Back to Details

trading-signals

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
<objective> Provide standardized technical analysis patterns for trading projects, combining Elliott Wave, Wyckoff, Fibonacci, Markov Regime, and Turtle Trading methodologies. Enables confluence detection through regime-weighted methodology fusion and cost-effective multi-LLM consensus. </objective>
<quick_start> Confluence analysis (methodologies agree = high-probability setup):
python
score = sum(signal.strength * weights[signal.method] for signal in signals)
action = 'BUY' if score >= 0.7 else 'WAIT'
Score interpretation:
  • 0.7-1.0: High conviction entry
  • 0.4-0.7: Wait for more confluence
  • 0.0-0.4: No trade
Cost-effective routing: DeepSeek-V3 for pattern detection → Claude Sonnet for critical decisions </quick_start>
<success_criteria> Analysis is successful when:
  • Multiple methodologies provide signals (not just one)
  • Regime identified (trending/ranging/volatile) before analysis
  • Confluence score calculated with regime-weighted methodology fusion
  • Cost-optimized: bulk processing on DeepSeek, critical decisions on Claude
  • Clear action (BUY/SELL/WAIT) with supporting rationale
  • NO OPENAI used in model routing </success_criteria>
<core_patterns> Standardized patterns for technical analysis across trading projects.
<objective> 为交易项目提供标准化技术分析模式，整合Elliott Wave、Wyckoff、Fibonacci、Markov Regime和Turtle Trading方法论。通过机制加权方法融合和高性价比的多LLM共识实现汇合检测。 </objective>
<quick_start> 汇合分析（多种方法论达成一致=高概率交易机会）：
python
score = sum(signal.strength * weights[signal.method] for signal in signals)
action = 'BUY' if score >= 0.7 else 'WAIT'
分数解读：
  • 0.7-1.0：高信心入场
  • 0.4-0.7：等待更多汇合信号
  • 0.0-0.4：不进行交易
高性价比路由：使用DeepSeek-V3进行模式检测 → 使用Claude Sonnet做关键决策 </quick_start>
<success_criteria> 满足以下条件时分析成功：
  • 多种方法论提供信号（而非单一方法）
  • 分析前已识别市场机制（趋势/盘整/波动）
  • 通过机制加权方法融合计算汇合分数
  • 成本优化：批量处理使用DeepSeek，关键决策使用Claude
  • 给出清晰的操作建议（BUY/SELL/WAIT）及支持理由
  • 模型路由中未使用OPENAI </success_criteria>
<core_patterns> 适用于各类交易项目的标准化技术分析模式。

Quick Reference

快速参考

MethodologyPurposeWhen to Use
Elliott WaveWave position + targetsTrend structure, cycle timing
Turtle TradingBreakout systemTrend following
FibonacciSupport/resistanceEntry/exit zones, golden pocket
WyckoffAccumulation/distributionInstitutional activity
Markov RegimeMarket state classificationPosition sizing, strategy selection
Pattern RecognitionCandlestick + chart patternsEntry confirmation
Swarm ConsensusMulti-LLM votingHigh-conviction decisions
方法论用途适用场景
Elliott Wave波浪定位 + 目标点位趋势结构、周期时机
Turtle Trading突破系统趋势跟踪
Fibonacci支撑/阻力位入场/离场区间、黄金口袋
Wyckoff积累/派发阶段机构行为分析
Markov Regime市场状态分类仓位管理、策略选择
Pattern RecognitionK线 + 图表形态入场确认
Swarm Consensus多LLM投票高信心决策

Confluence Detection

汇合检测

When methodologies agree = high-probability setup.
python
class ConfluenceAnalyzer:
    """Regime-weighted methodology fusion"""

    REGIME_WEIGHTS = {
        'trending_up':   {'elliott': 0.30, 'turtle': 0.30, 'fib': 0.20, 'wyckoff': 0.15},
        'trending_down': {'elliott': 0.30, 'turtle': 0.30, 'fib': 0.20, 'wyckoff': 0.15},
        'ranging':       {'fib': 0.35, 'wyckoff': 0.30, 'elliott': 0.20, 'turtle': 0.05},
        'volatile':      {'fib': 0.30, 'wyckoff': 0.30, 'elliott': 0.20, 'turtle': 0.10},
    }

    def analyze(self, df, regime: str) -> dict:
        weights = self.REGIME_WEIGHTS[regime]
        signals = self._collect_signals(df)

        score = sum(s.strength * weights[s.method] for s in signals)
        return {
            'score': score,  # 0-1.0
            'action': 'BUY' if score >= 0.7 else 'WAIT',
            'confluence': self._calc_agreement(signals)
        }
Score Interpretation:
  • 0.7-1.0: High conviction entry
  • 0.4-0.7: Wait for more confluence
  • 0.0-0.4: No trade
当多种方法论达成一致时，即为高概率交易机会。
python
class ConfluenceAnalyzer:
    """Regime-weighted methodology fusion"""

