$ loading_
Deploy apps or websites to Vercel and generate live or preview links.
Overall risk is low. This is an open-source, widely adopted deployment skill, but by design it may run local deployment commands and send project contents to Vercel, so network egress, code execution, and data access deserve attention.
The material states that no keys or environment variables are required; the README also describes an unauthenticated fallback deployment path. There is no evident design requiring users to provide or store sensitive credentials, so credential exposure appears limited.
The core function of this skill is deploying a project to Vercel, so project package contents will be sent to Vercel’s service, and it may request escalated network access when sandbox networking blocks deployment. This is consistent with its stated purpose, but it still means user code/static assets may leave the local environment.
The README explicitly instructs running local commands and scripts such as `vercel deploy` and `bash .../deploy.sh`, with possible escalation when needed for deployment. This is normal for a deployment tool and there is no evidence of system privileges beyond the stated function, but it does involve local process execution.
The documentation supports deploying the current directory, a specified project directory, or an existing tarball, which means it will read and package corresponding local project files for upload. There is no indication it accesses unrelated data, but running it from the wrong directory could upload unintended files.
The source is the open-source GitHub repository `openai/skills`, which is auditable and has strong community adoption (~22k stars), significantly lowering supply-chain risk. The undeclared license and unknown maintenance status are minor transparency gaps, but not enough on their own to raise it to high risk.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "vercel-deploy" skill from askskill: 1. Download https://raw.githubusercontent.com/openai/skills/main/skills/.curated/vercel-deploy/SKILL.md 2. Save it as ~/.claude/skills/vercel-deploy/SKILL.md 3. Reload skills and tell me it's ready
Deploy any project to Vercel instantly. Always deploy as preview (not production) unless the user explicitly asks for production.
command -v vercel).sandbox_permissions=require_escalated).command -v vercel
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.
vercel is not installed, or if the CLI fails with "No existing credentials found", use the fallback method below.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."
Only if user explicitly asks:
vercel deploy [path] --prod -y
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.
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?
Generate or edit bitmap images for illustrations, photos, textures, mockups, and cutouts.
Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications.
Create a composable CLI from docs, specs, SDKs, apps, or scripts.
Turn vague intentions into concrete, measurable goals and clear success criteria.
Create a new blank Figma design or FigJam file to start collaborating quickly.
Connect to Figma, fetch design assets, and turn nodes into production code.
Manage Vercel deployments, projects, domains, and environment variables with natural language.
Turn app ideas from chat into live full-stack web applications instantly.
Manage Vercel projects, deployments, domains, env vars, and teams via API.
Deploy, publish, and link web projects to Netlify using the CLI.
Deploy, publish, and host apps and infrastructure on Cloudflare services.
Analyze codebases and generate Render configs to deploy apps to the cloud.