quantwise 1.2.0 → 1.2.2

package/.claude/skills/theme-detector/scripts/themes.yaml

@@ -0,0 +1,168 @@
+# Theme Detector configuration
+# Cross-sector theme definitions with proxy ETFs and representative stocks.
+# Migrated from DEFAULT_THEMES_CONFIG + ETF_CATALOG inline constants.
+
+cross_sector_min_matches: 2
+vertical_min_industries: 3
+
+cross_sector:
+  - theme_name: "AI & Semiconductors"
+    matching_keywords:
+      - Semiconductors
+      - Semiconductor Equipment & Materials
+      - Software - Application
+      - Software - Infrastructure
+      - Information Technology Services
+      - Computer Hardware
+      - Electronic Components
+    proxy_etfs: [SMH, SOXX, AIQ, BOTZ]
+    static_stocks: [NVDA, AVGO, AMD, INTC, QCOM, MRVL, AMAT, LRCX, KLAC, TSM]
+    etf_count: 8
+
+  - theme_name: "Clean Energy & EV"
+    matching_keywords:
+      - Solar
+      - Utilities - Renewable
+      - Auto Manufacturers
+      - Electrical Equipment & Parts
+      - Specialty Chemicals
+    proxy_etfs: [ICLN, QCLN, TAN, LIT]
+    static_stocks: [ENPH, SEDG, FSLR, RUN, TSLA, RIVN, ALB, PLUG, BE, NEE]
+    etf_count: 7
+
+  - theme_name: "Cybersecurity"
+    matching_keywords:
+      - Software - Infrastructure
+      - Software - Application
+      - Information Technology Services
+    proxy_etfs: [CIBR, HACK, BUG]
+    static_stocks: [CRWD, PANW, FTNT, ZS, S, OKTA, NET, CYBR, QLYS, RPD]
+    etf_count: 4
+
+  - theme_name: "Cloud Computing & SaaS"
+    matching_keywords:
+      - Software - Application
+      - Software - Infrastructure
+      - Information Technology Services
+    proxy_etfs: [SKYY, WCLD, CLOU]
+    static_stocks: [CRM, NOW, SNOW, DDOG, MDB, NET, ZS, HUBS, WDAY, TEAM]
+    etf_count: 4
+
+  - theme_name: "Biotech & Genomics"
+    matching_keywords:
+      - Biotechnology
+      - Drug Manufacturers - General
+      - Drug Manufacturers - Specialty & Generic
+      - Diagnostics & Research
+    proxy_etfs: [XBI, IBB, ARKG]
+    static_stocks: [AMGN, GILD, VRTX, REGN, MRNA, BIIB, ILMN, SGEN, ALNY, BMRN]
+    etf_count: 5
+
+  - theme_name: "Infrastructure & Construction"
+    matching_keywords:
+      - Engineering & Construction
+      - Building Products & Equipment
+      - Building Materials
+      - Specialty Industrial Machinery
+      - Farm & Heavy Construction Machinery
+      - Infrastructure Operations
+    proxy_etfs: [PAVE, IFRA]
+    static_stocks: [CAT, DE, VMC, MLM, URI, PWR, EME, J, ACM, FAST]
+    etf_count: 3
+
+  - theme_name: "Gold & Precious Metals"
+    matching_keywords:
+      - Gold
+      - Silver
+      - Other Precious Metals & Mining
+    proxy_etfs: [GDX, GDXJ, SLV, GLD]
+    static_stocks: [NEM, GOLD, AEM, FNV, WPM, RGLD, KGC, AGI, HL, PAAS]
+    etf_count: 4
+
+  - theme_name: "Oil & Gas (Energy)"
+    matching_keywords:
+      - Oil & Gas E&P
+      - Oil & Gas Equipment & Services
