Fanvue logo

Fanvue

Community
viralcode
Fanvue

Manage content, chats, subscribers, and earnings on the Fanvue creator platform via OAuth 2.0 API.

Overview

Publisherviralcode
Repositoryopenwhale
Skill nameFanvue
Stars
65
Forks
11
Bundled files
7
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.

  • 7 bundled files

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

  • Open source

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

Installation

Install the Fanvue 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/viralcode/openwhale.git /tmp/openwhale
mkdir -p .claude/skills
cp -r /tmp/openwhale/skills/fanvue .claude/skills/Fanvue
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Fanvue 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 Fanvue 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 Fanvue 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.

Fanvue API Skill

Integrate with the Fanvue creator platform to manage chats, posts, subscribers, earnings insights, and media content.

Prerequisites

1. Create an OAuth Application

  1. Go to the Fanvue Developer Portal
  2. Create a new OAuth application
  3. Note your Client ID and Client Secret
  4. Configure your Redirect URI (e.g., https://your-app.com/callback)

2. Environment Variables

Set these environment variables:

bash
FANVUE_CLIENT_ID=your_client_id
FANVUE_CLIENT_SECRET=your_client_secret
FANVUE_REDIRECT_URI=https://your-app.com/callback

Authentication

Fanvue uses OAuth 2.0 with PKCE (Proof Key for Code Exchange). All API requests require:

  • Authorization Header: Bearer <access_token>
  • API Version Header: X-Fanvue-API-Version: 2025-06-26

OAuth Scopes

Request these scopes based on your needs:

ScopeAccess
openidOpenID Connect authentication
offline_accessRefresh token support
offlineOffline access
read:selfRead authenticated user profile
read:chatRead chat conversations
write:chatSend messages, update chats
read:postRead posts
write:postCreate posts
read:creatorRead subscriber/follower data
read:mediaRead media vault
write:tracking_linksManage campaign links
read:insightsRead earnings/analytics (creator accounts)
read:subscribersRead subscriber lists (creator accounts)

Note: Some endpoints (subscribers, insights, earnings) require a creator account and may need additional scopes not listed in the public documentation.

Quick Auth Flow

typescript
import { randomBytes, createHash } from 'crypto';

// 1. Generate PKCE parameters
const codeVerifier = randomBytes(32).toString('base64url');
const codeChallenge = createHash('sha256')
  .update(codeVerifier)
  .digest('base64url');

// 2. Build authorization URL
const authUrl = new URL('https://auth.fanvue.com/oauth2/auth');
authUrl.searchParams.set('client_id', process.env.FANVUE_CLIENT_ID);
authUrl.searchParams.set('redirect_uri', process.env.FANVUE_REDIRECT_URI);
authUrl.searchParams.set('response_type', 'code');
authUrl.searchParams.set('scope', 'openid offline_access read:self read:chat write:chat read:post');
authUrl.searchParams.set('state', randomBytes(32).toString('hex'));
authUrl.searchParams.set('code_challenge', codeChallenge);
authUrl.searchParams.set('code_challenge_method', 'S256');

// Redirect user to: authUrl.toString()
typescript
// 3. Exchange authorization code for tokens
const tokenResponse = await fetch('https://auth.fanvue.com/oauth2/token', {
  method: 'POST',
  headers: { 'Content-Type': 'application/x-www-form-urlencoded' },
  body: new URLSearchParams({
    grant_type: 'authorization_code',
    client_id: process.env.FANVUE_CLIENT_ID,
    client_secret: process.env.FANVUE_CLIENT_SECRET,
    code: authorizationCode,
    redirect_uri: process.env.FANVUE_REDIRECT_URI,
    code_verifier: codeVerifier,
  }),
});

const tokens = await tokenResponse.json();
// tokens.access_token, tokens.refresh_token

API Base URL

All API requests go to: https://api.fanvue.com

Standard Request Headers

typescript
const headers = {
  'Authorization': `Bearer ${accessToken}`,
  'X-Fanvue-API-Version': '2025-06-26',
  'Content-Type': 'application/json',
};

Agent Automation

These workflows are designed for AI agents automating Fanvue creator accounts.

