Trading Strategies

This is a comprehensive framework for building prediction market trading bots with actual strategy classes you can extend. You get a clean base class with signal generation, four concrete strategy implementations (arbitrage, copy trading, momentum, mean reversion), and position sizing logic. The arbitrage strategy catches YES+NO pricing inefficiencies, copy trading mirrors successful wallets with configurable delay and sizing, and the technical strategies use z-scores and orderbook imbalance calculations. It's well structured if you're building automated traders and want to backtest different approaches without writing everything from scratch. The signal confidence scoring and metadata tracking are thoughtful touches that make strategies debuggable in production.

skills.sh installs: 1.3K
GitHub stars: 26
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add agentmc15/polymarket-trader --skill trading-strategies --agent claude-code

Installs into .claude/skills of the current project.

Files

Trading Strategy Development Skill

Strategy Base Class

from abc import ABC, abstractmethod
from dataclasses import dataclass
from typing import Optional
from datetime import datetime
from enum import Enum

class SignalType(Enum):
    BUY = "buy"
    SELL = "sell"
    HOLD = "hold"

@dataclass
class Signal:
    type: SignalType
    token_id: str
    price: float
    size: float
    confidence: float  # 0-1
    timestamp: datetime
    metadata: dict = None

@dataclass
class MarketState:
    token_id: str
    yes_price: float
    no_price: float
    volume_24h: float
    open_interest: float
    orderbook: dict
    recent_trades: list
    timestamp: datetime

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly