An advanced AI trading skill for Polymarket BTC 1h markets using Binance as the source of truth for fair probability modeling and edge detection.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install polymarket-trader
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install polymarket-trader using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Polymarket Trader?
The Polymarket Trader skill is a sophisticated toolset designed for the Openclaw Skills ecosystem to automate and optimize BTC 1h Up/Down market strategies. By anchoring decision-making to real-time Binance BTCUSDT klines, it enables traders to identify mispricing between the resolution source and market prices. It provides a robust framework for professional-grade trading, focusing on statistical edge rather than speculation.
This skill bridges the gap between raw market data and actionable execution. It calculates fair probability by analyzing volatility and time-to-expiry, ensuring that every trade initiated within the Openclaw Skills framework is backed by measurable confidence. The inclusion of anti-churn and risk rules makes it a complete package for developers building automated trading agents.
Polymarket Trader Use Cases
- Designing mispricing models to find the statistical edge between fair probability and market price.
- Adding regime filters to differentiate between trend-following and range-bound market conditions.
- Debugging entry and exit points using structured logs like events.jsonl and state.json.
- Running offline analysis and parameter sweeps to fine-tune strategy performance before deployment.
How Polymarket Trader Works
- The agent confirms the market type specifically for bitcoin-up-or-down-1h markets.
- It fetches the anchor signal from Binance, including 1m closes and the 1h open for the target period.
- The skill computes volatility (sigma) and time-to-expiry to generate a fair probability for Up/Down outcomes.
- Trade execution occurs only when the calculated edge (fair probability minus market price) exceeds a defined threshold.
- It applies directional guardrails and z-score analysis to prevent betting against strong trends.
- Exits are managed via model-flip logic or reversion targets depending on the entry mode.
Polymarket Trader Setup
To integrate this skill into your Openclaw Skills environment, ensure the bundled Python scripts are located in your workspace directory. You can run individual analysis components using the following commands:
# Fetch Binance klines for data anchoring
python scripts/binance_klines.py
# Compute market regime metrics
python scripts/binance_regime.py
# Explain recent fills and performance
python scripts/explain_fills.py
Polymarket Trader Data Schema & Taxonomy
The skill organizes its operations through a specific set of files and metadata formats:
| File | Format | Description |
|---|---|---|
| events.jsonl | JSONL | Records fill data, including side, outcome, price, and reason |
| state.json | JSON | Maintains current agent status and risk management parameters |
| strategy.md | Markdown | Reference file containing math models, sigma calculations, and tuning checklists |
| binance_klines | JSON Output | Raw kline data used for anchor signal generation |
Polymarket Trader Advanced Features
- Real-time Binance resolution source anchoring for high-accuracy fair price estimation.
- Automated regime metrics including slope10 and ret15 to identify market stabilization.
- Comprehensive fills explanation script that correlates Openclaw Skills trade data with Binance context.
- Custom exit blocks that differentiate between model-driven decay and mean-reversion targets.
- Integrated z-score guardrails to prevent high-risk entries during non-trivial market moves.
SKILL.md
Loading
Related Openclaw Skills
WeChat MCP
A specialized Model Context Protocol (MCP) skill that enables AI agents to monitor, search, and send messages through the Windows WeChat desktop application.
Xiaohongshu Auto-Publisher
A powerful automation tool for Xiaohongshu that handles content publishing, login management, and batch operations via MCP.
WeChat MCP for Windows
A professional automation skill for monitoring and sending messages through the Windows desktop version of WeChat using the Model Context Protocol.
PPT Maker
An automated presentation generator that creates professional PowerPoint slides with tech-themed designs and versatile layouts.
Linux GUI Control
A comprehensive automation skill for controlling Linux desktop applications via window management and input simulation.
ClawBridge Dashboard
A mobile-first Node.js sidecar process providing a web-based mission control for monitoring and managing OpenClaw agents.
Featured*
