Vibes logo

Vibes

Community
popmechanic
vibes

Self-contained app generator — invoke this skill directly, do not decompose into sub-steps. Generates React web apps with TinyBase reactive data store. Use when creating new web applications, adding components, or working with real-time data. Ideal for quick prototypes and single-page apps that need real-time data sync.

Overview

Publisherpopmechanic
RepositoryVibesOS
Skill namevibes
Stars
134
Forks
6
Bundled files
135
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.

  • 135 bundled files

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

  • Open source

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

Installation

Install the Vibes 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/popmechanic/VibesOS.git /tmp/VibesOS
mkdir -p .claude/skills
cp -r /tmp/VibesOS/skills/vibes .claude/skills/vibes
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vibes 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 Vibes 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 Vibes 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.

Plan mode: If you are planning work, this entire skill is ONE plan step: "Invoke /vibes:vibes". Do not decompose the steps below into separate plan tasks.

Display this ASCII art immediately when starting:

░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░▒▓███████▓▒░░▒▓████████▓▒░░▒▓███████▓▒░
░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░      ░▒▓█▓▒░
 ░▒▓█▓▒▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░      ░▒▓█▓▒░
 ░▒▓█▓▒▒▓█▓▒░░▒▓█▓▒░▒▓███████▓▒░░▒▓██████▓▒░  ░▒▓██████▓▒░
  ░▒▓█▓▓█▓▒░ ░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░             ░▒▓█▓▒░
  ░▒▓█▓▓█▓▒░ ░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░             ░▒▓█▓▒░
   ░▒▓██▓▒░  ░▒▓█▓▒░▒▓███████▓▒░░▒▓████████▓▒░▒▓███████▓▒░

Quick Navigation


Vibes DIY App Generator

Generate React web applications using TinyBase for reactive data with real-time sync.

Auth Check (silent — only prompt if needed)

Before asking Terminal or Editor, check for cached auth:

bash
VIBES_ROOT="${CLAUDE_PLUGIN_ROOT:-$(dirname "$(dirname "${CLAUDE_SKILL_DIR}")")}"
bun --input-type=module -e "
import { readCachedTokens, isTokenExpired } from '$VIBES_ROOT/scripts/lib/cli-auth.js';
const tokens = readCachedTokens();
if (tokens && !isTokenExpired(tokens.expiresAt)) {
  console.log('AUTH_OK');
} else {
  console.log('AUTH_NEEDED');
}
"
  • If AUTH_OK → proceed silently to "Terminal or Editor?" (do not mention auth)
  • If AUTH_NEEDED → ask: "To deploy apps, you'll need a Vibes account. Sign in now? (A browser window will open for Pocket ID — takes about 10 seconds.)"
    • If yes:
      bash
      VIBES_ROOT="${CLAUDE_PLUGIN_ROOT:-$(dirname "$(dirname "${CLAUDE_SKILL_DIR}")")}"
      bun --input-type=module -e "
      import { getAccessToken } from '$VIBES_ROOT/scripts/lib/cli-auth.js';
      import { OIDC_AUTHORITY, OIDC_CLIENT_ID } from '$VIBES_ROOT/scripts/lib/auth-constants.js';
      const tokens = await getAccessToken({ authority: OIDC_AUTHORITY, clientId: OIDC_CLIENT_ID });
      if (tokens) console.log('Signed in successfully!');
      "
      Confirm success, then proceed to "Terminal or Editor?"
    • If no → proceed anyway (auth will be needed at deploy time)

Step 0: Terminal or Editor UI?

This is the very first question — ask before anything else (after auth check above). Do not check .env, credentials, or project state before asking this question. Do not invoke any other skill before asking this question. If Editor is chosen, skip all pre-flight checks — the editor handles everything.

Ask the user:

"How do you want to build? Editor (opens a browser UI with live preview, chat, and deploy button) or Terminal (I'll generate and deploy from here)?"

Present Editor as the first/recommended option.

  • If Editor: Start the editor server and END YOUR TURN. Do not ask any more questions. Do not continue to Pre-Flight Check or any step below. The editor UI handles the entire workflow — setup, generation, preview, deploy.

    Launch the editor server:

    bash
    VIBES_ROOT="${CLAUDE_PLUGIN_ROOT:-$(dirname "$(dirname "${CLAUDE_SKILL_DIR}")")}"
    bun "$VIBES_ROOT/scripts/server.ts" --mode=editor --prompt "USER_PROMPT_HERE"

    If no prompt was given, omit --prompt:

    bash
    VIBES_ROOT="${CLAUDE_PLUGIN_ROOT:-$(dirname "$(dirname "${CLAUDE_SKILL_DIR}")")}"
    bun "$VIBES_ROOT/scripts/server.ts" --mode=editor

    Tell the user: "Open http://localhost:3333 — the editor handles everything from here." Your job is done. Stop. Do not read further. Do not proceed to any step below.

  • If Terminal: Continue with the project folder selection and normal generation workflow below.


⛔ EVERYTHING BELOW IS TERMINAL MODE ONLY

If the user chose Editor above, STOP. Do not read or execute anything below this line. The editor UI handles setup, generation, preview, and deployment.


Project Folder

Before generating, ask the user where to save the project:

"Where should this project live? Enter a path or press Enter for the default (~/VibesOS/{app-slug}/)."

