdk","kind":"skill","name":"Ai sdk","blurb":"Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/ai-sdk/SKILL.md"},{"id":"auth","kind":"skill","name":"Auth","blurb":"Authentication integration guidance — Clerk (native Vercel Marketplace), Better Auth, Descope, and Auth0 setup for Next.js applications, plus Sign in with Vercel, Vercel Passport, and Vercel KMS. Covers server config, route handlers, proxy.ts auth patterns, sign-in/sign-up flows, and Marketplace provisioning. Use when implementing user authentication, sessions, protected routes, or protecting deployments.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/auth/SKILL.md"},{"id":"bootstrap","kind":"skill","name":"Bootstrap","blurb":"Project bootstrapping orchestrator for repos that depend on Vercel-linked resources (databases, auth, and managed integrations). Use when setting up or repairing a repository so linking, environment provisioning, env pulls, and first-run db/dev commands happen in the correct safe order.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/bootstrap/SKILL.md"},{"id":"build-agents","kind":"skill","name":"Build agents","blurb":"Default guidance for building AI agents. Use for generic requests to build, create, scaffold, design, architect, or implement an AI agent, agent app, tool-calling agent, durable agent, multi-agent system, or scheduled agent.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/build-agents/SKILL.md"},{"id":"cdn-caching","kind":"skill","name":"Cdn caching","blurb":"Debug Vercel CDN caching — cache hit rate, stale content, revalidation behavior, ISR + PPR, per-request cache reasons (cacheReason) and PPR state (ppr_state), and costs.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/cdn-caching/SKILL.md"},{"id":"chat-sdk","kind":"skill","name":"Chat sdk","blurb":"Vercel Chat SDK expert guidance. Use when building multi-platform chat bots — Slack, Telegram, Microsoft Teams, Discord, Google Chat, GitHub, Linear — with a single codebase. Covers the Chat class, adapters, threads, messages, cards, modals, streaming, state management, and webhook setup.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/chat-sdk/SKILL.md"},{"id":"create-a-backend","kind":"skill","name":"Create a backend","blurb":"Backend architecture guidance. Use when planning, building, or migrating an API or backend; choosing between Functions, Services, containers, Daemons, Workflow, Queues, and Marketplace databases; or selecting a supported backend framework or runtime.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/create-a-backend/SKILL.md"},{"id":"custom-metrics","kind":"skill","name":"Custom metrics","blurb":"Emit and query Vercel Custom Metrics. Use when instrumenting application or business measurements in Vercel Functions, using metric() from @vercel/functions, choosing metric names and attributes, or querying emitted values with vc metrics.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/custom-metrics/SKILL.md"},{"id":"daemons","kind":"skill","name":"Daemons","blurb":"Vercel Daemons guidance — long-running background workers built from a Dockerfile and declared under the `daemons` key in vercel.json. Use when running queue consumers, Celery/Sidekiq/BullMQ workers, workflow workers, or job runners next to an app on Vercel; configuring daemon instances per region, memory, or command; handling SIGTERM; or choosing between Daemons, Functions, Queues, and Workflows.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/daemons/SKILL.md"},{"id":"deployments-cicd","kind":"skill","name":"Deployments cicd","blurb":"Vercel deployment and CI/CD expert guidance. Use when deploying, promoting, rolling back, inspecting deployments, building with --prebuilt, or configuring CI workflow files for Vercel.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/deployments-cicd/SKILL.md"},{"id":"domains","kind":"skill","name":"Domains","blurb":"Search, register, connect, transfer, and renew domain names on Vercel using the CLI or Domains Registrar API. Use for domain availability and pricing, custom domains, DNS records, nameservers, ownership verification, and domain orders.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/domains/SKILL.md"},{"id":"env-vars","kind":"skill","name":"Env vars","blurb":"Vercel environment variable expert guidance. Use when working with .env files, vercel env commands, Secret or Config variable types, OIDC tokens, or managing environment-specific configuration.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/env-vars/SKILL.md"},{"id":"eve","kind":"skill","name":"Eve","blurb":"eve framework guidance for durable AI agents and agent-powered applications. Use when creating, editing, or debugging an eve project, when the user explicitly asks for eve, or when the build-agents skill has selected eve as the default framework. Covers eve's filesystem-first runtime, durable sessions, tools, skills, connections, channels, sandboxes, subagents, schedules, evals, frontend clients, and Agent Runs observability. Do not use for incidental agent mentions, generic agent-building prompts, or established non-eve stacks unless the user asks for comparison or migration.