ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

polymarket-valuation-divergence

Trade Polymarket markets based on valuation divergence. When your probability model differs from Polymarket's price by >threshold, enter using Kelly sizing. Works with any probability model (Simmer AI consensus, user model, external API).

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/adlai88/polymarket-valuation-divergence
Or

Polymarket Valuation Divergence Trader

Trade markets where model probability diverges from Polymarket price.

This is a template. The default uses Simmer AI consensus as your probability model. Remix it with your own model, external APIs, or custom forecasting logic. The skill handles market scanning, Kelly sizing, and safe trade execution.

When to Use This Skill

Use this when:

  • You have a probability model (AI, statistical, fundamental analysis)
  • You want to trade when market prices diverge from your model
  • You need Kelly criterion sizing for risk management
  • You want to catch structural mispricings (mergers, earnings, regulatory events)

Quick Start

Setup

  1. Set your API key:

    export SIMMER_API_KEY=sk_live_...
    
  2. Check config:

    python valuation_trader.py --config
    
  3. Dry run (no trades):

    python valuation_trader.py
    
  4. Live trading:

    python valuation_trader.py --live
    

Configuration

SettingEnv VarDefaultDescription
edge_thresholdSIMMER_VALUATION_EDGE0.015Min edge to trade (1.5%)
kelly_fractionSIMMER_VALUATION_KELLY0.25Kelly criterion fraction (cap at 25%)
max_position_usdSIMMER_VALUATION_MAX_POSITION5.00Max per trade
max_trades_per_runSIMMER_VALUATION_MAX_TRADES5Max trades per cycle
probability_sourceSIMMER_VALUATION_SOURCEsimmer_ai"simmer_ai" or "user_model"

Update settings:

python valuation_trader.py --set edge_threshold=0.02

How It Works

1. Scan Markets

Fetches active markets from Simmer. For each:

2. Get Model Probability

Default: Simmer AI consensus from /api/sdk/context/{market_id}

To use your own model: Edit get_model_probability() function.

3. Calculate Edge

edge = model_probability - market_price

If edge > threshold: trade signal āœ“

4. Kelly Sizing

kelly_fraction = edge / (1 - market_price)
kelly_fraction = min(kelly_fraction, MAX_KELLY)
position_size = kelly_fraction * bankroll
position_size = min(position_size, max_position_usd)

5. Execute Trade

  • If edge > 0: Buy YES (model thinks it's underpriced)
  • If edge < 0: Buy NO (model thinks it's overpriced)
  • Include reasoning for transparency
  • Execute with safeguards (flip-flop detection, slippage warnings)

6. Hold to Resolution

Positions held until market resolves. Check --positions to see current holdings.

Interpreting the Output

šŸŽÆ Valuation Trader Scan
   Markets scanned: 50
   Signals found: 3
   Executed: 2

šŸ“° BTC hits $100k by EOY?
   Model: 65% | Market: 52% | Edge: +13%
   šŸ’° BUY YES $4.50 (Kelly: 2.25 shares)

šŸ“° Will Trump win in 2028?
   Model: 58% | Market: 71% | Edge: -13%
   šŸ’° BUY NO $3.75 (Kelly: 2.05 shares)

Customizing Your Model

Edit get_model_probability() to use any source:

Metadata

Author@adlai88
Stars4473
Views1
Updated2026-05-01
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-adlai88-polymarket-valuation-divergence": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.