Feeds logo

Feeds

CommunityPopular
alsk1992
feeds

Real-time market data feeds from 8 prediction market platforms

Overview

Publisheralsk1992
RepositoryCloddsBot
Skill namefeeds
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 Feeds 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/feeds .claude/skills/feeds
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Feeds 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 Feeds 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 Feeds 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.

Market Feeds - Complete API Reference

Real-time and historical market data from Polymarket, Kalshi, Manifold, Metaculus, PredictIt, Drift, Betfair, and Smarkets.

Supported Platforms

PlatformFeed TypeTradingData
PolymarketWebSocket + RTDSYesPrices, orderbook, trades
KalshiWebSocketYesPrices, orderbook
BetfairWebSocketYesOdds, volume
SmarketsWebSocketYesOdds, volume
DriftRESTYesPrices, funding
ManifoldWebSocketRead-onlyPrices, comments
MetaculusRESTRead-onlyForecasts
PredictItRESTRead-onlyPrices

Chat Commands

Search Markets

/feed search "trump"                        # Search all platforms
/feed search "election" --platform poly     # Search specific platform
/feed search "fed rate" --limit 20          # Limit results

Get Prices

/feed price poly <market-id>                # Get current price
/feed price kalshi TRUMP-WIN                # Kalshi market
/feed prices "trump"                        # Prices for all matching markets

Orderbook

/feed orderbook poly <market-id>            # Get orderbook
/feed orderbook poly <market-id> --depth 10 # Limit depth

Subscribe (Real-time)

/feed subscribe poly <market-id>            # Subscribe to price updates
/feed unsubscribe poly <market-id>          # Unsubscribe
/feed subscriptions                         # List active subscriptions

News

/feed news "trump"                          # Get news for topic
/feed news <market-id>                      # News for specific market
/feed news --recent 10                      # Last 10 news items

Edge Analysis

/feed edge poly <market-id>                 # Analyze edge vs models
/feed kelly poly <market-id> --prob 0.55    # Calculate Kelly fraction

TypeScript API Reference

Create Feed Manager

typescript
import { createFeedManager } from 'clodds/feeds';

const feeds = createFeedManager({
  platforms: ['polymarket', 'kalshi', 'manifold', 'betfair'],

  // Enable real-time
  enableRealtime: true,

  // Platform credentials (optional for read-only)
  polymarket: { apiKey },
  kalshi: { apiKey },
  betfair: { appKey, sessionToken },
});

Search Markets

typescript
// Search across all platforms
const results = await feeds.searchMarkets('trump election', {
  platforms: ['polymarket', 'kalshi'],
  limit: 20,
  sortBy: 'volume',
});

for (const market of results) {
  console.log(`[${market.platform}] ${market.question}`);
  console.log(`  Price: ${market.price}`);
  console.log(`  Volume: $${market.volume.toLocaleString()}`);
}

Get Single Market

typescript
// Get specific market
const market = await feeds.getMarket('polymarket', 'market-123');

console.log(`Question: ${market.question}`);
console.log(`YES: ${market.yesPrice} / NO: ${market.noPrice}`);
console.log(`Volume: $${market.volume.toLocaleString()}`);
console.log(`End date: ${market.endDate}`);

Get Price

typescript
// Get current price
const price = await feeds.getPrice('polymarket', 'market-123');

console.log(`YES: ${price.yes}`);
console.log(`NO: ${price.no}`);
console.log(`Spread: ${price.spread}`);
console.log(`Updated: ${price.timestamp}`);

Get Orderbook

typescript
// Get orderbook
const orderbook = await feeds.getOrderbook('polymarket', 'market-123', {
  depth: 10,
});

console.log('Bids (YES):');
for (const bid of orderbook.bids) {
  console.log(`  ${bid.price}: $${bid.size}`);
}

console.log('Asks (YES):');
for (const ask of orderbook.asks) {
  console.log(`  ${ask.price}: $${ask.size}`);
}

Subscribe to Real-time Updates

typescript
// Subscribe to price updates
const subscription = await feeds.subscribePrice('polymarket', 'market-123');

subscription.on('price', (update) => {
  console.log(`Price update: YES=${update.yes}, NO=${update.no}`);
});

subscription.on('trade', (trade) => {
  console.log(`Trade: ${trade.side} ${trade.size} @ ${trade.price}`);
});

// Unsubscribe
await subscription.unsubscribe();

News

typescript
// Get recent news
const news = await feeds.getRecentNews('trump', { limit: 10 });

for (const article of news) {
  console.log(`[${article.source}] ${article.title}`);
  console.log(`  ${article.summary}`);
  console.log(`  ${article.url}`);
}

// Search news
const searchResults = await feeds.searchNews('federal reserve', {
  from: '2024-01-01',
  sources: ['reuters', 'bloomberg'],
});

Edge Analysis

typescript
// Analyze edge vs external models
const edge = await feeds.analyzeEdge('polymarket', 'market-123');

console.log(`Market price: ${edge.marketPrice}`);
console.log(`Model estimates:`);
for (const model of edge.models) {
  console.log(`  ${model.name}: ${model.estimate}`);
  console.log(`    Edge: ${model.edge > 0 ? '+' : ''}${model.edge.toFixed(1)}%`);
}
console.log(`Consensus edge: ${edge.consensusEdge.toFixed(1)}%`);

Kelly Criterion

typescript
// Calculate optimal position size
const kelly = await feeds.calculateKelly({
  platform: 'polymarket',
  marketId: 'market-123',
  estimatedProbability: 0.55,  // Your estimate
  bankroll: 10000,             // Your bankroll
  kellyFraction: 0.5,          // Half-Kelly for safety
});

console.log(`Market price: ${kelly.marketPrice}`);
console.log(`Your estimate: ${kelly.estimatedProb}`);
console.log(`Edge: ${kelly.edge.toFixed(1)}%`);
console.log(`Full Kelly: ${kelly.fullKelly.toFixed(1)}%`);
console.log(`Recommended size: $${kelly.recommendedSize}`);

Platform-Specific Features

Polymarket RTDS (Real-time Data Service)

typescript
// Connect to RTDS for ultra-low-latency updates
const rtds = await feeds.connectRTDS('polymarket');

rtds.on('tick', (tick) => {
  console.log(`${tick.market}: ${tick.price} (${tick.side})`);
});

rtds.subscribe(['market-123', 'market-456']);

Betfair Odds

typescript
// Get Betfair odds
const odds = await feeds.getBetfairOdds('event-123');

for (const runner of odds.runners) {
  console.log(`${runner.name}: ${runner.backOdds} / ${runner.layOdds}`);
}

Metaculus Forecasts

typescript
// Get Metaculus community forecast
const forecast = await feeds.getMetaculusForecast('question-123');

console.log(`Community median: ${forecast.median}`);
console.log(`25th percentile: ${forecast.q25}`);
console.log(`75th percentile: ${forecast.q75}`);
console.log(`Forecasters: ${forecast.forecasterCount}`);

Data Refresh Rates

PlatformRESTWebSocket
Polymarket5sReal-time
Kalshi10sReal-time
Betfair1sReal-time
Manifold30sReal-time
Metaculus60sN/A
PredictIt30sN/A

Best Practices

  1. Use WebSocket for real-time trading decisions
  2. Cache responses for non-time-sensitive queries
  3. Respect rate limits - batch requests when possible
  4. Subscribe selectively - only to markets you need
  5. Handle reconnections - WebSocket connections can drop

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 Feeds AI skill do?

Real-time market data feeds from 8 prediction market platforms

Why use Feeds on TypingMind?

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

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

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 Feeds?

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

Is the Feeds 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 👇