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/eve/SKILL.md"},{"id":"flags-sdk","kind":"skill","name":"Flags sdk","blurb":"Implement feature flags in Next.js or SvelteKit code with the Flags SDK (`flags` npm package). Use when installing or configuring the SDK, declaring flags with `flag()`, wiring a provider adapter (`@flags-sdk/vercel`, Statsig, LaunchDarkly, PostHog, GrowthBook, Global Config, OpenFeature, and others), using `identify`, `dedupe`, or `evaluate`, keeping pages static with precompute, setting up Flags Explorer, or encrypting flag values. For planning a flag, Vercel Flags rollouts and experiments, the `vercel flags` CLI, or other frameworks, use the `vercel-flags` skill.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/flags-sdk/SKILL.md"},{"id":"is-agentic","kind":"skill","name":"Is agentic","blurb":"Score how ready a website, domain, or public MCP endpoint is for AI agents using Is Agentic, and read or act on the resulting report. Use when asked to check a site's agent readiness, get its Is Agentic score, fetch a scored report as JSON, or fix the issues that lower a site's score.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/is-agentic/SKILL.md"},{"id":"knowledge-update","kind":"skill","name":"Knowledge update","blurb":"Corrects outdated LLM knowledge about the Vercel platform and introduces new products. Injected at session start.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/knowledge-update/SKILL.md"},{"id":"marketplace","kind":"skill","name":"Marketplace","blurb":"Vercel Marketplace expert guidance — discovering, installing, and managing third-party integrations via the `vercel integration` CLI. Use when building any app that needs an external capability without a dedicated skill — commerce (stores, storefronts, selling products), payments (checkout, subscriptions, billing), observability/monitoring, messaging/email, search, or CMS — or when discovering, installing, or managing integrations.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/marketplace/SKILL.md"},{"id":"microfrontends","kind":"skill","name":"Microfrontends","blurb":"Guide for building, configuring, and deploying microfrontends on Vercel. Use this skill when the user mentions microfrontends, multi-zones, splitting an app across teams, independent deployments, cross-app routing, incremental migration, composing multiple frontends under one domain, microfrontends.json, @vercel/microfrontends, the microfrontends local proxy, or path-based routing between Vercel projects. Also use when the user asks about shared layouts across projects, navigation between microfrontends, fallback environments, asset prefixes, or feature flag controlled routing.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/microfrontends/SKILL.md"},{"id":"queues","kind":"skill","name":"Queues","blurb":"Vercel Queues guidance — durable topics with at-least-once delivery, independent consumer groups, retries, delays, and idempotency keys via @vercel/queue (JS) or vercel-queue (Python). Use when deferring background work, buffering traffic, fanning out events, or choosing between Queues and Workflows.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/queues/SKILL.md"},{"id":"react-best-practices","kind":"skill","name":"React best practices","blurb":"React best-practices reviewer for TSX files. Triggers after editing multiple TSX components to run a condensed quality checklist covering component structure, hooks usage, accessibility, performance, and TypeScript patterns.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/react-best-practices/SKILL.md"},{"id":"routing-middleware","kind":"skill","name":"Routing middleware","blurb":"Vercel Routing Middleware guidance — request interception before cache, rewrites, redirects, personalization. Works with any framework. Supports Edge, Node.js, and Bun runtimes. Use when intercepting requests at the platform level.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/routing-middleware/SKILL.md"},{"id":"runtime-cache","kind":"skill","name":"Runtime cache","blurb":"Vercel Runtime Cache API guidance — ephemeral per-region key-value cache with tag-based invalidation. Shared across Functions, Routing Middleware, and Builds. Use when implementing caching strategies beyond framework-level caching.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/runtime-cache/SKILL.md"},{"id":"vercel-agent","kind":"skill","name":"Vercel agent","blurb":"Vercel Agent guidance — dashboard and Slack chat, code review, production investigation, approved actions, and product installation. Use when configuring or working with Vercel's AI assistant.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-agent/SKILL.md"},{"id":"vercel-cli","kind":"skill","name":"Vercel cli","blurb":"Vercel CLI expert guidance. Use when deploying, managing environment variables, linking projects, viewing logs, querying metrics, inspecting or searching request traces, debugging a deployed app on Vercel (errors, 5xx responses, timeouts, slow routes, or a single failing request), managing domains, managing feature flags with vercel flags, or interacting with the Vercel platform from the command line.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-cli/SKILL.md"},{"id":"vercel-connect","kind":"skill","name":"Vercel connect","blurb":"Vercel Connect expert guidance for securely obtaining scoped credentials for third-party services on behalf of apps or users. Use when wiring up provider API access, OAuth, API-key services, MCP servers, triggers, framework adapters, eve agent connections, or provider tokens for Passport-authenticated users.