Integrations logo

Integrations

CommunityPopular
alsk1992
integrations

External data sources, connectors, and custom data streams

Overview

Publisheralsk1992
RepositoryCloddsBot
Skill nameintegrations
Stars
2.8K
Forks
336
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

    Published by alsk1992 on GitHub. Read the source before you install it.

Installation

Install the Integrations 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/alsk1992/CloddsBot.git /tmp/CloddsBot
mkdir -p .claude/skills
cp -r /tmp/CloddsBot/src/skills/bundled/integrations .claude/skills/integrations
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Integrations 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 Integrations 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 Integrations 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.

Integrations - Complete API Reference

Manage external data sources, add custom connectors, and plug in new data streams for trading bots.


Chat Commands

List Data Sources

/integrations                               List all data sources
/integrations status                        Show source health
/integrations sources                       Available source types

Manage Sources

/integrations enable fedwatch              Enable CME FedWatch
/integrations disable 538                   Disable FiveThirtyEight
/integrations add webhook "my-signals"      Add custom webhook source
/integrations add rest "my-api" <url>       Add REST API source
/integrations remove <source-id>            Remove data source

Configure Sources

/integrations config fedwatch              View source config
/integrations set fedwatch interval 60     Set refresh interval
/integrations set fedwatch key <api-key>   Set API key
/integrations test <source-id>             Test source connection

View Data

/integrations data fedwatch                Latest data from source
/integrations history <source> --hours 24  Historical data
/integrations subscribe <source>           Real-time updates

TypeScript API Reference

Create Integrations Manager

typescript
import { createIntegrationsManager } from 'clodds/integrations';

const integrations = createIntegrationsManager({
  // Storage
  storage: 'sqlite',
  dbPath: './integrations.db',

  // Default refresh interval
  defaultIntervalMs: 60000,

  // Retry settings
  maxRetries: 3,
  retryDelayMs: 5000,
});

Built-in Data Sources

typescript
// Enable built-in sources
await integrations.enable('fedwatch');     // CME FedWatch
await integrations.enable('538');          // FiveThirtyEight
await integrations.enable('silver');       // Silver Bulletin
await integrations.enable('rcp');          // RealClearPolitics
await integrations.enable('odds-api');     // The Odds API
await integrations.enable('polymarket');   // Polymarket prices
await integrations.enable('kalshi');       // Kalshi prices
await integrations.enable('binance');      // Binance spot prices
await integrations.enable('crypto');       // Multi-exchange crypto

Add Custom Webhook Source

typescript
// Add webhook to receive custom signals
const source = await integrations.addWebhook({
  name: 'my-signals',
  description: 'Custom trading signals',

  // Webhook config
  path: '/webhooks/my-signals',
  secret: process.env.WEBHOOK_SECRET,

  // Data schema (optional validation)
  schema: {
    type: 'object',
    properties: {
      signal: { type: 'string', enum: ['BUY', 'SELL', 'HOLD'] },
      symbol: { type: 'string' },
      confidence: { type: 'number', min: 0, max: 1 },
    },
    required: ['signal', 'symbol'],
  },

  // Transform incoming data
  transform: (payload) => ({
    signal: payload.signal,
    symbol: payload.symbol,
    confidence: payload.confidence || 0.5,
    timestamp: Date.now(),
  }),
});

console.log(`Webhook URL: ${source.url}`);
// POST to: https://your-domain.com/webhooks/my-signals

Add Custom REST Source

typescript
// Add REST API data source
const source = await integrations.addRest({
  name: 'my-api',
  description: 'Custom price API',

  // API config
  url: 'https://api.example.com/prices',
  method: 'GET',
  headers: {
    'Authorization': `Bearer ${process.env.MY_API_KEY}`,
  },

  // Polling interval
  intervalMs: 30000,

  // Transform response
  transform: (response) => ({
    price: response.data.price,
    volume: response.data.volume,
    timestamp: Date.now(),
  }),
});

Add WebSocket Source

typescript
// Add WebSocket data source
const source = await integrations.addWebSocket({
  name: 'live-prices',
  description: 'Real-time price feed',

