kymera-mr-optimizer
Skill3 starsChanged 12 months agoMITView on GitHub
Continuously optimizes mean-reversion strategy parameters based on real performance data. Identifies winning patterns and recommends parameter adjustments. Works with: - Strategy-to-portfolio integrator - Portfolio-to-strategy converter - Unified dashboard - Risk adjuster Aaron Storey | Kymera Strategy (Nov 2025)
In this repository11 other files it gives its agents.
- forecasting-agentSkill
- kymera-integratorSkill
- kymera-portfolio-checkerSkill
- kymera-risk-monitorSkill
- kymera-tax-optimizerSkill
- paper-reviewerSkill
- portfolio-analysis-agentSkill
- SKILL.mdSkill
- system-health-checkSkill
- trading-analysisSkill
- youtube-transcriberSkill
The file
Files
Kymera Mean-Reversion Optimizer
Continuously optimizes mean-reversion strategy parameters based on real performance data. Identifies winning patterns and recommends parameter adjustments.
Capabilities
- Performance Analysis: Analyze MR trade results and identify patterns
- Win Rate Optimization: Detect entry quality degradation
- Parameter Tuning: Recommend VWAP thresholds, stop-loss levels, profit targets
- Symbol Selection: Identify best-performing symbols
- Portfolio Alignment: Validate correlation with portfolio system
Use Cases
- Analyze MR Performance
/kymera-mr-optimizer analyze - Generate Optimization Report
/kymera-mr-optimizer report - Validate System Alignment
/kymera-mr-optimizer check-alignment
Key Parameters
- Win rate (target: ≥50%)
- Profit factor (target: ≥1.2)
- VWAP band threshold (1.5σ - 2.5σ)
- Stop-loss level (-2% to -4%)
- Profit targets (0.5% - 2%)
- Position sizing (Kelly-based)
Integration
Works with:
- Strategy-to-portfolio integrator
- Portfolio-to-strategy converter
- Unified dashboard
- Risk adjuster
Author
Aaron Storey | Kymera Strategy (Nov 2025)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.