Lov Deploy To Vercel logo

Lov Deploy To Vercel

Organization
lovstudio
lov-deploy-to-vercel

Deploy frontend projects to Vercel with automatic custom domain setup. Handles Vite, Next.js, CRA, and static sites. Auto-configures Cloudflare DNS CNAME records and Vercel domain aliases. Supports SPA routing via vercel.json. Trigger when user says "deploy to vercel", "部署到 vercel", "vercel deploy", or mentions a *.example.com / custom domain with vercel deployment.

Overview

Publisherlovstudio
Repositoryskills
Skill namelov-deploy-to-vercel
Stars
67
Forks
17
Bundled files
2
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.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by lovstudio on GitHub. Read the source before you install it.

Installation

Install the Lov Deploy To Vercel 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.
  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/lovstudio/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/deploy-to-vercel .claude/skills/lov-deploy-to-vercel
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lov Deploy To Vercel 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 Lov Deploy To Vercel 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 Lov Deploy To Vercel 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 部署助手 · Vercel Deployer

Deploy frontend projects to Vercel with automatic custom domain and DNS setup.

When to Use

  • User says "deploy to vercel" or "部署到 xxx.example.com"
  • After building a frontend project that needs hosting
  • When setting up a custom domain on an existing Vercel deployment

Arguments

Pass via $ARGUMENTS:

ArgumentExampleDescription
<domain>sbti.example.comCustom domain to configure
--previewDeploy preview only (skip --prod)
--no-dnsSkip Cloudflare DNS auto-config
--link-onlyOnly link project, don't deploy

Workflow

Step 1: Detect Project Type

bash
if [ -f "vite.config.ts" ] || [ -f "vite.config.js" ]; then
  FRAMEWORK="vite"
elif [ -f "next.config.js" ] || [ -f "next.config.mjs" ]; then
  FRAMEWORK="next"
elif grep -q "react-scripts" package.json 2>/dev/null; then
  FRAMEWORK="cra"
else
  FRAMEWORK="static"
fi

Step 2: Ensure vercel.json for SPA

For Vite/CRA (SPA) projects, create vercel.json if missing:

json
{
  "rewrites": [
    { "source": "/(.*)", "destination": "/" }
  ]
}

Skip for Next.js — it handles routing natively.

Step 3: Deploy to Vercel

Before running a production deployment, use AskUserQuestion if the target project, production/non-production mode, or custom domain is unclear. If the user already explicitly requested production deployment for this project, proceed.

bash
# Check CLI
vercel --version || npm i -g vercel

# Deploy (use project name from package.json "name" field)
# IMPORTANT: package.json "name" must be lowercase, no special chars
PROJECT_NAME=$(node -p "require('./package.json').name" 2>/dev/null || basename "$PWD")
vercel --yes --prod

Known issue: If package.json name contains uppercase or invalid chars, vercel will error with "Project names must be lowercase". Fix the name first.

Step 4: Configure Custom Domain (if provided)

bash
DOMAIN="<user-provided-domain>"  # e.g. sbti.example.com

# 1. Add domain to Vercel project
vercel domains add "$DOMAIN"

# 2. Set alias to point domain to latest deployment
PROD_URL=$(vercel ls --prod 2>&1 | grep -oE 'https://[^ ]+\.vercel\.app' | head -1)
vercel alias set "$PROD_URL" "$DOMAIN"

CRITICAL: vercel domains add alone is NOT enough. You MUST also run vercel alias set to actually route traffic. Without it, the domain returns ERR_CONNECTION_CLOSED.

Step 5: Auto-Configure Cloudflare DNS

Requires: CLOUDFLARE_API_KEY env var (API Token with DNS edit permission).

bash
# Extract base domain and subdomain
# e.g. "sbti.example.com" → base="example.com", sub="sbti"
BASE_DOMAIN=$(echo "$DOMAIN" | awk -F. '{print $(NF-1)"."$NF}')
SUBDOMAIN=$(echo "$DOMAIN" | sed "s/\.$BASE_DOMAIN$//")

# 1. Get zone ID
ZONE_ID=$(curl -s "https://api.cloudflare.com/client/v4/zones?name=$BASE_DOMAIN" \
  -H "Authorization: Bearer $CLOUDFLARE_API_KEY" \
  -H "Content-Type: application/json" | python3 -c "import sys,json; print(json.load(sys.stdin)['result'][0]['id'])")

# 2. Check if record already exists
EXISTING=$(curl -s "https://api.cloudflare.com/client/v4/zones/$ZONE_ID/dns_records?name=$DOMAIN&type=CNAME" \
  -H "Authorization: Bearer $CLOUDFLARE_API_KEY" | python3 -c "import sys,json; r=json.load(sys.stdin)['result']; print(r[0]['id'] if r else '')")

