Vercel logo

Vercel

Community
Dicklesworthstone
vercel

Operate Next.js 16 SaaS on Vercel with Cloudflare DNS + Supabase. Use when deploying to Vercel, reducing build costs, managing secrets, or splitting traffic between Vercel and Cloudflare.

Overview

PublisherDicklesworthstone
Repositoryagent_flywheel_clawdbot_skills_and_integrations
Skill namevercel
Stars
73
Forks
16
Bundled files
8
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.

  • 8 bundled files

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

  • Open source

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

Installation

Install the 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.
    https://github.com/Dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations/tree/main/skills/vercel
  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/Dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations.git /tmp/agent_flywheel_clawdbot_skills_and_integrations
mkdir -p .claude/skills
cp -r /tmp/agent_flywheel_clawdbot_skills_and_integrations/skills/vercel .claude/skills/vercel
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 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 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 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 for SaaS

Core Insight: Optimize three axes: operational control (CLI-first), cost control (avoid accidental builds), correctness (caching + auth without breaking SSR).

Table of Contents


THE EXACT PROMPT

Set up [Next.js app / SaaS] on Vercel with:
1. Cloudflare DNS at: [domain.com]
2. Supabase project: [project-ref]
3. Build control: [manual deploys only / CI-triggered / default]
4. Cost offload: [R2 for assets / Cloudflare Pages for marketing / none]

Follow vercel-for-saas skill patterns.

Architecture Decision

Where should traffic go?
│
├─ Authenticated app (SSR/RSC) ─────► Vercel (app.example.com)
│  • DNS-only in Cloudflare (no proxy)
│  • Manual deploys, prebuilt artifacts
│
├─ Marketing/docs (static) ─────────► Cloudflare Pages (www.example.com)
│  • Direct Upload for deploy control
│  • Aggressive caching, cheap bandwidth
│
└─ Uploads/assets (storage) ────────► Cloudflare R2 (assets.example.com)
   • Worker-signed URLs
   • No egress fees

Why this split: Vercel does NOT recommend reverse-proxying. Hostname splitting gets Cloudflare benefits without breaking Vercel's edge.

Quick Start: Manual Deploy

bash
# 1. Pull settings + env (creates .vercel/)
vercel pull --yes --token $VERCEL_TOKEN

# 2. Build locally (skips Vercel build minutes)
vercel build --prod

# 3. Upload prebuilt artifact
vercel deploy --prebuilt --prod --token $VERCEL_TOKEN

This is the highest-leverage pattern for cost control.

Stop Build Credit Burn

MethodHowEffectiveness
Disable auto-deploysvercel.json: "git": { "deploymentEnabled": false }★★★★★
Prebuilt workflowBuild outside Vercel, upload with --prebuilt★★★★☆
Ignored Build StepExit 0 = skip, Exit 1 = build (commonly reversed!)★★☆☆☆
Deploy HooksHTTP-triggered deploys only★★★☆☆

Config-as-code (recommended):

json
{
  "$schema": "https://openapi.vercel.sh/vercel.json",
  "git": { "deploymentEnabled": false }
}

Details: BUILD-CONTROL.md

Environment Variables

bash
# List
vercel env ls

# Add secret (interactive)
vercel env add SECRET_NAME production

# Pull to local .env
vercel env pull .env.local

# Bulk sync via REST (for agents)
curl -X POST "https://api.vercel.com/v10/projects/$PROJECT/env?upsert=true" \
  -H "Authorization: Bearer $VERCEL_TOKEN" \
  -d '{"key":"VAR","value":"val","target":["production"]}'

For OIDC + Vault: TOKEN-AND-KEY-MANAGEMENT.md

Domain Setup

bash
# Add domain to Vercel
vercel domains add example.com --token $VERCEL_TOKEN

# Then in Cloudflare DNS (DNS-only, not proxied):
# A record → Vercel IP  OR
# CNAME → cname.vercel-dns.com

Workflow Checklist

Phase 1: Initial Setup

  • Install CLIs: vercel, supabase, wrangler, jq
  • Set tokens: VERCEL_TOKEN, CLOUDFLARE_API_TOKEN
  • Link project: vercel link --yes
  • Pull env: vercel pull --yes

Phase 2: Cost Optimization

Phase 3: Secrets & Auth

  • Store secrets via vercel env add or REST API
  • Configure OIDC for cloud credentials — TOKEN-AND-KEY-MANAGEMENT.md
  • Set up Supabase auth integration

Phase 4: Database

  • Create migrations: supabase migration new
  • Apply: supabase migration up (local) / supabase db push (CI)
  • Generate types: supabase gen types typescript

Two-Button Deploy (Agent-Friendly)

bash
# Marketing (Cloudflare Pages)
pnpm -C apps/marketing build
npx wrangler pages deploy apps/marketing/dist --branch=main

# App (Vercel prebuilt)
vercel pull --yes && vercel build --prod && vercel deploy --prebuilt --prod

Critical Gotchas

GotchaFix
Ignored Build Step exits reversed0 = skip, 1 = build (not intuitive)
Ignored builds still count toward quotasUse git.deploymentEnabled: false instead
Cloudflare proxy + Vercel = problemsUse DNS-only for Vercel domains
.vercel/ folder committedAdd to .gitignore
Secrets in config filesUse vercel env or wrangler secret put

Full list: FOOTGUNS.md

Core Commands

TaskCommand
Deploy previewvercel
Deploy prodvercel --prod
Pull settingsvercel pull
Build locallyvercel build
Deploy prebuiltvercel deploy --prebuilt
List env varsvercel env ls
Add env varvercel env add NAME target
Pull env to filevercel env pull

Full CLI reference: CLI-COMMANDS.md


AGENTS.md Blurb

Copy this to your project's AGENTS.md:

markdown
### Vercel

Vercel CLI is installed and authenticated.

Project: `<PROJECT_NAME>`

Common commands:

\`\`\`bash
vercel pull --yes         # Fetch settings + env
vercel build --prod       # Build locally (saves build minutes)
vercel deploy --prebuilt --prod  # Deploy prebuilt artifact
vercel env ls             # List env vars
vercel env add SECRET production  # Add secret
\`\`\`

**Cost tip:** Use prebuilt workflow to avoid burning build credits.

References

TopicReference
Architecture & cost modelARCHITECTURE.md
Stopping build burnBUILD-CONTROL.md
API-based build controlAPI-BUILD-CONTROL.md
All CLI commandsCLI-COMMANDS.md
Secrets, env, OIDC, VaultTOKEN-AND-KEY-MANAGEMENT.md
R2 + Pages cost offloadCLOUDFLARE-OFFLOAD.md
Full automation blueprintAUTOMATION-BLUEPRINT.md
Common mistakesFOOTGUNS.md

Token Setup (Non-Interactive Auth)

bash
# Vercel: https://vercel.com/account/tokens
export VERCEL_TOKEN=xxx

# Cloudflare: https://dash.cloudflare.com/profile/api-tokens
export CLOUDFLARE_API_TOKEN=xxx

# Supabase: project settings → API
export SUPABASE_ACCESS_TOKEN=xxx

All CLIs read these automatically. No interactive login needed.

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 Vercel AI skill do?

Operate Next.js 16 SaaS on Vercel with Cloudflare DNS + Supabase. Use when deploying to Vercel, reducing build costs, managing secrets, or splitting traffic between Vercel and Cloudflare.

Why use Vercel on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations/tree/main/skills/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 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 Vercel?

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

Is the Vercel AI skill free?

It is published on GitHub by Dicklesworthstone. Check the repository for licensing terms. 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 👇