ai-sdk-core
Build backend AI with Vercel AI SDK v6 stable. Covers Output API (replaces generateObject/streamObject), speech synthesis, transcription, embeddings, MCP tools with security guidance. Includes v4→v5 migration and 15 error solutions with workarounds. Use when: implementing AI SDK v5/v6, migrating versions, troubleshooting AI_APICallError, Workers startup issues, Output API errors, Gemini caching issues, Anthropic tool errors, MCP tools, or stream resumption failures.
Why use this skill?
Master backend AI development with Vercel AI SDK v6. Learn to use the new Output API, implement ToolLoopAgent, and manage secure tool workflows.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/veeramanikandanr48/ai-sdk-coreWhat This Skill Does
The ai-sdk-core skill is an essential developer toolkit for managing Vercel AI SDK v6 integrations. It provides a standardized interface for interacting with LLMs, handling structured output, and orchestrating agentic tool workflows. By abstracting the complexity of the Output API, it ensures that your application remains forward-compatible while utilizing the latest features of v6, such as ToolLoopAgent and selective human-in-the-loop tool approvals.
Installation
To integrate this skill into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/veeramanikandanr48/ai-sdk-core
Ensure you have your environment variables set for your preferred providers (OpenAI, Anthropic, or Google) before initializing the SDK within your project structure.
Use Cases
- Implementing structured data extraction using the new Output API, which supersedes older generateObject/streamObject methods.
- Developing autonomous agents that require multi-step tool execution, state management, and granular control over tool approval processes.
- Migrating legacy Vercel AI SDK v4/v5 projects to the stable v6 architecture with minimal breaking changes.
- Troubleshooting complex API errors, including AI_APICallError, Gemini caching inconsistencies, and stream resumption failures.
- Implementing secure MCP (Model Context Protocol) tool calls within backend AI services.
Example Prompts
- "Refactor my existing generateObject implementation to use the new v6 Output API with a Zod schema for a user profile generator."
- "Set up a ToolLoopAgent that includes a payment tool requiring human approval only if the transaction amount exceeds $500."
- "Help me troubleshoot a stream resumption failure occurring when calling the Anthropic API through the AI SDK core."
Tips & Limitations
- Always prioritize the Output API. The
generateObjectandstreamObjectmethods are deprecated; using them will result in warnings and future runtime failures. - Utilize
needsApprovalinside tool definitions to enhance security; it is a powerful way to gate sensitive operations like file writing or financial transactions. - When working with large prompts, ensure you are leveraging the latest caching mechanisms to optimize costs.
- The skill requires strict Zod schema compliance for the Output API to function correctly. If your LLM output fails schema validation, use the
Output.json()type for unstructured data until your prompt engineering is refined.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-veeramanikandanr48-ai-sdk-core": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: external-api, code-execution
Related Skills
better-auth
Self-hosted auth for TypeScript/Cloudflare Workers with social auth, 2FA, passkeys, organizations, RBAC, and 15+ plugins. Requires Drizzle ORM or Kysely for D1 (no direct adapter). Self-hosted alternative to Clerk/Auth.js. Use when: self-hosting auth on D1, building OAuth provider, multi-tenant SaaS, or troubleshooting D1 adapter errors, session caching, rate limits, Expo crashes, additionalFields bugs.
security-reviewer
Use when conducting security audits, reviewing code for vulnerabilities, or analyzing infrastructure security. Invoke for SAST scans, penetration testing, DevSecOps practices, cloud security reviews.
api-designer
Use when designing REST or GraphQL APIs, creating OpenAPI specifications, or planning API architecture. Invoke for resource modeling, versioning strategies, pagination patterns, error handling standards.
cli-developer
Use when building CLI tools, implementing argument parsing, or adding interactive prompts. Invoke for CLI design, argument parsing, interactive prompts, progress indicators, shell completions.
swift-expert
Use when building iOS/macOS applications with Swift 5.9+, SwiftUI, or async/await concurrency. Invoke for protocol-oriented programming, SwiftUI state management, actors, server-side Swift.