knowledge-update

Corrects outdated LLM knowledge about the Vercel platform and introduces new products.

Updated Aug 21, 2025
One-click install
npx skills add https://github.com/Adithiya-S/AI-Study-Companion --skill knowledge-update-adithiya-s
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: knowledge-update
Source: https://github.com/Adithiya-S/AI-Study-Companion/tree/main/.agents/skills/knowledge-update
Command: npx skills add https://github.com/Adithiya-S/AI-Study-Companion --skill knowledge-update-adithiya-s

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? LLM training data often contains outdated or incorrect information about the Vercel platform, leading to wrong recommendations such as defaulting to Edge runtime, using deprecated products like Vercel Postgres, or missing new capabilities like Fluid Compute and vercel.ts configuration. ## Core Features & Use Cases - Knowledge Correction: Overrides stale assumptions about Edge Functions, streaming, timeouts, pricing, and runtimes with current Vercel platform facts. - New Product Awareness: Introduces recent offerings such as Vercel AI Gateway, Vercel Queues, Vercel Sandbox, Rolling Releases, BotID, and the eve agent framework. - Integration Guidance: Directs the agent to load the marketplace skill first whenever a build requires an external service like a database, payments, or CMS. - Use Case: When a user asks how to stream AI responses on Vercel, the agent correctly recommends the default Node.js Fluid Compute runtime instead of unnecessarily switching to the Edge runtime. ## Quick Start Ask the agent to configure or deploy a Vercel project and it will apply the corrected platform knowledge automatically.

Frequently Asked Questions about knowledge-update

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
Do I need the Edge runtime to stream responses on Vercel?

No, streaming responses including ReadableStream, Server-Sent Events, and AI token streaming work on the default Node.js runtime with zero configuration. Staying on Fluid Compute keeps full Node.js APIs and longer execution durations.

How do I configure a Vercel project with TypeScript?

Use vercel.ts, which replaces vercel.json with full TypeScript support, dynamic logic, and environment variable access. Install @vercel/config and export a typed VercelConfig with rewrites, redirects, headers, and crons.

Are Vercel Postgres and Vercel KV still available?

No, Vercel Postgres and Vercel KV are no longer offered. Vercel now provides various databases through the Vercel Marketplace, and integrations should be provisioned via the marketplace skill.

What is Fluid Compute on Vercel?

Fluid Compute is the default compute model that reuses function instances across concurrent requests, reducing cold starts compared to traditional one-request-per-instance serverless. It supports Node.js, Python, Bun, and Rust runtimes with graceful shutdown and request cancellation.

What are the current Vercel Functions limits?

Vercel Functions support up to 5 GB package size, 100 MB request bodies, a default 300 second execution timeout, and WebSocket connections on Fluid Compute. Pricing uses Active CPU time, provisioned memory, and invocations rather than wall-clock GB-seconds.