Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.
76
74%
Does it follow best practices?
Impact
76%
6.33xAverage score across 3 eval scenarios
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/ai-sdk/SKILL.mdThe canonical home for this skill is ai-sdk in vercel/ai
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
I flagged https://ai-gateway.vercel.sh/v1/models and the ai-sdk.dev endpoints (https://ai-sdk.dev/api/search-docs?q=your_query and https://ai-sdk.dev/docs/agents/building-agents.md) because the skill explicitly instructs running curl/searches at runtime to fetch model IDs and docs which directly determine model selection and agent behavior.
11c3258
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.