vercel/ai
10 skills52.8k installs258k starsGitHub
Install
npx skills add https://github.com/vercel/aiSkills in this repo
1Ai SdkThe Vercel AI SDK is a framework for building AI applications with built-in streaming, function calling, and multi-provider support. It simplifies integrating language models into web applications and agents. Includes utilities for prompt management, token optimization, and structured output handling.43.6kinstalls2Migrate Ai Sdk V6 To V7The migrate-ai-sdk-v6-to-v7 skill walks developers through upgrading Vercel AI SDK packages from 6.x to 7.0 using the official migration guide as source of truth. It catalogs breaking changes, renamed APIs, streaming behavior updates, and package import path adjustments agents must apply across app code and tests. Workflows reference content/docs migration guide MDX from the AI SDK repo when exact examples are needed. Agents use the skill when users mention AI SDK v6, v7, upgrade errors, or migration failures during SDK bumps. AI SDK 6.x to 7.0 migration checklist and breaking changes. References official migration guide MDX as source of truth. Covers renamed APIs, streaming, and import path updates. Helps fix v7 migration errors across app and test code. Vercel AI SDK upgrade workflow for production apps.2.3kinstalls3Adr SkillThe adr-skill skill create and maintain Architecture Decision Records ADRs optimized for agentic coding workflows Use when you need to propose write update accept reject deprecate or supersede an ADR bootstrap an adr folder and index consult existing ADRs before implementing changes or enforce ADR conventions This skill uses Socratic questioning to capture intent before drafting and validates output against an agent-readiness checklist ADR Skill Philosophy ADRs created with this skill are executable specifications for coding agents A human approves the decision an agent implements it The ADR must contain everything the agent needs to write correct code without asking follow-up questions This means Constraints must be explicit and measurable not vibes Decisions must be specific enough to act on use PostgreSQL 16 with pgvector not use a database Consequences must map to concrete follow-up tasks Non-goals must be stated to prevent scope creep The ADR must be self-contained no tribal knowledge assumptions The ADR must include an implementation plan which files to touch which patterns to follow which tests1.6kinstalls4Develop Ai Functions ExampleThe develop-ai-functions-example skill is designed for create and run AI SDK function examples under examples/ai-functions for provider validation. AI Functions Examples The examples/ai-functions/ directory contains scripts for validating, testing, and iterating on AI SDK functions across providers. Adding a new provider: Create basic examples for each supported API (generateText, streamText, generateObject, etc.) 2. Invoke when the user creates, runs, or modifies AI SDK examples under examples/ai-functions.1.4kinstalls5Capture Api Response Test FixtureThe capture-api-response-test-fixture skill capture API response test fixture API Response Test Fixtures For provider response parsing tests we aim at storing test fixtures with the true responses from the providers unless they are too large in which case some cutting that does not change semantics is advised The fixtures are stored in a __fixtures__ subfolder e g packages openai src responses __fixtures__ See the file names in packages openai src responses __fixtures__ for naming conventions and packages openai src responses openai-responses-language-model test ts for how to set up test helpers You can use our examples under examples ai-functions to generate test fixtures generateText doGenerate testing For generateText log the raw response output to the console and copy it into a new test fixture ts import openai from ai-sdk openai import generateText from ai import run from lib run run async const result await generateText model openai gpt-5-nano prompt Invent a new holiday and describe its traditions console log JSON stringify result response body null 2 streamText doStream testing For streamText1.3kinstalls6List Npm Package ContentThe list-npm-package-content skill 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. # List npm Package Content This skill lists the exact contents of an npm package tarball - the same files that would be uploaded to npm and downloaded by users. ## Usage Run the script from the package directory (e.g., `packages/ai`): ```bash bash scripts/list-package-files.sh ``` The script will build the package, create a tarball, list its contents, and clean up automatically. ## Understanding Package Contents The files included are determined by: 1. **`files` field in `package.json`** - explicit allowlist of files/directories 2. **`.npmignore`** - files to exclude (if present) 3. **`.gitignore`** - used if no `.npmignore` exists 4. **Always included**: `package.json`, `README`, `LICENSE`, `CHANGELOG` 5. **Always excluded**: `.git`, `node_modules`, `.npmrc`, etc.1.2kinstalls7Add Provider PackageGuide for adding new AI provider packages to the AI SDK. Use when creating a new @ai-sdk/<provider> package to integrate an AI service into the SDK. This guide covers the process of creating a new `@ai-sdk/<provider>` package to integrate an AI service into the AI SDK.945installs8Update Provider ModelsAdd new or remove obsolete model IDs for existing AI SDK providers. Use when adding a model to a provider, removing an obsolete model, or processing a list of model changes from an issue. Triggers on "add model", "remove model", "new model ID", "obsolete model", "update model IDs". This skill covers adding new model IDs and removing obsolete ones across the AI SDK codebase. Each workflow uses search to discover all locations that need changes.231installs9Add Function ExamplesGuide for contributing function examples to the Vercel AI SDK repository. Focuses on adding examples that exercise specific provider API capabilities with real network calls rather than mocks. Ensures examples follow repo conventions for structure, imports, and runnable scripts that developers can copy when validating provider behavior. Used when extending the examples directory with new model features, tool calling patterns, or streaming behaviors that need live verification against provider APIs.161installs10Major Version ModeVercel AI SDK major version mode skill providing context for working on the next major release. Explicitly must NOT trigger autonomously based on task content; only activates when user invokes via /major-version-mode. Contains breaking change guidance, migration patterns, and major version development conventions separate from stable release maintenance. Prevents agents from applying major-version assumptions to routine SDK tasks.139installs