Dr. Manhattan - Prediction Market Trading

Trust Score 71/100

Unified CCXT-style API and tools for discovering, analyzing, and trading prediction markets across Polymarket, Kalshi, Opinion, Limitless, and Predict.fun; incl

triggers:search marketsfetch orderbookcreate ordermarket-makingfetch balancecalculate nav

GitHub SKILL.md

What it does

Provides a unified library and MCP-compatible tools to browse, search, and trade prediction markets across multiple exchanges. Offers market discovery, orderbook access, trading primitives, account/position management, and market-making strategy orchestration.

When to use it

Use when you need programmatic access to prediction markets for research, trading, arbitrage, or automated strategies. Triggers include searching markets, fetching orderbooks, placing or cancelling orders, running market-making strategies, or calculating portfolio NAV.

What's included

Scripts: No — primarily a Python library with examples and MCP server integration examples.
References: No explicit references listed in SKILL.md, but the repo contains examples and MCP configuration snippets.
Instructions: Installation and usage examples for library and MCP server; detailed tools reference for market discovery, orderbook, trading, account, and strategy workflows.

Compatible agents

Best suited for code-capable agents and MCP server integrations (Claude Code, Copilot-style agents) that can run Python-based MCP servers or use the library directly.

Audit Summary

Dr. Manhattan provides a unified CCXT-style API for trading prediction markets across Polymarket, Kalshi, Opinion, Limitless, and Predict.fun. The SKILL.md is thorough with clear workflows, code examples, and data model docs. The scripts/ directory only contains a README.md (no executable scripts), so script execution was skipped. The skill directs agents to make real financial transactions on prediction markets, which carries inherent risk. No security red flags found — credentials are loaded from .env, no hardcoded secrets, no destructive commands.

Watch Out

Involves real financial transactions — agent can trade real money if exchange credentials are configured
Requires Python >= 3.11 and uv package manager
No actual executable scripts bundled — scripts/ only has a README.md

Notes

Skill is primarily documentation for an external Python library (dr_manhattan pip package). No bundled executable scripts. Financial risk is inherent to the domain but not a security vulnerability. Network calls to exchange APIs are expected functionality, not suspicious.

Information

Repository: dr-manhattan
Stars: 184

Trust Score

Overall71

Security75

Code Quality72

Architecture58

Usefulness55

Related Skills

Extract Circuit Netlist Edge Features

Extract structured edge features from a bipartite circuit netlist (NetworkX MultiGraph), normalizing device/net ordering, mapping terminal colors, and detecting

Pine Script Generator (TradingView)

Convert Python backtest strategies into TradingView Pine Script v6 or generate Pine Script from natural-language strategy descriptions.

Markdrop

Convert PDFs to structured Markdown or interactive HTML and generate AI-powered descriptions for images and tables using multiple LLM providers.

FastAPI Project Templates

Creates production-ready FastAPI project scaffolds with async patterns, DI, middleware, and testing best practices for high-performance APIs.

Unitree Robot Controller

Control and command Unitree robots (GO1/GO2/G1/H1) via OpenClaw: initialization, basic motion commands, and sensor integrations.

Alpha Forge Pre-Ship Quality Gates

Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.

Integrated Finance (Membrane) Connector

Interact with Integrated Finance via the Membrane CLI to manage accounts, transactions, budgets, and reports; handles auth and proxy requests.

Plotly (Interactive Python Visualizations)

Interactive Python visualization skill for building hoverable, zoomable, and embeddable charts (Plotly Express + Graph Objects) for EDA, dashboards, and present

Back to Skills