New to Claude Skills? Learn how to install them →

openai on GitHub

Vercel Deploy

OfficialFree

Instantly deploy applications and websites to Vercel.

by openai24.8k stars on openai/skills
3 views
Updated Jun 24, 2026
Get this skill

Free · Opens the source repo

What Vercel Deploy does

The Vercel Deploy skill allows developers to deploy their applications and websites to Vercel with ease. This skill is designed to streamline the deployment process by checking for the necessary Vercel CLI installation and executing deployment commands directly from the command line. Users can initiate deployments by simply requesting actions like "deploy my app" or "push this live," making it a practical tool for both developers and designers who frequently deploy web projects.

Upon activation, the skill first verifies whether the Vercel CLI is installed without requiring escalated permissions. If the CLI is present, it proceeds to deploy the specified project with a default timeout of 10 minutes, accommodating the time needed for builds. If the CLI is not installed or if there are authentication issues, the skill provides a fallback method using a deploy script that handles framework detection and packaging. This script ensures that even users without the Vercel CLI can deploy their projects efficiently.

The skill primarily deploys projects as preview versions, allowing users to review changes before going live. If a production deployment is explicitly requested, the skill can accommodate that as well. The output includes URLs for both the preview and claim links, enabling users to manage their deployments easily. This functionality is particularly useful for teams working in agile environments who need to frequently test and iterate on their applications.

Overall, the Vercel Deploy skill is an essential tool for anyone looking to simplify their deployment workflow on Vercel, enhancing productivity and reducing the friction often associated with deploying web applications.

When to use it

Use this skill when you need to deploy web applications or websites to Vercel, especially in development or preview scenarios.

When not to use it

This skill is not suitable for users who require extensive customization during deployment or those who prefer a graphical interface for deployment tasks.

What you can build with it

Quick Preview Deployment

Deploy your web application as a preview to test changes before going live.

Fallback Deployment

Use the deploy script to deploy when the Vercel CLI is not installed or fails due to authentication.

Production Deployment

Deploy your application directly to production when explicitly requested by the user.

How to install Vercel Deploy

View source

1. Install with the skills CLI

npx skills add openai/skills/vercel-deploy --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by openai

Vercel Deploy

Deploy any project to Vercel instantly. Always deploy as preview (not production) unless the user explicitly asks for production.

Prerequisites

  • Check whether the Vercel CLI is installed without escalated permissions (for example, command -v vercel).
  • Only escalate the actual deploy command if sandboxing blocks the deployment network calls (sandbox_permissions=require_escalated).
  • The deployment might take a few minutes. Use appropriate timeout values.

Quick Start

  1. Check whether the Vercel CLI is installed (no escalation for this check):
command -v vercel
  1. If vercel is installed, run this (with a 10 minute timeout):
vercel deploy [path] -y

Important: Use a 10 minute (600000ms) timeout for the deploy command since builds can take a while.

  1. If vercel is not installed, or if the CLI fails with "No existing credentials found", use the fallback method below.

Fallback (No Auth)

If CLI fails with auth error, use the deploy script:

skill_dir="<path-to-skill>"

# Deploy current directory
bash "$skill_dir/scripts/deploy.sh"

# Deploy specific project
bash "$skill_dir/scripts/deploy.sh" /path/to/project

# Deploy existing tarball
bash "$skill_dir/scripts/deploy.sh" /path/to/project.tgz

The script handles framework detection, packaging, and deployment. It waits for the build to complete and returns JSON with previewUrl and claimUrl.

Tell the user: "Your deployment is ready at [previewUrl]. Claim it at [claimUrl] to manage your deployment."

Production Deploys

Only if user explicitly asks:

vercel deploy [path] --prod -y

Output

Show the user the deployment URL. For fallback deployments, also show the claim URL.

Do not curl or fetch the deployed URL to verify it works. Just return the link.

Troubleshooting

Escalated Network Access

If deployment fails due to network issues (timeouts, DNS errors, connection resets), rerun the actual deploy command with escalated permissions (use sandbox_permissions=require_escalated). Do not escalate the command -v vercel installation check. The deploy requires escalated network access when sandbox networking blocks outbound requests.

Example guidance to the user:

The deploy needs escalated network access to deploy to Vercel. I can rerun the command with escalated permissions—want me to proceed?

Frequently asked questions about Vercel Deploy

Similar skills