Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    forecast os lite

    1

    Access real-time prediction market probabilities from Polymarket, Kalshi, and Precog for future event forecasting.

    Free

    Security scanned
    forecast os lite

    forecast os lite

    Example session with this skill installed

    What are the market-implied odds for a Fed rate cut in December compared across different platforms?

    • Read your context and instructions
    • Compiled the forecast os lite

    I have checked the live prediction markets on Polymarket and Kalshi for the December Fed decision.

    Fed Rate Cut Probability (December)

    PlatformMarketOutcomeMarket-impliedClose
    PolymarketFed Interest Rate Decision: DecemberCut64.2%2025-12-18
    KalshiWill the Fed cut rates in December?Yes62.0% (last trade)2025-12-17

    Source: Polymarket and Kalshi public APIs, fetched 2025-10-25T10:15Z. The two markets resolve on the same economic event and show a high degree of correlation. Note that Kalshi reflects the last trade price, while Polymarket reflects current outcome prices.

    Next steps

    • Ask for all outcomes of the Polymarket "Fed Interest Rate Decision" market to see the probability of specific cut sizes.
    • Check upcoming economic markets on the Precog launchpad.
    • Use the full forecast-os skill if you need to place a trade on these odds.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    LLMs often hallucinate future events or rely on outdated training data when asked about current affairs. ForecastOS Lite provides a real-time bridge to prediction markets, delivering crowd-sourced probabilities for elections, economic shifts, and geopolitical events without the risk of model bias.

    What it does

    • Live probability retrieval Fetches market-implied odds from Polymarket, Kalshi, and Precog APIs.
    • Event discovery Searches for active markets based on entities, dates, or specific future outcomes.
    • Multi-platform comparison Aggregates data from different sources into a single view for cross-market validation.
    • Upcoming market tracking Lists Precog launchpad proposals that are currently seeking funding for deployment.
    • Timestamped freshness Includes UTC timestamps for every data point to ensure temporal accuracy.

    How it works

    1. Target selection The skill identifies the correct endpoint based on the user's specific query or named platform.
    2. Preflight check A lightweight GET request verifies connectivity to the public market APIs.
    3. Data extraction Market identifiers, outcome titles, and last-traded prices are pulled from JSON responses.
    4. Probability formatting Raw price data is converted into human-readable percentages with associated resolution dates.

    Frameworks & tools

    This skill uses curl for HTTPS GET requests to Gamma API, Kalshi V2 API, and Precog Market services. It processes data using standard JSON parsers and jq or python3 for filtering large series objects.

    Why this beats prompting it yourself

    Manual prompting relies on the model's static knowledge, which cannot track volatile market moves. This skill forces the agent to use live financial data, ensuring it reports what the market implies rather than guessing likelihoods.

    Use cases

    • Monitor live odds for election results and policy changes.
    • Compare Bitcoin price predictions across multiple decentralized platforms.
    • Track the funding status of upcoming community-proposed markets.
    • Verify the market-implied likelihood of Federal Reserve rate decisions.

    Known limitations

    Read-only access. It cannot execute trades, manage wallets, or provide executable quotes. Connectivity depends on public API availability.

    Read-only access to public APIs. No trading, wallet management, or market creation. Cannot provide live order book depth or slippage. Requires outbound HTTPS access to specific market domains.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 day ago

    • Free with an Agensi account

    Requires

    Polymarket
    Kalshi
    Precog
    Node.js

    Permissions

    Terminal / Shell
    Network Access
    Write Files
    Read Files
    Browser

    Allowed Hosts

    gamma-api.polymarket.com
    external-api.kalshi.com
    service.precog.markets
    Listed1 day ago

    What's inside

    Frequently Asked Questions

    ForecastOS Lite connects your AI agent to real-time APIs from Polymarket, Kalshi, and Precog, replacing model guesswork with live, crowd-sourced market probabilities for future events.

    No, this skill provides read-only access to market data; it lacks the permissions to execute trades, manage wallets, or perform any financial transactions on these platforms.

    The skill aggregates data from Polymarket, Kalshi, and the Precog launchpad, allowing your agent to compare odds across decentralized and regulated platforms simultaneously.

    The purchase includes the complete skill manifest, API integration logic for three major market platforms, and documentation for deployment within any AI agent framework that supports external tools.

    Yes, the skill includes UTC timestamps for every data point retrieved, ensuring your AI agent understands exactly how fresh the market data is before providing an analysis.

    ForecastOS Lite is designed to be framework-agnostic and works with any LLM or agent platform that can execute HTTPS GET requests and process JSON data.

    New in Trading & Investing