Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →

0xhubed/agent-trading-arena

4 skills3.6k installs24 starsGitHub

Install

npx skills add https://github.com/0xhubed/agent-trading-arena

Skills in this repo

1Risk ManagementLast updated 2026 03 09 20 08 UTC Active patterns 54 Total samples 8500 Confidence threshold 60 These rules are derived from analyzing profitable vs losing trades Rule Success Rate Samples Confidence Seen Trade frequency inversely correlates wit 95 473 50 1x When ALL 5 tracked assets are positive o 95 58 45 1x Position sizing at 2 equity risk with 2 92 183 90 1x Position sizing at 2 equity risk with 2 92 200 95 1x Cap trade frequency at 10 trades 24h max 90 84 45 1x Closing LONG positions quickly to pivot 88 50 95 1x Trade frequency must be inversely propor 88 109 45 1x Multi timeframe bearish alignment 15m 88 383 99 2x In uniformly bearish markets low sever 85 49 85 1x Validation checks passing validation p 85 200 95 1x High trade frequency 189 200 trades 24h 85 389 95 1x When ALL 5 tracked assets are positive o 85 113 95 1x Position sizing at 2 equity risk with 2 801.9kinstalls2Trading Wisdomtrading-wisdom comes from the 0xhubed agent-trading-arena repository and surfaces winning and losing strategy patterns discovered by competing trading agents. Pattern records include pattern_id, pattern_type, descriptive rules, agent conditions, success_rate, sample_size, and confirmation timestamps in JSON form. Example entries document strategies such as minimal trading frequency with passive index allocation in sideways markets, annotated with an 0.85 success_rate over a sample_size of 15 observations. Developers reach for trading-wisdom when wiring autonomous trading agents and want to import swarm-validated heuristics instead of hand-authored guesses.775installs3Market Regimesmarket-regimes is a skill from 0xhubed/agent-trading-arena that maps detected market conditions to regime-specific trading strategies stored as pattern records. Regime types include sideways_flat, low_volatility_mixed, and related conditions, each linked to strategy guidance such as reducing trade frequency in flat markets or avoiding leveraged positions in low-volatility mixed regimes. Developers invoke market-regimes when building or operating autonomous trading agents that must adapt position sizing and activity level without manual regime labeling. The skill reads pattern_id entries with regime conditions and strategy descriptions so agents shift between aggressive, passive, or flat postures automatically.621installs4Entry Signalsentry-signals is a skill from agent-trading-arena for defining and tuning entry signal rules that drive autonomous trading agent decisions. It covers buy and sell triggers built from technical indicators, threshold levels, and confirmation conditions used in simulated or live trading competitions. Developers reach for entry-signals when configuring when an agent should enter positions, refining signal sensitivity, or aligning indicator logic with arena constraints rather than building unrelated portfolio or risk-management modules.341installs

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.