    REGIME_WEIGHTS = {
        'trending_up':   {'elliott': 0.30, 'turtle': 0.30, 'fib': 0.20, 'wyckoff': 0.15},
        'trending_down': {'elliott': 0.30, 'turtle': 0.30, 'fib': 0.20, 'wyckoff': 0.15},
        'ranging':       {'fib': 0.35, 'wyckoff': 0.30, 'elliott': 0.20, 'turtle': 0.05},
        'volatile':      {'fib': 0.30, 'wyckoff': 0.30, 'elliott': 0.20, 'turtle': 0.10},
    }

    def analyze(self, df, regime: str) -> dict:
        weights = self.REGIME_WEIGHTS[regime]
        signals = self._collect_signals(df)

        score = sum(s.strength * weights[s.method] for s in signals)
        return {
            'score': score,  # 0-1.0
            'action': 'BUY' if score >= 0.7 else 'WAIT',
            'confluence': self._calc_agreement(signals)
        }
分数解读：
  • 0.7-1.0：高信心入场
  • 0.4-0.7：等待更多汇合信号
  • 0.0-0.4：不进行交易

File Structure

文件结构

trading-project/
├── methodologies/
│   ├── elliott_wave.py     # Wave detection + halving cycle
│   ├── turtle_system.py    # Donchian breakouts
│   ├── fibonacci.py        # Levels + golden pocket
│   ├── wyckoff.py          # Phase detection + VSA
│   └── markov_regime.py    # State classification
├── patterns/
│   ├── candlestick.py      # Engulfing, hammer, doji
│   └── chart_patterns.py   # H&S, double bottom, triangles
├── aggregator.py           # Regime-weighted fusion
└── swarm/
    ├── consensus.py        # Multi-LLM voting
    └── adapters/           # Claude, DeepSeek, Gemini
trading-project/
├── methodologies/
│   ├── elliott_wave.py     # Wave detection + halving cycle
│   ├── turtle_system.py    # Donchian breakouts
│   ├── fibonacci.py        # Levels + golden pocket
│   ├── wyckoff.py          # Phase detection + VSA
│   └── markov_regime.py    # State classification
├── patterns/
│   ├── candlestick.py      # Engulfing, hammer, doji
│   └── chart_patterns.py   # H&S, double bottom, triangles
├── aggregator.py           # Regime-weighted fusion
└── swarm/
    ├── consensus.py        # Multi-LLM voting
    └── adapters/           # Claude, DeepSeek, Gemini

Cost-Effective Model Routing

高性价比模型路由

TaskModelCost
Pattern detectionDeepSeek-V3$0.27/1M
Confluence scoringQwen-72B$0.40/1M
Critical decisionsClaude Sonnet$3.00/1M
Swarm consensusMixed tier~$1.50/1M avg
任务模型成本
模式检测DeepSeek-V3$0.27/1M
汇合评分Qwen-72B$0.40/1M
关键决策Claude Sonnet$3.00/1M
群体共识混合层级~$1.50/1M 平均

Integration Notes

集成说明

  • Data Sources: yfinance, CCXT, Alpaca API
  • Pairs with: runpod-deployment-skill (model serving)
  • Projects: ThetaRoom, swaggy-stacks, alpha-lens
  • 数据来源： yfinance, CCXT, Alpaca API
  • 搭配技能： runpod-deployment-skill（模型部署）
  • 关联项目： ThetaRoom, swaggy-stacks, alpha-lens

Reference Files

参考文件

Core Methodologies:
  • reference/elliott-wave.md
    - Wave rules, halving supercycle, targets
  • reference/turtle-trading.md
    - Donchian channels, ATR sizing, pyramiding
  • reference/fibonacci.md
    - Levels, golden pocket, on-chain enhanced
  • reference/wyckoff.md
    - Phase state machines, VSA, composite operator
  • reference/markov-regime.md
    - 7-state model, transition probabilities
Advanced Patterns:
  • reference/pattern-recognition.md
    - Candlestick + chart patterns
  • reference/swarm-consensus.md
    - Multi-LLM voting system
  • reference/chinese-llm-stack.md
    - Cost-optimized Chinese LLMs for trading
核心方法论：
  • reference/elliott-wave.md
    - 波浪规则、减半超级周期、目标点位
  • reference/turtle-trading.md
    - 唐奇安通道、ATR仓位管理、金字塔加仓
  • reference/fibonacci.md
    - 水平位、黄金口袋、链上数据增强
  • reference/wyckoff.md
    - 阶段状态机、VSA、复合操作者
  • reference/markov-regime.md
    - 7状态模型、转换概率
进阶模式：
  • reference/pattern-recognition.md
    - K线 + 图表形态
  • reference/swarm-consensus.md
    - 多LLM投票系统
  • reference/chinese-llm-stack.md
    - 适用于交易场景的高性价比中文LLM栈