# 3. Create or update CNAME → cname.vercel-dns.com
if [ -z "$EXISTING" ]; then
  curl -s -X POST "https://api.cloudflare.com/client/v4/zones/$ZONE_ID/dns_records" \
    -H "Authorization: Bearer $CLOUDFLARE_API_KEY" \
    -H "Content-Type: application/json" \
    --data "{\"type\":\"CNAME\",\"name\":\"$SUBDOMAIN\",\"content\":\"cname.vercel-dns.com\",\"ttl\":1,\"proxied\":false}"
else
  curl -s -X PUT "https://api.cloudflare.com/client/v4/zones/$ZONE_ID/dns_records/$EXISTING" \
    -H "Authorization: Bearer $CLOUDFLARE_API_KEY" \
    -H "Content-Type: application/json" \
    --data "{\"type\":\"CNAME\",\"name\":\"$SUBDOMAIN\",\"content\":\"cname.vercel-dns.com\",\"ttl\":1,\"proxied\":false}"
fi

IMPORTANT: proxied must be false (DNS only). Cloudflare proxy conflicts with Vercel's SSL certificate provisioning.

If CLOUDFLARE_API_KEY is not set, print manual DNS instructions instead:

Add DNS record:
  Type: CNAME
  Name: <subdomain>
  Target: cname.vercel-dns.com
  Proxy: OFF (DNS only)

Step 6: Verify

bash
# Wait for DNS + SSL propagation
sleep 5
HTTP_CODE=$(curl -sI "https://$DOMAIN" -o /dev/null -w '%{http_code}')
if [ "$HTTP_CODE" = "200" ]; then
  echo "✓ $DOMAIN is live"
else
  echo "⚠ HTTP $HTTP_CODE — SSL may still be provisioning, try again in 1-2 min"
fi

Step 7: Output Summary

✓ Framework: vite
✓ Deployed: https://xxx.vercel.app
✓ Domain: https://sbti.example.com
✓ DNS: CNAME sbti → cname.vercel-dns.com (Cloudflare)
✓ Settings: https://vercel.com/<scope>/<project>/settings

Troubleshooting

ProblemCauseFix
ERR_CONNECTION_CLOSEDDomain added but no alias setRun vercel alias set <url> <domain>
"Project names must be lowercase"package.json name invalidFix name field
SSL not provisioningCloudflare proxy ONSet DNS to "DNS only" (no orange cloud)
404 on sub-routesSPA missing rewritesAdd vercel.json with rewrites
DNS resolves to 198.18.x.xLocal proxy (Clash etc.)Normal — check with dig @8.8.8.8
CLOUDFLARE_API_KEY not foundToken not in envAdd to ~/.zshrc: export CLOUDFLARE_API_KEY=...

Runtime context (shared)

运行前读取本 Skill 包的 skill.yaml,由宿主提供 skill-runtime/v1 上下文。字段解析顺序为:当前请求、项目上下文、个人 Preferences、品牌 Profile、通用默认值。

  • 只使用 Manifest 声明的字段;Profile 保存公开品牌事实,Preferences 保存个人工作偏好。
  • required: true 字段缺失时,按 Manifest 的问题配置向用户提出一个聚焦问题;用户明确同意后再保存回答。
  • 报错提供可复制的 context_id、字段路径与来源,诊断内容避开秘密、完整私人路径和原始配置。

通用反馈闭环

用户在 Skill 驱动任务中提出修改意见时,继续当前产物前必须执行:

  1. 先判断意见是 task-specific(仅本次)还是 reusable(可跨任务复用)。
  2. task-specific 只修改当前任务,不改 Skill。
  3. reusable 先确定作用域:领域规则先更新对应 canonical Skill;适用于所有 Skill 的规则先更新共享规范。
  4. 完成规则更新、版本、lint 与分发核验后,再把修改应用到当前任务。
  5. reusable 修改会使此前的“确认”“继续”“发吧”失效;完成当前产物修改和回读后必须停下,等待用户下一步指示,不自动进入发布、提交或其他外部写入。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Lov Deploy To Vercel AI skill do?

Deploy frontend projects to Vercel with automatic custom domain setup. Handles Vite, Next.js, CRA, and static sites. Auto-configures Cloudflare DNS CNAME records and Vercel domain aliases. Supports SPA routing via vercel.json. Trigger when user says "deploy to vercel", "部署到 vercel", "vercel deploy", or mentions a *.example.com / custom domain with vercel deployment.

Why use Lov Deploy To Vercel on TypingMind?

Because you install it once and use it with any model. Lov Deploy To Vercel 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 Lov Deploy To Vercel in TypingMind?

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

Which AI models can use Lov Deploy To Vercel?

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 Lov Deploy To Vercel?

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

Is the Lov Deploy To Vercel AI skill free?

Yes. It is published on GitHub by lovstudio 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 👇