  // WebSocket config
  url: 'wss://stream.example.com/prices',

  // Message handlers
  onMessage: (data) => ({
    type: 'price',
    symbol: data.s,
    price: parseFloat(data.p),
    timestamp: data.t,
  }),

  // Subscription message
  subscribe: {
    method: 'SUBSCRIBE',
    params: ['btcusdt@trade'],
  },

  // Reconnect settings
  reconnect: true,
  reconnectIntervalMs: 5000,
});

Subscribe to Data

typescript
// Subscribe to real-time updates
integrations.subscribe('my-signals', (data) => {
  console.log(`Signal: ${data.signal} ${data.symbol}`);
  console.log(`Confidence: ${data.confidence}`);

  if (data.signal === 'BUY' && data.confidence > 0.8) {
    // Execute trade logic
  }
});

// Subscribe to multiple sources
integrations.subscribeAll(['fedwatch', 'crypto', 'my-signals'], (source, data) => {
  console.log(`[${source}] ${JSON.stringify(data)}`);
});

Get Latest Data

typescript
// Get current data from source
const fedData = await integrations.getData('fedwatch');

console.log('Fed Rate Probabilities:');
for (const meeting of fedData.meetings) {
  console.log(`${meeting.date}: ${meeting.probabilities}`);
}

// Get with freshness check
const data = await integrations.getData('crypto', {
  maxAgeMs: 60000,  // Refetch if older than 60s
});

Check Status

typescript
// Get source status
const status = await integrations.getStatus('my-api');

console.log(`Status: ${status.status}`);  // 'healthy' | 'degraded' | 'error'
console.log(`Last fetch: ${status.lastFetch}`);
console.log(`Last error: ${status.lastError}`);
console.log(`Fetch count: ${status.fetchCount}`);
console.log(`Error count: ${status.errorCount}`);

// Get all statuses
const all = await integrations.getAllStatuses();

Built-in Data Sources

SourceTypeDataRefresh
fedwatchRESTFed rate probabilities5 min
538RESTElection forecasts1 hour
silverRESTSilver Bulletin forecasts1 hour
rcpRESTPolling averages15 min
odds-apiRESTSports betting odds1 min
polymarketWebSocketMarket pricesReal-time
kalshiWebSocketMarket pricesReal-time
binanceWebSocketCrypto pricesReal-time

Custom Source Types

TypeBest ForLatency
webhookExternal signals pushed to youInstant
restAPIs you poll periodicallySeconds
websocketReal-time streaming dataMilliseconds

Using Data in Bots

typescript
import { createTradingBot } from 'clodds/trading';
import { createIntegrationsManager } from 'clodds/integrations';

const integrations = createIntegrationsManager();
const bot = createTradingBot();

// Use custom signals in bot strategy
integrations.subscribe('my-signals', async (signal) => {
  if (signal.signal === 'BUY' && signal.confidence > 0.9) {
    await bot.execute({
      platform: 'polymarket',
      market: signal.symbol,
      side: 'YES',
      size: 100 * signal.confidence,
    });
  }
});

// Use Fed data for macro bets
integrations.subscribe('fedwatch', async (data) => {
  const cutProb = data.meetings[0].probabilities['25bp_cut'];
  if (cutProb > 0.8) {
    // High probability of rate cut
    await bot.execute({
      platform: 'kalshi',
      market: 'fed-rate-cut',
      side: 'YES',
      size: 500,
    });
  }
});

Environment Variables

bash
# Built-in sources
CME_FEDWATCH_API_KEY=your-key
FIVETHIRTYEIGHT_API_KEY=your-key
ODDS_API_KEY=your-key

# Custom sources
MY_SIGNALS_WEBHOOK_SECRET=your-secret
MY_API_KEY=your-key

Best Practices

  1. Validate incoming data — Use schemas for webhooks
  2. Set appropriate intervals — Don't poll too frequently
  3. Handle errors gracefully — Sources will fail sometimes
  4. Monitor freshness — Alert on stale data
  5. Transform consistently — Normalize data formats
  6. Use WebSocket for latency — When milliseconds matter

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 Integrations AI skill do?

External data sources, connectors, and custom data streams

Why use Integrations on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/integrations. 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 Integrations?

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 Integrations?

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

Is the Integrations AI skill free?

Yes. It is published on GitHub by alsk1992 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 👇