Prediction Market Oracle Research

If you're building a dashboard, agent, or decision tool that needs to pull probability signals from prediction markets like Polymarket or Manifold, this gives you a structured research workflow. It pushes you to log liquidity, spreads, resolution authority, and compare market odds against non-market sources before you wire anything up. The guardrails are solid: it won't give trading advice, it flags thin or stale markets, and it requires running a security check before giving any agent write access to on-chain markets. Honestly most useful as a checklist to keep you from treating a $47 market as gospel truth.

skills.sh installs: 5.3K
GitHub stars: 300.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/ecc --skill prediction-market-oracle-research --agent claude-code

Installs into .claude/skills of the current project.

Files

Prediction Market Oracle Research

Use this skill when prediction markets are being considered as a data source, forecasting input, oracle-like signal, or decision-intelligence layer.

Guardrails

Do not treat market prices as objective truth.
Do not provide investment advice or trading recommendations.
Separate venue mechanics, liquidity, incentives, and resolution rules from the implied signal.
Call out manipulation, thin liquidity, stale markets, and ambiguous outcomes.
For on-chain or execution-linked systems, run llm-trading-agent-security before granting any write authority.

Research Workflow

Define the decision the signal is meant to inform.
Find relevant markets, events, tags, and venues.
Record market-implied probabilities with timestamps and source links.
Evaluate signal quality:
- liquidity
- spread
- market age
- trader/incentive concentration if known
- resolution authority
- geography or account restrictions
Compare against non-market sources such as filings, news, polls, research, customer data, or internal KPIs.
Recommend whether the signal is usable, weak, or unsuitable for the stated decision.