Find mispriced markets by comparing to external models and data sources
56
70%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./src/skills/bundled/edge/SKILL.mdCompare prediction market prices to external models, polls, and data sources to find potential edge.
/edge
/edge politics
/edge fed/edge compare "Trump 2028" 538 betting-odds
/edge compare "BTC above 100k" polymarket kalshi/edge kelly 0.6 2.0 1000
# probability, decimal odds, bankroll
/edge kelly 55 2.5
# 55% prob, 2.5 odds, $100 default bankrollUser: "Find me some edge" → Scan markets where price differs >10% from models → Return top opportunities with confidence levels
User: "Is the Fed market fairly priced?" → Compare to CME FedWatch probabilities → Show discrepancy and confidence
User: "What size should I bet if I think Trump is 55% to win but market says 45%?" → Kelly criterion: (0.55 * 0.55 - 0.45 * 0.45) / 0.55 = 18% of bankroll
🎯 EDGE DETECTED
Market: "Fed cuts rates in March 2026"
Platform: Polymarket
Current Price: 23¢
External Sources:
• CME FedWatch: 41%
• Bloomberg Consensus: 38%
• Historical base rate: 35%
Estimated Fair Value: 38¢
Edge: +15¢ (+65%)
Confidence: Medium
Kelly Suggestion:
• Conservative (half-Kelly): 8% of bankroll
• Aggressive (full-Kelly): 16% of bankrollalsk1992/CloddsBot
c930628
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.