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-connect/SKILL.md"},{"id":"vercel-firewall","kind":"skill","name":"Vercel firewall","blurb":"Vercel Firewall expert guidance — automatic DDoS mitigation, the Vercel WAF (custom rules, IP blocking, managed rulesets, rate limiting), Attack Mode, system bypass, bot management, and the `vercel firewall` CLI. Use when configuring platform-level security, responding to attacks, or staging firewall rules.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-firewall/SKILL.md"},{"id":"vercel-flags","kind":"skill","name":"Vercel flags","blurb":"Feature flags, A/B tests, and gradual rollouts with Vercel Flags, in any app or framework. Use whenever the user is planning, adding, or changing a feature flag, toggle, kill switch, experiment, percentage rollout, or targeting rule, or wants to gate or hide a feature for some users, even before a library or provider is chosen. Covers choosing an integration (Flags SDK, `@vercel/flags-core`, OpenFeature), the Vercel dashboard, the `vercel flags` CLI (create, inspect, set, split, rollout, rules, segments, evaluations, archive), OIDC vs SDK keys, `FLAGS_SECRET`, and Flags Explorer overrides. For `flag()` declarations, adapters, precompute, and the Flags Explorer endpoint in Next.js or SvelteKit code, load the `flags-sdk` skill.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-flags/SKILL.md"},{"id":"vercel-functions","kind":"skill","name":"Vercel functions","blurb":"Vercel Functions expert guidance — Node.js/Bun/Python runtimes, Fluid Compute, long-duration (30 min) functions, large functions (5 GB bundles), Docker/OCI container images, plan limits, streaming, WebSockets, and Cron Jobs. Use when configuring, debugging, or optimizing server-side code running on Vercel.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-functions/SKILL.md"},{"id":"vercel-sandbox","kind":"skill","name":"Vercel sandbox","blurb":"Vercel Sandbox guidance — ephemeral Firecracker microVMs for running untrusted code safely. Supports AI agents, code generation, and experimentation. Use when executing user-generated or AI-generated code in isolation.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-sandbox/SKILL.md"},{"id":"vercel-services","kind":"skill","name":"Vercel services","blurb":"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`.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-services/SKILL.md"},{"id":"vercel-storage","kind":"skill","name":"Vercel storage","blurb":"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.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/vercel-storage/SKILL.md"},{"id":"verification","kind":"skill","name":"Verification","blurb":"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.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/verification/SKILL.md"},{"id":"workflow","kind":"skill","name":"Workflow","blurb":"Vercel Workflow SDK expert guidance. Use when building durable workflows, long-running tasks, API routes or agents that need pause/resume, retries, step-based execution, or crash-safe orchestration with Vercel Workflow.","href":"https://github.com/vercel/vercel-plugin/blob/HEAD/skills/workflow/SKILL.md"}],"gives":"Your AI knows how to do 35 things the way Vercel does them.","refs":[{"label":"Skills directory","href":"https://skills.sh/vercel/vercel-plugin"},{"label":"How skills work","href":"https://agentskills.io/specification"}],"id":"skills","kind":"skills","name":"Skills","href":"https://github.com/vercel/vercel-plugin/tree/HEAD/skills"},{"blurb":"An MCP server for Vercel","repo":{"slug":"vercel/vercel-mcp-overview","stars":15,"forks":8,"license":null,"avatar":"https://avatars.githubusercontent.com/u/14985020?v=4"},"version":"0.0.3","updated":"2026-01-14T18:38:33.404454Z","weekly":null,"contents":[],"items":[],"parts":[],"gives":"Your AI can see and change what is in your Vercel account.","refs":[{"label":"Connection address","href":"https://mcp.vercel.com"},{"label":"Official listing","href":"https://registry.modelcontextprotocol.io/v0.1/servers/com.vercel%2Fvercel-mcp/versions/latest"},{"label":"How account links work","href":"https://modelcontextprotocol.io/specification/latest"}],"id":"connector","kind":"connector","name":"Connects to your account","href":"https://mcp.vercel.com"},{"blurb":"The command-line interface for Vercel","repo":null,"version":"64.5.0","updated":null,"weekly":2714557,"contents":[],"items":[],"parts":[],"gives":"Your AI can run Vercel for you, the way its engineers do.","refs":[{"label":"Docs","href":"https://vercel.com/docs/cli"},{"label":"Package page","href":"https://www.npmjs.com/package/vercel"}],"id":"cli","kind":"cli","name":"Runs on your computer","href":"https://vercel.com/docs/cli"},{"blurb":null,"repo":null,"version":null,"updated":null,"weekly":null,"contents":[],"items":[],"parts":[],"gives":"Anything else Vercel can do, your AI can reach directly.","refs":[{"label":"API reference","href":"https://vercel.com/docs/rest-api"}],"id":"api","kind":"api","name":"Connects directly","href":"https://vercel.com/docs/rest-api"}]}]}