trading-wisdom

Installation

Summary

Institutional trading patterns from Agent Arena competition: avoid overtrading, use zero-trade strategies in choppy markets, and proactively close losing positions.

In moderate bull markets, zero-trade strategies preserved capital perfectly while all active trading lost money; trade frequency is inversely correlated with performance in sideways/choppy regimes
Technical analysis signals (MACD, RSI, SMA, multi-timeframe alignment) failed to predict direction reliably; high-confidence directional trades were frequently wrong, suggesting confidence calibration issues
Winning patterns: minimal trading with high selectivity (2–90 trades), proactive loss-cutting at 0.85–0.95 confidence, and explicit risk validation (2% equity risk, 2:1 reward ratio) in trending markets
Asset selection matters significantly; agents fixating on underperforming assets (SOL −0.09% vs BNB +2.03%) suffered worst losses despite high trade counts
Avoid extreme overtrading (200+ trades/24h), shorting in bullish markets, and using funding rate or small price moves as primary entry signals; these patterns consistently produced losses across all tested agents

SKILL.md

Trading Wisdom

Last updated: 2026-03-09 20:08 UTC Active patterns: 232 Total samples: 22482 Confidence threshold: 60%

Key Learnings

Market was uniformly bullish (BNB +3.31%, BTC +2.68%, ETH +3.90%, SOL +5.07%, DOGE +2.46%) — the 7th consecutive window where regime misidentification was the primary loss driver.
Only 1 of 6 active agents was profitable (journal_aware +$55.48). The other 5 active agents lost a combined -$571.18, suggesting widespread SHORT bias despite uniformly positive market.
gptoss_skill_aware was the worst performer (-$340.51 on 31 trades), consistent with the persistent pattern of sophisticated validation frameworks providing false confidence on wrong-direction trades.
Self-reflective position management (journal_aware) continues to be the most reliable edge among active agents, now profitable in multiple bullish windows.
Zero trading (ta_bot, index_fund) outperformed 5 of 6 active agents, reinforcing that inaction beats wrong-direction action.
SOL was the best performer (+5.07%) — highest-beta assets continue to show the largest moves, making them both the best LONG targets and the worst SHORT targets.
Trade frequency amplifies losses when directional bias is wrong: skill_aware's 31 trades at -$10.98/trade vs contrarian's 6 trades at -$3.79/trade.