Vercel Skill logo

Vercel Skill

Community
zeenie-ai
vercel-skill

Deploy sites and apps to Vercel, inspect deployments, stream logs, and manage projects/env/domains via the Vercel CLI. Deploy a directory and get back the live deployment URL; everything else the CLI supports is available through the custom command passthrough.

Overview

Publisherzeenie-ai
RepositoryOpenCompany
Skill namevercel-skill
Stars
995
Forks
151
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by zeenie-ai on GitHub. Read the source before you install it.

Installation

Install the Vercel Skill AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/zeenie-ai/OpenCompany/tree/main/server/skills/vercel/vercel-skill
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zeenie-ai/OpenCompany.git /tmp/OpenCompany
mkdir -p .claude/skills
cp -r /tmp/OpenCompany/server/skills/vercel/vercel-skill .claude/skills/vercel-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vercel Skill in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Vercel Skill on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Vercel Skill is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Vercel Skill

Wrapper over the official Vercel CLI. Four operations: deploy, inspect, list, and a custom passthrough that runs any other CLI command — env vars, logs, rollback, promote, domains, aliases, projects.

Tool: vercel

Operations

OperationPurposeKey fields
deployDeploy a directory; returns the live deployment URLpath, project, prod, prebuilt, archive, scope, extra_args
inspectDetails or build logs for one deploymentdeployment (URL or id), logs, wait, timeout
listRecent deployments for a projectproject, prod, status
customAny other CLI commandcommand — exactly what you would type after vercel

Response

json
{
  "operation": "deploy",
  "success": true,
  "url": "https://my-site-abc123.vercel.app",
  "result": null,
  "stdout": "https://my-site-abc123.vercel.app",
  "stderr_tail": "… build output …"
}

For deploy, url is the live deployment URL (stdout carries only the URL; progress goes to stderr — stderr_tail keeps the last part for context). list / inspect return human-readable text in stdout. custom commands that support --json / --format=json (logs, project ls, teams ls, domains verify) return parsed JSON in result.

On CLI failure the tool raises an error carrying Vercel's own message — surface it verbatim; Vercel's errors are precise.

Project naming — read before your first deploy

A first deploy from an unlinked directory MUST set project. Vercel project names allow lowercase letters, digits, ., _, - (no uppercase, no spaces, no --- sequence). Workflow workspace directories often violate this (AI_Assistant_1), so the tool refuses an unlinked no-project deploy up front rather than failing after the upload.

json
{ "operation": "deploy", "project": "my-site" }

Once a directory is linked (.vercel/project.json exists — created by the first successful deploy, or by custom: "link --yes --project my-site"), later deploys may omit project.

Common workflows

Deploy files from the workflow workspace

Write your site files (e.g. index.html) into the workspace, then:

json
{ "operation": "deploy", "project": "my-site" }

path defaults to the per-workflow workspace directory. Preview deploy by default; add "prod": true for production. The returned url is live immediately.

Deploy a specific directory

json
{ "operation": "deploy", "path": "dist", "project": "my-site", "prod": true }

Relative path resolves against the workflow workspace; absolute paths are used as-is.

Wait for a deployment to finish building

json
{ "operation": "inspect", "deployment": "https://my-site-abc123.vercel.app", "wait": true, "timeout": "5m" }

Add "logs": true to see build logs instead of the summary.

List recent deployments

json
{ "operation": "list", "project": "my-site", "status": "READY,ERROR" }

Runtime logs (JSON)

json
{ "operation": "custom", "command": "logs https://my-site-abc123.vercel.app --json" }

Environment variables

json
{ "operation": "custom", "command": "env ls" }
{ "operation": "custom", "command": "env rm API_KEY production --yes" }

Adding env values non-interactively needs stdin, which the passthrough does not provide — set values at deploy time instead via extra_args (--env KEY=value for runtime, --build-env KEY=value for build time):

json
{ "operation": "deploy", "project": "my-site", "extra_args": "--env API_URL=https://api.example.com" }

Rollback / promote production

json
{ "operation": "custom", "command": "rollback https://my-site-abc123.vercel.app" }
{ "operation": "custom", "command": "promote https://my-site-abc123.vercel.app" }

Projects, domains, aliases

json
{ "operation": "custom", "command": "project ls --format=json" }
{ "operation": "custom", "command": "domains ls" }
{ "operation": "custom", "command": "alias set https://my-site-abc123.vercel.app www.example.com" }

Quoting and escaping

command and extra_args are parsed with shlex.split. Quote arguments containing spaces with single quotes. Never put an access token in command — auth is injected automatically as the VERCEL_TOKEN environment variable.

Timeouts and long builds

deploy waits up to 10 minutes for the build. For longer builds pass --no-wait in extra_args (returns the URL immediately while the build continues) and poll with inspect + "wait": true afterwards.

Authentication

Two independent paths (either is enough), configured in the Credentials Modal → Vercel:

  1. Login with Vercel — browser device flow driven through the CLI. The CLI is auto-installed with bun on first use and keeps its auth state in a OpenCompany-owned config directory.
  2. Access token — paste a token from vercel.com/account/tokens. Injected as VERCEL_TOKEN on every call; takes precedence over CLI login and works headless.

If neither is configured the tool raises a credential error telling the user which panel to open.

Best practices

  1. Always pass a lowercase project on first deploys (naming rules above).
  2. Default to preview deploys; set "prod": true only when the user explicitly wants production.
  3. Return the deployment URL to the user — it is live the moment deploy succeeds.
  4. Use the archive field when deploying directories with thousands of files.
  5. Surface Vercel error messages verbatim — don't paraphrase.
  6. Prefer --json / --format=json variants in custom commands when you need to read fields programmatically.

Frequently asked questions

What does the Vercel Skill AI skill do?

Deploy sites and apps to Vercel, inspect deployments, stream logs, and manage projects/env/domains via the Vercel CLI. Deploy a directory and get back the live deployment URL; everything else the CLI supports is available through the custom command passthrough.

Why use Vercel Skill on TypingMind?

Because you install it once and use it with any model. Vercel Skill is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Vercel Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zeenie-ai/OpenCompany/tree/main/server/skills/vercel/vercel-skill. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Vercel Skill?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Vercel Skill?

As many as you like. As long as a model supports skills, you can use Vercel Skill with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Vercel Skill AI skill free?

Yes. It is published on GitHub by zeenie-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