What problem does it solve? LLMs often carry outdated training data about the Vercel platform, leading to wrong recommendations such as defaulting to Edge Functions, assuming streaming requires the edge runtime, or referencing deprecated products like Vercel Postgres and Vercel KV. This Skill injects authoritative corrections at session start so guidance reflects the current platform. ## Core Features & Use Cases - Knowledge Corrections: Overrides stale assumptions about Edge Functions, Fluid Compute, streaming/SSE on Node.js, ISR framework support, Node.js 24 default, 300s timeouts, and Active CPU pricing. - New Product Awareness: Introduces recent offerings including Vercel AI Gateway, Vercel Queues, Vercel Sandbox, Rolling Releases, Sign in with Vercel, Vercel Agent, BotID, and the eve agent framework. - Configuration Guidance: Promotes vercel.ts with @vercel/config as the replacement for vercel.json, including typed rewrites, redirects, headers, and crons. - Use Case: When a developer asks how to stream AI responses on Vercel, the assistant correctly recommends the default Node.js Fluid Compute runtime instead of unnecessarily switching to the edge runtime. ## Quick Start Ask the assistant to configure a Vercel deployment or explain a Vercel feature, and the corrected platform knowledge is applied automatically.