  • If the user provides a path, use it as the project directory
  • If they press Enter, use ~/VibesOS/{app-slug}/ (the slug is derived from the prompt later — for now just note the preference)
  • Create the directory if it doesn't exist
bash
VIBES_ROOT="${CLAUDE_PLUGIN_ROOT:-$(dirname "$(dirname "${CLAUDE_SKILL_DIR}")")}"
mkdir -p "$PROJECT_DIR"

After the directory is ready, initialize vibes.json:

bash
bun -e "
  const { initVibesJson } = await import('$VIBES_ROOT/scripts/lib/vibes-json.js');
  initVibesJson('$PROJECT_DIR');
"

Use $PROJECT_DIR as the working directory (cwd) for all subsequent code generation. The generated app.jsx and assembled index.html will be written here.


Pre-Flight Check

Complete these steps before generating any app code.

  • Auth is automatic — on first deploy, a browser window opens for Pocket ID login
  • Tokens are cached at ~/.vibes/auth.json for subsequent deploys
  • Sync infrastructure deploys automatically on first app deploy — no manual setup needed

Read ${CLAUDE_SKILL_DIR}/references/generation-rules.md for platform constraints, core rules, what generated code must/must not contain, generation process, assembly workflow, and the <Markdown> component for rendering formatted text.


Read ${CLAUDE_SKILL_DIR}/references/style-guide.md for OKLCH colors, theming, design token overrides, and visual style patterns.


Read ${CLAUDE_SKILL_DIR}/references/data-api.md for the complete TinyBase hook API reference, data access patterns, user identity, game patterns, reference app, and bug prevention checklist.


When to Read Extended Docs

Read these reference files when the user's prompt matches the signals below:

NeedSignal in PromptRead This
TinyBase data patternsforms, lists, filtering, ordering, pagination, master-detail${CLAUDE_SKILL_DIR}/references/tinybase-patterns.md
Multiplayer / shared appsmultiplayer, collaborative, shared, multi-user, game with players${CLAUDE_SKILL_DIR}/references/multiplayer-guide.md
Game developmentgame, timer, countdown, turn-based, score${CLAUDE_SKILL_DIR}/references/game-patterns.md
AI-powered featuresAI, chatbot, summarize, generate, openrouter${CLAUDE_SKILL_DIR}/references/ai-integration.md
Bug prevention referencedebugging, troubleshooting, reviewing code${CLAUDE_SKILL_DIR}/references/bug-prevention.md
Design tokens & themingcolors, theme, tokens, brand colors, styling${CLAUDE_PLUGIN_ROOT}/build/design-tokens.txt
Full design system detailsdetailed design system, spacing, typography${CLAUDE_SKILL_DIR}/defaults/style-prompt.txt
Advanced visual effects"interactive", "animated", "3D", "particles", "shader", "canvas"${CLAUDE_SKILL_DIR}/defaults/advanced-effects-prompt.txt

Deployment Options

After generating your app, deploy it:

  • Cloudflare - Edge deployment with Workers. Use /vibes:cloudflare to deploy.

What's Next?

After generating and assembling the app, present these options using AskUserQuestion:

Question: "Your app is live! Want to turn it into a product? The /sell skill adds multi-tenant SaaS with auth and billing. Or pick another direction:"
Header: "Next"
Options:
- Label: "Keep improving this app"
  Description: "Continue iterating on what you've built. Add new features, refine the styling, or adjust functionality. Great when you have a clear vision and want to polish it further."

- Label: "Apply a design reference (/design)"
  Description: "Have a design.html or mockup file? This skill mechanically transforms your app to match it exactly - pixel-perfect fidelity with your TinyBase data binding preserved."

- Label: "Explore variations (/riff)"
  Description: "Not sure if this is the best approach? Riff generates 3-10 completely different interpretations of your idea in parallel. You'll get ranked variations with business model analysis to help you pick the winner."

- Label: "Make it a SaaS (/sell)"
  Description: "Ready to monetize? Sell transforms your app into a multi-tenant SaaS with Pocket ID authentication, subscription billing, and isolated databases per customer. Each user gets their own subdomain."

- Label: "Deploy to Cloudflare (/cloudflare)"
  Description: "Go live on the edge. Deploy to Cloudflare Workers with a subdomain registry, KV storage, and global CDN. Fast, scalable, and always on."

- Label: "I'm done for now"
  Description: "Wrap up this session. Your files are saved locally - come back anytime to continue."

After user responds:

  • "Keep improving" → Acknowledge and stay ready for iteration prompts. After each round of changes to app.jsx, re-run assembly and re-deploy.
  • "Apply a design reference" → Auto-invoke /vibes:design skill
  • "Explore variations" → Auto-invoke /vibes:riff skill
  • "Make it a SaaS" → Auto-invoke /vibes:factory skill
  • "Deploy" → Auto-invoke /vibes:cloudflare skill
  • "I'm done" → Confirm files saved, wish them well

Do not proceed to code generation until: Pre-flight check is complete (auth is automatic on deploy — no credentials to collect).

Bundled files

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

and 75 more files.

Frequently asked questions

What does the Vibes AI skill do?

Self-contained app generator — invoke this skill directly, do not decompose into sub-steps. Generates React web apps with TinyBase reactive data store. Use when creating new web applications, adding components, or working with real-time data. Ideal for quick prototypes and single-page apps that need real-time data sync.

Why use Vibes on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/popmechanic/VibesOS/tree/main/skills/vibes. 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 Vibes?

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 Vibes?

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

Is the Vibes AI skill free?

Yes. It is published on GitHub by popmechanic 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 👇