+      - Oil & Gas Integrated
+      - Oil & Gas Midstream
+      - Oil & Gas Refining & Marketing
+      - Oil & Gas Drilling
+    proxy_etfs: [XLE, XOP, OIH]
+    static_stocks: [XOM, CVX, COP, EOG, SLB, PXD, MPC, PSX, OXY, DVN]
+    etf_count: 5
+
+  - theme_name: "Financial Services & Banks"
+    matching_keywords:
+      - Banks - Diversified
+      - Banks - Regional
+      - Capital Markets
+      - Insurance - Diversified
+      - Financial Data & Stock Exchanges
+      - Asset Management
+    proxy_etfs: [XLF, KBE, KRE]
+    static_stocks: [JPM, BAC, GS, MS, WFC, C, BLK, SCHW, ICE, CME]
+    etf_count: 5
+
+  - theme_name: "Healthcare & Pharma"
+    matching_keywords:
+      - Drug Manufacturers - General
+      - Medical Devices
+      - Medical Instruments & Supplies
+      - Healthcare Plans
+      - Medical Care Facilities
+    proxy_etfs: [XLV, IHI, XBI]
+    static_stocks: [UNH, JNJ, LLY, PFE, ABT, TMO, DHR, SYK, ISRG, MDT]
+    etf_count: 5
+
+  - theme_name: "Defense & Aerospace"
+    matching_keywords:
+      - Aerospace & Defense
+      - Communication Equipment
+      - Scientific & Technical Instruments
+    proxy_etfs: [ITA, PPA, XAR]
+    static_stocks: [LMT, RTX, NOC, GD, BA, LHX, HII, TDG, HWM, AXON]
+    etf_count: 5
+
+  - theme_name: "Real Estate & REITs"
+    matching_keywords:
+      - REIT - Diversified
+      - REIT - Industrial
+      - REIT - Residential
+      - REIT - Retail
+      - REIT - Specialty
+      - REIT - Office
+      - Real Estate - Development
+      - Real Estate Services
+    proxy_etfs: [VNQ, IYR, XLRE]
+    static_stocks: [PLD, AMT, EQIX, CCI, SPG, O, WELL, DLR, PSA, AVB]
+    etf_count: 4
+
+  - theme_name: "Retail & Consumer"
+    matching_keywords:
+      - Internet Retail
+      - Specialty Retail
+      - Apparel Retail
+      - Discount Stores
+      - Home Improvement Retail
+      - Department Stores
+    proxy_etfs: [XRT, XLY]
+    static_stocks: [AMZN, HD, LOW, TJX, COST, WMT, TGT, ROST, BURL, LULU]
+    etf_count: 3
+
+  - theme_name: "Crypto & Blockchain"
+    matching_keywords:
+      - Capital Markets
+      - Software - Infrastructure
+      - Financial Data & Stock Exchanges
+    proxy_etfs: [BITO, BLOK, BITQ]
+    static_stocks: [COIN, MSTR, MARA, RIOT, CLSK, HUT, BITF, HIVE, SQ, PYPL]
+    etf_count: 4
+
+  - theme_name: "Nuclear & Uranium"
+    matching_keywords:
+      - Uranium
+      - Utilities - Independent Power Producers
+      - Utilities - Regulated Electric
+    proxy_etfs: [URA, URNM, NLR]
+    static_stocks: [CCJ, UEC, NXE, DNN, LEU, SMR, UUUU, URG, OKLO, VST]
+    etf_count: 3

package/.claude/skills/theme-detector/scripts/uptrend_client.py

@@ -0,0 +1,241 @@
+#!/usr/bin/env python3
+"""
+Theme Detector - Uptrend Ratio Client
+
+Fetches sector uptrend ratio data from Monty's Uptrend Ratio Dashboard
+(GitHub CSV). No API key required.
