@vercel

add-provider-package provides a numbered 15-step walkthrough for integrating new ai services into the sdk via @ai-sdk/<provider> packages, covering architecture, file structure, configuration, testing, and deployment with reference examples.

deployments-cicd covers vercel cli workflows (deploy, promote, rollback, inspect), prebuilt deployments for custom ci pipelines, and github/gitlab/bitbucket integration patterns. includes oidc federation for runtime backend auth and observable deploy result formatting.

turborepo covers monorepo task orchestration, caching, filtering, ci optimization, and architectural boundaries with decision trees and anti-pattern guidance.

verification infers the complete user story from recent code changes, then traces the end-to-end data flow across browser, server, api, and data layers with explicit evidence reporting at each boundary.

workflow-init scaffolds vercel workflow sdk setup by detecting the user's framework, fetching the appropriate getting-started guide, and walking through install, config, and verification steps before handing off to versioned docs.

workflow skill provides detailed guidance on vercel's workflow devkit, covering orchestration patterns, step functions, hooks for pause-resume, streaming, ai agents, and debugging. reference-heavy rather than goal-oriented.

adr-skill guides creation of executable architecture decision records for agentic workflows, emphasizing measurable constraints, concrete specifications, and implementation details sufficient for autonomous coding agents to act without clarification.

guides adoption of next.js cache components by enabling the flag, resolving build errors via dev overlay feedback, and translating legacy revalidation exports. sequences work across version checks, config migration, and iterative route fixes.

vercel-workflow covers durable, resumable orchestration with step functions, hooks for pausing on external events, error handling via fatal/retryable errors, and ai agent integration. sandbox limitations and serialization rules are documented but procedures lack step-by-step clarity.

next-cache-components-optimizer establishes a test-driven agentic loop to maximize static shell rendering in next.js routes under cache components, using @next/playwright instant() as the measurement gate and shipping the test as the regression guard.

lists npm package tarball contents before publishing by respecting package.json files, npmignore, and gitignore rules. identifies what gets distributed without manual tarball inspection.

vercel-cli covers deployment and project management from the terminal, with emphasis on correct project linking via .vercel metadata. narrow scope limits practical versatility.

chat-sdk provides a unified typescript interface for authoring bots once and deploying across eight chat platforms. developers get normalized event handling, ai sdk streaming, and jsx-based interactive cards, with pluggable state and custom adapter support.

vercel-ai-elements provides shadcn/ui-based components for building ai chat interfaces in next.js apps. covers installation, usage patterns, and customization via tailwind, but lacks depth on component capabilities and integration workflows.

env-vars documents vercel environment variable file hierarchy and loading order, covering .env naming conventions across development, production, and test environments. lacks actionable procedures for common tasks.

vercel-functions covers serverless and edge compute on vercel with runtime details, cold start timings, and payload limits. lacks deployment workflow and error handling patterns.

next-upgrade detects the current next.js version and fetches official migration guides and codemods, then determines an incremental upgrade path. incomplete procedure and missing failure handling.

ai-sdk covers vercel ai sdk integration patterns including agent creation, model selection, and framework-specific consumption. emphasizes source verification over memorized apis and provides troubleshooting references.

ai-sdk provides guardrails for querying vercel's ai package and building agents, emphasizing source-of-truth verification over memorized apis and framework-specific consumption patterns.

vercel-web-design-guidelines audits ui code against web interface standards by fetching remote rules and reporting compliance violations. delegates actual rule definitions to an external github source, making the skill itself a thin wrapper.

shadcn covers react component installation and customization via CLI, emphasizing copy-paste patterns over npm packages. lacks depth on composition, theming workflows, and registry setup despite claims in metadata.

marketplace covers vercel integration discovery and installation with project linking validation, but lacks depth on billing workflows, environment variable configuration, and integration-specific troubleshooting.

capture-api-response-test-fixture provides conventions and helper patterns for storing provider api responses as test fixtures, with separate approaches for generatetext and streamtext patterns.

next-best-practices is a reference index covering next.js conventions, rsc boundaries, async patterns, error handling, image/font optimization, and deployment. it links to detailed sub-documents but provides no actionable procedures inline.

vercel-capture-api-response-test-fixture documents how to collect real api responses for testing purposes, covering both generatetext and streamtext patterns with code examples.

flags-sdk provides feature flag management for next.js and sveltekit via callable functions and provider adapters, with first-party integration through vercel flags.

turbopack covers rust-powered bundling for next.js with emphasis on hmr performance and file caching, but lacks actionable configuration and troubleshooting guidance.

chat-sdk covers multi-platform bot development across eight integrations (slack, teams, discord, telegram, github, linear, google chat, whatsapp) using a unified typescript interface. install paths documented but procedures absent.