Accessing Images (with Signed URLs)

The basic /media endpoint only returns metadata. To get actual viewable URLs, use the variants query parameter:

typescript
// Step 1: List all media
const list = await fetch('https://api.fanvue.com/media', { headers });
const { data } = await list.json();

// Step 2: Get signed URLs for a specific media item
const media = await fetch(
  `https://api.fanvue.com/media/${uuid}?variants=main,thumbnail,blurred`, 
  { headers }
);
const { variants } = await media.json();

// variants = [
//   { variantType: 'main', url: 'https://media.fanvue.com/private/...' },
//   { variantType: 'thumbnail', url: '...' },
//   { variantType: 'blurred', url: '...' }
// ]

Variant Types:

  • main - Full resolution original
  • thumbnail - Optimized preview (smaller)
  • blurred - Censored version for teasers

Creating a Post with Media

typescript
// Step 1: Have existing media UUIDs from vault
const mediaIds = ['media-uuid-1', 'media-uuid-2'];

// Step 2: Create post
const response = await fetch('https://api.fanvue.com/posts', {
  method: 'POST',
  headers,
  body: JSON.stringify({
    text: 'Check out my new content! 🔥',
    mediaIds,
    audience: 'subscribers',  // or 'followers-and-subscribers'
    // Optional:
    price: null,              // Set for pay-per-view
    publishAt: null,          // Set for scheduled posts
  }),
});

Audience Options:

ValueWho Can See
subscribersPaid subscribers only
followers-and-subscribersBoth free followers and subscribers

Sending Messages with Media

typescript
// Get subscriber list for decision making
const subs = await fetch('https://api.fanvue.com/creators/list-subscribers', { headers });
const { data: subscribers } = await subs.json();

// Get top spenders for VIP targeting
const vips = await fetch('https://api.fanvue.com/insights/get-top-spenders', { headers });
const { data: topSpenders } = await vips.json();

// Send personalized message with media
await fetch('https://api.fanvue.com/chat-messages', {
  method: 'POST',
  headers,
  body: JSON.stringify({
    recipientUuid: subscribers[0].userUuid,
    content: 'Thanks for being a subscriber! Here\'s something special for you 💕',
    mediaIds: ['vault-media-uuid'],  // Attach media from vault
  }),
});

// Or send to multiple subscribers at once
await fetch('https://api.fanvue.com/chat-messages/mass', {
  method: 'POST',
  headers,
  body: JSON.stringify({
    recipientUuids: subscribers.map(s => s.userUuid),
    content: 'New exclusive content just dropped! 🎉',
    mediaIds: ['vault-media-uuid'],
  }),
});

Agent Decision Context

For effective automation, gather this context:

typescript
interface AutomationContext {
  // Current media in vault
  media: {
    uuid: string;
    name: string;
    type: 'image' | 'video';
    description: string;  // AI-generated caption
    signedUrl: string;    // From variants query
  }[];
  
  // Audience data
  subscribers: {
    uuid: string;
    name: string;
    subscribedAt: string;
    tier: string;
  }[];
  
  // Engagement signals
  topSpenders: {
    uuid: string;
    totalSpent: number;
  }[];
  
  // Recent earnings for trend analysis
  earnings: {
    period: string;
    total: number;
    breakdown: { type: string; amount: number }[];
  };
}

Core Operations

Get Current User

typescript
const response = await fetch('https://api.fanvue.com/users/me', { headers });
const user = await response.json();

List Chats

typescript
const response = await fetch('https://api.fanvue.com/chats', { headers });
const { data, pagination } = await response.json();

Send a Message

typescript
const response = await fetch('https://api.fanvue.com/chat-messages', {
  method: 'POST',
  headers,
  body: JSON.stringify({
    recipientUuid: 'user-uuid-here',
    content: 'Hello! Thanks for subscribing!',
  }),
});

Create a Post

typescript
const response = await fetch('https://api.fanvue.com/posts', {
  method: 'POST',
  headers,
  body: JSON.stringify({
    content: 'New content available!',
    // Add media IDs, pricing, etc.
  }),
});

Get Earnings

typescript
const response = await fetch('https://api.fanvue.com/insights/get-earnings', { headers });
const earnings = await response.json();

List Subscribers

typescript
const response = await fetch('https://api.fanvue.com/creators/list-subscribers', { headers });
const { data } = await response.json();

API Reference

See api-reference.md for the complete endpoint documentation.


Token Refresh

Access tokens expire. Use the refresh token to get new ones:

typescript
const response = await fetch('https://auth.fanvue.com/oauth2/token', {
  method: 'POST',
  headers: { 'Content-Type': 'application/x-www-form-urlencoded' },
  body: new URLSearchParams({
    grant_type: 'refresh_token',
    client_id: process.env.FANVUE_CLIENT_ID,
    client_secret: process.env.FANVUE_CLIENT_SECRET,
    refresh_token: currentRefreshToken,
  }),
});

const newTokens = await response.json();

Error Handling

Common HTTP status codes:

StatusMeaning
200Success
400Bad request - check your parameters
401Unauthorized - token expired or invalid
403Forbidden - missing required scope
404Resource not found
429Rate limited - slow down requests

Resources

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 Fanvue AI skill do?

Manage content, chats, subscribers, and earnings on the Fanvue creator platform via OAuth 2.0 API.

Why use Fanvue on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/viralcode/openwhale/tree/main/skills/fanvue. 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 Fanvue?

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 Fanvue?

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

Is the Fanvue AI skill free?

It is published on GitHub by viralcode. 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 👇