+
+Data Source: https://github.com/tradermonty/uptrend-dashboard
+"""
+
+import csv
+import io
+import sys
+from datetime import datetime, timedelta
+from typing import Dict, List, Optional
+
+try:
+    import requests
+    HAS_REQUESTS = True
+except ImportError:
+    HAS_REQUESTS = False
+
+
+TIMESERIES_URL = (
+    "https://raw.githubusercontent.com/tradermonty/uptrend-dashboard/"
+    "main/data/uptrend_ratio_timeseries.csv"
+)
+SECTOR_SUMMARY_URL = (
+    "https://raw.githubusercontent.com/tradermonty/uptrend-dashboard/"
+    "main/data/sector_summary.csv"
+)
+
+# Map FINVIZ sector names to uptrend worksheet names
+FINVIZ_TO_WORKSHEET = {
+    "Technology": "sec_technology",
+    "Healthcare": "sec_healthcare",
+    "Financial": "sec_financial",
+    "Consumer Cyclical": "sec_consumercyclical",
+    "Consumer Defensive": "sec_consumerdefensive",
+    "Industrials": "sec_industrials",
+    "Energy": "sec_energy",
+    "Basic Materials": "sec_basicmaterials",
+    "Communication Services": "sec_communicationservices",
+    "Real Estate": "sec_realestate",
+    "Utilities": "sec_utilities",
+}
+
+# Reverse mapping for display
+WORKSHEET_TO_DISPLAY = {v: k for k, v in FINVIZ_TO_WORKSHEET.items()}
+
+
+def _safe_float(value) -> Optional[float]:
+    """Convert to float, return None if empty or invalid."""
+    if value is None or str(value).strip() == "":
+        return None
+    try:
+        return float(value)
+    except (ValueError, TypeError):
+        return None
+
+
+def _calculate_slope(values: List[float]) -> Optional[float]:
+    """Calculate slope from a list of values using simple linear regression.
+
+    Uses least-squares fit: slope = sum((x-xbar)(y-ybar)) / sum((x-xbar)^2)
+
+    Args:
+        values: List of float values (at least 2 required)
+
+    Returns:
+        Slope value or None if insufficient data
+    """
+    if not values or len(values) < 2:
+        return None
+
+    n = len(values)
+    x_mean = (n - 1) / 2.0
+    y_mean = sum(values) / n
+
+    numerator = sum((i - x_mean) * (v - y_mean) for i, v in enumerate(values))
+    denominator = sum((i - x_mean) ** 2 for i in range(n))
+
+    if denominator == 0:
+        return 0.0
+
+    return round(numerator / denominator, 6)
+
+
+def is_data_stale(latest_date_str: str, threshold_bdays: int = 2) -> bool:
+    """Check if the latest data is older than threshold business days.
+
+    Counts only Mon-Fri as business days, so Friday data is not considered
+    stale when checked on Saturday or Sunday.
+
+    Args:
+        latest_date_str: Date string in YYYY-MM-DD format
+        threshold_bdays: Maximum acceptable age in business days (default 2)
+
+    Returns:
+        True if data is stale (older than threshold)
+    """
+    try:
+        latest = datetime.strptime(latest_date_str, "%Y-%m-%d")
+        now = datetime.now()
+        # Compare at date level to avoid intraday time issues
+        now_midnight = now.replace(hour=0, minute=0, second=0, microsecond=0)
+        bdays = 0
+        current = latest
+        while current < now_midnight:
+            current += timedelta(days=1)
+            if current.weekday() < 5:  # Mon-Fri
+                bdays += 1
+        return bdays > threshold_bdays
+    except (ValueError, TypeError):
+        return True
+
+
+def fetch_sector_uptrend_data() -> Dict[str, Dict]:
+    """Fetch sector uptrend ratio data from timeseries CSV.
+
+    Downloads the full timeseries, extracts the latest row per sector,
+    and calculates slope from the last 5 data points.
+
+    Returns:
+        Dict mapping display sector name to:
+        {
+            "ratio": float,       # Current uptrend ratio (0.0-1.0)
+            "ma_10": float,       # 10-period moving average
+            "slope": float,       # Slope from last 5 data points
+            "trend": str,         # "up" or "down"
+            "latest_date": str,   # YYYY-MM-DD
+        }
+        Empty dict on failure.