vercel-agent provides ai-powered code review, incident investigation, and sdk installation on the vercel platform. capabilities include automated pr analysis, anomaly root-cause detection, and analytics sdk setup, with pricing at $0.30 per review or investigation.

dce-edge documents webpack dead code elimination patterns for conditional node imports and edge runtime branching, showing correct require patterns and common pitfalls.

building-components outlines when to invoke component design guidance across primitives, accessibility, composition patterns, and publishing workflows, but lacks procedural depth and concrete failure-mode handling.

reference documentation for vercel's workflow sdk covering sandbox behavior, step functions, hooks, serialization, streaming, and durable agents. not a skill with clear intent or actionable workflow patterns.

nextjs provides a taxonomy of next.js concerns (routing, server components, caching, optimization) but delegates all procedural content to external docs, offering no actionable guidance or decision frameworks within the skill itself.

Build durable backend AI agents with the eve framework. Use when creating, editing, or debugging an eve project — agent instructions, skills, tools,…

eve framework guidance for durable AI agents and agent-powered applications. Use when creating, editing, or debugging an eve project, when the user explicitly…

Debug Vercel CDN caching — cache hit rate, stale content, revalidation behavior, ISR + PPR, per-request cache reasons (cacheReason) and PPR state (ppr_state),…

Verify Next.js runtime behavior after editing app code. Use this skill to confirm a change actually works in a running app — not just that it compiles or…

Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and more. Use when the user wants to build a…

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI…

Implement, configure, and customize Streamdown — a streaming-optimized React Markdown renderer with syntax highlighting, Mermaid diagrams, math rendering, and CJK support. Use when working with Streamdown setup, configuration, plugins, styling, security, or integration with AI streaming (e.g., Vercel AI SDK). Triggers on: (1) Installing or setting up Streamdown, (2) Configuring plugins (code, mermaid, math, cjk), (3) Styling or theming Streamdown output, (4) Integrating with AI chat/streaming, (5) Configuring security, link safety, or custom HTML tags, (6) Using carets, static mode, or custom components, (7) Troubleshooting Tailwind, Shiki, or Vite issues.

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".

This skill should be used when the user asks to "update documentation for my changes", "check docs for this PR", "what docs need updating", "sync docs with code", "scaffold docs for this feature", "document this feature", "review docs completeness", "add docs for this change", "what documentation is affected", "docs impact", or mentions "docs/", "docs/01-app", "docs/02-pages", "MDX", "documentation update", "API reference", ".mdx files". Provides guided workflow for updating Next.js documentation based on code changes.

List the contents of an npm package tarball before publishing. Use when the user wants to see what files are included in an npm bundle, verify package contents, or debug npm publish issues.

Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.

Develop examples for AI SDK functions. Use when creating, running, or modifying examples under examples/ai-functions/src to validate provider support, demonstrate features, or create test fixtures.

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip…

Migrate applications from AI SDK 6.x to AI SDK 7.0. Use when upgrading Vercel AI SDK packages, fixing v7 migration errors, or when the user mentions AI SDK v6,…

Implement, configure, and customize Streamdown — a streaming-optimized React Markdown renderer with syntax highlighting, Mermaid diagrams, math rendering, and…

develop-ai-functions-example — an installable skill for AI agents, published by vercel/ai.

Authentication integration guidance — Clerk (native Vercel Marketplace), Descope, and Auth0 setup for Next.js applications. Covers middleware auth patterns,…

Next.js 16 Cache Components guidance — PPR, use cache directive, cacheLife, cacheTag, updateTag, and migration from unstable_cache. Use when implementing…

React best-practices reviewer for TSX files. Triggers after editing multiple TSX components to run a condensed quality checklist covering component structure,…

Vercel Routing Middleware guidance — request interception before cache, rewrites, redirects, personalization. Works with any framework. Supports Edge, Node.js,…

Next.js 16 Cache Components - PPR, use cache directive, cacheLife, cacheTag, updateTag

Vercel Sandbox guidance — ephemeral Firecracker microVMs for running untrusted code safely. Supports AI agents, code generation, and experimentation. Use when…

Project bootstrapping orchestrator for repos that depend on Vercel-linked resources (databases, auth, and managed integrations). Use when setting up or…

>

update-docs — an installable skill for AI agents, published by vercel/next.js.

Vercel Runtime Cache API guidance — ephemeral per-region key-value cache with tag-based invalidation. Shared across Functions, Routing Middleware, and Builds.…

Vercel storage expert guidance — Blob, Edge Config, and Marketplace storage (Neon Postgres, Upstash Redis). Use when choosing, configuring, or using data…

Vercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified…

>