Share a reviewable build
Ask for a preview URL so a teammate can inspect the change without targeting production.
Deploy to Vercel by Vercel Labs
Use Deploy to Vercel by Vercel Labs to guide an agent through publishing a project to Vercel. Check repository linkage, account access, and the intended team, choose a deployment path that fits the project, and create a preview for review before requesting a production release.
Install and get started
Choose your agent to see how to get started. In Floatboat, copy a request that asks the agent to read the original instructions. Other options show the Skill installation command or the publisher’s native setup steps.
Choose an agent
Start in Floatboat
Copy the request into a Floatboat conversation
Read the original Deploy to Vercel instructions at https://github.com/vercel-labs/agent-skills/blob/main/skills/deploy-to-vercel/SKILL.md. Explain its purpose, required tools, and installation options, then help me use it.Let the agent read the original instructions and check how to use them in your environment.
Download Floatboat ↗Try this request
Create a Vercel preview for this branch, confirm the linked project and team first, and do not push or deploy production without asking me.
About Deploy to Vercel
Deploy to Vercel is a Vercel Labs Skill that guides an agent through selecting and carrying out a deployment workflow. It starts by checking the Git remote, local Vercel project linkage, CLI authentication, and available teams. Those checks establish the intended destination before the agent chooses a linked Git or another supported deployment route. The source defaults to preview deployments unless production is explicitly requested and requires approval before pushing code through its Git path. Installing the Skill supplies workflow instructions; a deployable project and the required account access are still needed. After deployment, verify the returned URL and project rather than treating an upload as proof of the intended result.
Use Cases for Deploy to Vercel
Explore deployment tasks where the project destination and review environment need to be clear. Create a preview for feedback, check an existing local project link, or choose the intended Vercel team before taking the deployment path supported by the current repository and account.
The local folder may point to the wrong project
Check existing Vercel link files and Git remote before running any command that might silently connect a project.
Several Vercel teams are available
Confirm the intended team or use the linked project's org ID instead of guessing an account scope.
How to Deploy a Project to Vercel
Tell the agent which project to deploy and whether you need a preview or an explicitly requested production release. Review the repository, project, and team checks, follow the selected deployment path, and verify the returned URL against the intended version and environment.
- 01
Check project and team
Ask the agent to read the Git remote, local Vercel link, authentication, and team context. Confirm the intended project and environment.
- 02
Choose the deployment path
Use the method that matches the linked repository and available access. Review any proposed Git push before authorizing it.
- 03
Verify the deployment URL
Open the returned URL and inspect representative pages. Confirm the project, version, and preview or production destination.
Explore More Agent Skills
Read another Skill guide and check its original source before using it.
Deploy to Vercel FAQ
What does this Skill install?
It adds agent instructions. You still need appropriate Vercel access and a project that can be built and deployed.
Is preview deployment the default?
Yes. The source reserves production for an explicit user request.
Does it choose a Vercel team automatically?
A linked project can establish the team. If multiple unlinked teams are possible, the workflow asks which one is intended.
How is this different from Vercel CLI with Tokens?
Deploy to Vercel is the general deployment-decision workflow. Vercel CLI with Tokens focuses on authenticated CLI operations using an existing access token.
What should I verify before a deployment can affect production?
Confirm the intended project, team, branch, and deployment target. Review environment settings and the proposed action, and obtain authorization for a production-changing step before executing it.
How do I confirm that the intended version is actually live?
Check the deployment result and the URL that serves the intended environment. Compare the revision and representative page behavior; a completed upload alone does not prove that production traffic uses it.
Will the Skill push code without asking?
The source’s linked-Git deployment path explicitly requires approval before pushing. Review the target branch and project first, since a push may trigger the repository’s configured deployment workflow.