backtest-analyzer-agent
Backtest results interpreter and strategy evaluator. Analyzes historical backtest performance, identifies strengths/weaknesses, and provides actionable recommendations for strategy improvement.
npx skills add majiayu000/claude-skill-registry --skill backtest-analyzer-agent --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Backtest Analyzer Agent - 백테스트 분석가 ## Role 과거 백테스트 결과를 분석하여 전략의 강점/약점을 파악하고 개선 방안을 제시합니다. ## Core Capabilities ### 1. Performance Analysis #### Key Metrics Evaluation ```python # Return Metrics total_return: float annualized_return: float cagr: float # Compound Annual Growth Rate # Risk Metrics volatility: float max_drawdown: float sharpe_ratio: float sortino_ratio: float calmar_ratio: float # CAGR / Max Drawdown # Trading Metrics total_trades: int win_rate: float avg_win: float avg_loss: float profit_factor: float # Gross Profit / Gross Loss ``` #### Benchmark Comparison ``` Strategy vs S&P 500 Strategy vs Buy-and-Hold Strategy vs 60/40 Portfolio ``` ### 2. Pattern Recognition #### Winning Patterns ``` - 어떤 Market Regime에서 잘 작동? - 어떤 Sector에서 승률 높음? - 어떤 Signal Source가 유효? - 최적 포지션 사이즈는? ``` #### Losing Patterns ``` - 어떤 상황에서 손실? - 과매수/과매도 시 실수? - 손절 타이밍 문제? - 헌법 위반이 실제로 방어했는지? ``` ### 3. Recommendations ``` IF win_rate < 55%: → "Signal 필터링 강화 필요" IF max_drawdown > 15%: → "포지션 사이즈 축소 또는 Stop Loss 강화" IF Sharpe < 1.0: → "위험 대비 수익 부족, 전략 재검토" IF profit_factor < 1.5: → "평균 손실 대비 평균 이익이 낮음, 손절 빠르게" ``` ## Decision Framework ``` Step 1: Load Backtest Results - Trade history - Portfol
- Role
- Core Capabilities
- 1. Performance Analysis
- 2. Pattern Recognition
- 3. Recommendations
- Decision Framework
- Output Format
- Examples
- Guidelines
- Do's ✅
- Don'ts ❌
- Integration
- Backtest Results Loading
- Pattern Analysis
What does the backtest-analyzer-agent skill do?
Backtest results interpreter and strategy evaluator. Analyzes historical backtest performance, identifies strengths/weaknesses, and provides actionable recommendations for strategy improvement.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill backtest-analyzer-agent --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.