+    """
+    if not HAS_REQUESTS:
+        print("WARNING: requests library not installed.", file=sys.stderr)
+        return {}
+
+    try:
+        response = requests.get(TIMESERIES_URL, timeout=30)
+        response.raise_for_status()
+    except Exception as e:
+        print(f"WARNING: Failed to fetch uptrend timeseries: {e}",
+              file=sys.stderr)
+        return {}
+
+    # Parse all rows, grouped by worksheet
+    sector_rows: Dict[str, List[Dict]] = {}
+    reader = csv.DictReader(io.StringIO(response.text))
+    for row in reader:
+        ws = row.get("worksheet", "").strip()
+        if ws == "all" or not ws.startswith("sec_"):
+            continue
+        date_str = row.get("date", "").strip()
+        ratio = _safe_float(row.get("ratio"))
+        ma_10 = _safe_float(row.get("ma_10"))
+        slope_csv = _safe_float(row.get("slope"))
+        trend = row.get("trend", "").strip()
+
+        if not date_str or ratio is None:
+            continue
+
+        if ws not in sector_rows:
+            sector_rows[ws] = []
+        sector_rows[ws].append({
+            "date": date_str,
+            "ratio": ratio,
+            "ma_10": ma_10,
+            "slope_csv": slope_csv,
+            "trend": trend,
+        })
+
+    # For each sector: sort by date, get latest, calculate slope from last 5
+    result = {}
+    for ws_name, rows in sector_rows.items():
+        rows.sort(key=lambda r: r["date"])
+        latest = rows[-1]
+        display_name = WORKSHEET_TO_DISPLAY.get(ws_name, ws_name)
+
+        # Calculate slope from last 5 ratio values
+        last_n = rows[-5:] if len(rows) >= 5 else rows
+        ratio_values = [r["ratio"] for r in last_n if r["ratio"] is not None]
+        calculated_slope = _calculate_slope(ratio_values)
+
+        # Prefer CSV slope if available, otherwise use calculated
+        slope = latest["slope_csv"] if latest["slope_csv"] is not None else calculated_slope
+
+        result[display_name] = {
+            "ratio": latest["ratio"],
+            "ma_10": latest["ma_10"],
+            "slope": slope,
+            "trend": latest["trend"] or ("up" if slope and slope > 0 else "down"),
+            "latest_date": latest["date"],
+        }
+
+    return result
+
+
+def build_summary_from_timeseries(sector_timeseries: Dict[str, Dict]) -> List[Dict]:
+    """Build a sector summary list from timeseries data.
+
+    Fallback when sector_summary.csv is unavailable.
+
+    Args:
+        sector_timeseries: Dict from fetch_sector_uptrend_data()
+
+    Returns:
+        List of dicts with: Sector, Ratio, 10MA, Trend, Slope, Status
+    """
+    OVERBOUGHT = 0.37
+    OVERSOLD = 0.097
+
+    rows = []
+    for sector_name, data in sector_timeseries.items():
+        ratio = data.get("ratio")
+        status = ("Overbought" if ratio is not None and ratio > OVERBOUGHT else
+                  "Oversold" if ratio is not None and ratio < OVERSOLD else
+                  "Normal")
+        rows.append({
+            "Sector": sector_name,
+            "Ratio": ratio,
+            "10MA": data.get("ma_10"),
+            "Trend": (data.get("trend") or "").capitalize(),
+            "Slope": data.get("slope"),
+            "Status": status,
+        })
+    return rows
+
+
+def get_sector_uptrend_3point(sector_name: str,
+                               all_data: Dict[str, Dict]) -> Optional[Dict]:
+    """Get ratio + ma_10 + slope for a specific sector.
+
+    Args:
+        sector_name: Display name (e.g., "Technology")
+        all_data: Output from fetch_sector_uptrend_data()
+
+    Returns:
+        Dict with ratio, ma_10, slope, trend, latest_date. None if not found.
+    """
+    return all_data.get(sector_name)

package/.claude/skills/uptrend-analyzer/SKILL.md

@@ -0,0 +1,108 @@
+---
+name: uptrend-analyzer
+description: 使用Monty的上升趋势比率仪表盘数据分析市场广度，诊断当前市场环境。从5个维度（广度、板块参与度、轮动、动量、历史背景）生成0-100的综合评分。当询问市场广度、上升趋势比率，或市场环境是否支持股票仓位时使用。无需API密钥。
+---
+
+# 上升趋势分析器技能
+
+## 目的
+
+使用Monty的上升趋势比率仪表盘诊断市场广度健康状况，该仪表盘跟踪约2,800只美股和11个板块。生成0-100的综合评分（越高越健康），并提供仓位建议。
+
+与Market Top Detector（基于API的风险评分器）不同，本技能使用免费的CSV数据评估"参与广度"——即市场的上涨是广泛的还是狭窄的。
+
+## 何时使用本技能
+
+**英文：**
+- User asks "Is the market breadth healthy?" or "How broad is the rally?"
+- User wants to assess uptrend ratios across sectors
+- User asks about market participation or breadth conditions
+- User needs exposure guidance based on breadth analysis
+- User references Monty's Uptrend Dashboard or uptrend ratios
+
+**中文：**
+- "市场广度健康吗？""上涨范围广泛吗？"
+- 想要查看各板块的上升趋势比率
+- 想要诊断市场参与率和广度状况
+- 需要基于广度分析的仓位指导建议
+- 关于Monty的上升趋势仪表盘的问题
+
+## 与Market Top Detector的区别
+
+| 方面 | Uptrend Analyzer | Market Top Detector |
+|------|-----------------|-------------------|
+| 评分方向 | 越高越健康 | 越高越危险 |
+| 数据来源 | 免费GitHub CSV | FMP API（付费） |
+| 关注点 | 广度参与度 | 顶部形成风险 |
+| API密钥 | 不需要 | 需要（FMP） |
+| 方法论 | Monty上升趋势比率 | O'Neil/Minervini/Monty |
+
+---
+
+## 执行工作流
+
+### 第一阶段：执行Python脚本
+
+运行分析脚本（无需API密钥）：
+
+```bash
+python3 skills/uptrend-analyzer/scripts/uptrend_analyzer.py
+```
+
+脚本将执行以下操作：
+1. 从Monty的GitHub仓库下载CSV数据
+2. 计算5个维度的评分
+3. 生成综合评分和报告
+
+### 第二阶段：展示结果
+
+向用户展示生成的Markdown报告，重点说明：
+- 综合评分和区域分类
+- 仓位建议（满仓/正常/减仓/防御/保存资本）
+- 板块热力图，显示最强和最弱的板块
+- 关键动量和轮动信号
+
+---
+
+## 5维度评分系统
+
+| # | 维度 | 权重 | 关键信号 |
+|---|------|------|----------|
+| 1 | 市场广度（整体） | **30%** | 比率水平 + 趋势方向 |
+| 2 | 板块参与度 | **25%** | 处于上升趋势的板块数量 + 比率离散度 |
+| 3 | 板块轮动 | **15%** | 周期性 vs 防御性板块平衡 |
+| 4 | 动量 | **20%** | 斜率方向 + 加速度 |
+| 5 | 历史背景 | **10%** | 在历史中的百分位排名 |
+
+## 评分区域
+
+| 评分 | 区域 | 仓位建议 |
+|------|------|----------|
+| 80-100 | 强牛市 | 满仓（100%） |
+| 60-79 | 牛市 | 正常仓位（80-100%） |
+| 40-59 | 中性 | 减仓（60-80%） |
+| 20-39 | 谨慎 | 防御性（30-60%） |
+| 0-19 | 熊市 | 保存资本（0-30%） |
+
+---
+
+## API要求
+
+**必需：** 无（使用免费的GitHub CSV数据）
+
+## 输出文件
+
+- JSON: `uptrend_analysis_YYYY-MM-DD_HHMMSS.json`
+- Markdown: `uptrend_analysis_YYYY-MM-DD_HHMMSS.md`
+
+## 参考文档
+
+### `references/uptrend_methodology.md`
+- 上升趋势比率的定义和阈值
+- 5维度评分方法论
+- 板块分类（周期性/防御性/大宗商品）
+- 历史校准说明
+
+### 何时加载参考文档
+- **首次使用：** 加载 `uptrend_methodology.md` 以全面理解框架
+- **常规执行：** 无需参考文档——脚本会处理评分