quantwise 1.2.7 → 1.2.9

package/.claude/skills/canslim-screener/SKILL.md

@@ -3,16 +3,16 @@ name: canslim-screener
 description: Screen US stocks using William O'Neil's CANSLIM growth stock methodology. Use when user requests CANSLIM stock screening, growth stock analysis, momentum stock identification, or wants to find stocks with strong earnings and price momentum following O'Neil's investment system.
 ---
 
-# CANSLIM Stock Screener - Phase 2
+# CANSLIM Stock Screener - Phase 3 (Full CANSLIM)
 
 ## Overview
 
 This skill screens US stocks using William O'Neil's proven CANSLIM methodology, a systematic approach for identifying growth stocks with strong fundamentals and price momentum. CANSLIM analyzes 7 key components: **C**urrent Earnings, **A**nnual Growth, **N**ewness/New Highs, **S**upply/Demand, **L**eadership/RS Rank, **I**nstitutional Sponsorship, and **M**arket Direction.
 
-**Phase 2** implements 6 of 7 components (C, A, N, S, I, M), representing **80% of the full methodology**. This phase adds critical volume analysis (S) and institutional ownership tracking (I) to the Phase 1 foundation.
+**Phase 3** implements all 7 components (C, A, N, S, L, I, M), representing **100% of the full methodology**.
 
 **Two-Stage Approach:**
-1. **Stage 1 (FMP API + Finviz)**: Analyze stock universe with 6 CANSLIM components
+1. **Stage 1 (FMP API + Finviz)**: Analyze stock universe with all 7 CANSLIM components
 2. **Stage 2 (Reporting)**: Rank by composite score and generate actionable reports
 
 **Key Features:**
@@ -23,16 +23,16 @@ This skill screens US stocks using William O'Neil's proven CANSLIM methodology,
 - Interpretation bands: Exceptional+ (90+), Exceptional (80-89), Strong (70-79), Above Average (60-69)
 - Bear market protection (M component gating)
 
-**Phase 2 Component Weights (Renormalized for 6 components):**
-- C (Current Earnings): 19%
-- A (Annual Growth): 25%
-- N (Newness): 19%
-- S (Supply/Demand): 19% ← **NEW**
-- I (Institutional): 13% ← **NEW**
-- M (Market Direction): 6%
+**Phase 3 Component Weights (Full 7 components):**
+- C (Current Earnings): 15%
+- A (Annual Growth): 20%
+- N (Newness): 15%
+- S (Supply/Demand): 15%
+- L (Leadership/RS Rank): 20%
+- I (Institutional): 10%
+- M (Market Direction): 5%
 
 **Future Phases:**
-- Phase 3: Add L (Leadership/RS Rank) → 100% coverage (full CANSLIM)
 - Phase 4: FINVIZ Elite integration → 10x faster execution
 
 ---
@@ -121,10 +121,8 @@ User can provide sector-focused list (Technology, Healthcare, etc.)
 Run the main screening script with appropriate parameters:
 
 ```bash
-cd /Users/takueisaotome/PycharmProjects/claude-trading-skills/skills/canslim-screener/scripts
-
 # Basic run (40 stocks, top 20 in report)
-python3 screen_canslim.py --api-key $FMP_API_KEY
+python3 skills/canslim-screener/scripts/screen_canslim.py --api-key $FMP_API_KEY
 
 # Custom parameters
 python3 screen_canslim.py \
@@ -134,15 +132,16 @@ python3 screen_canslim.py \
   --output-dir ../../../
 ```
 
-**Script Workflow (Phase 2):**
+**Script Workflow (Phase 3 - Full CANSLIM):**
 1. **Market Direction (M)**: Analyze S&P 500 trend vs 50-day EMA
    - If bear market detected (M=0), warn user to raise cash
 2. **Stock Analysis**: For each stock, calculate:
    - **C Component**: Quarterly EPS/revenue growth (YoY)
    - **A Component**: 3-year EPS CAGR and stability
    - **N Component**: Distance from 52-week high, breakout detection
-   - **S Component**: Volume-based accumulation/distribution (up-day vs down-day volume) ← **NEW**
-   - **I Component**: Institutional holder count + ownership % (with Finviz fallback) ← **NEW**
+   - **S Component**: Volume-based accumulation/distribution (up-day vs down-day volume)
+   - **L Component**: Leadership/Relative Strength ranking
+   - **I Component**: Institutional holder count + ownership % (with Finviz fallback)
 3. **Composite Scoring**: Weighted average with component breakdown
 4. **Ranking**: Sort by composite score (highest first)
 5. **Reporting**: Generate JSON + Markdown outputs
@@ -341,6 +340,11 @@ Create a concise, actionable summary for the user:
   - Superinvestor detection (Berkshire Hathaway, Baupost, etc.)
   - Scoring: 50-100 holders + 30-60% ownership = 100pts
 
+- `leadership_calculator.py` - L component (Leadership/RS Rank)
+  - Relative strength ranking vs market
+  - Price performance relative to index
+  - Scoring based on RS rank percentile
+
 - `market_calculator.py` - M component (Market Direction)
   - S&P 500 vs 50-day EMA
   - VIX-adjusted scoring
@@ -348,7 +352,7 @@ Create a concise, actionable summary for the user:
 
 **Supporting Modules:**
 - `scorer.py` - Composite score calculation
-  - Phase 2 weighted average: C×19% + A×25% + N×19% + S×19% + I×13% + M×6%
+  - Phase 3 weighted average: C×15% + A×20% + N×15% + S×15% + L×20% + I×10% + M×5%
   - Rating interpretation (Exceptional+/Exceptional/Strong/etc.)
   - Minimum threshold validation (all 6 components must meet baseline)
 
@@ -521,27 +525,19 @@ Top 5 Stocks:
 
 ## Important Notes
 
-### Phase 2 Implementation Status
+### Phase 3 Implementation Status
 
-This is **Phase 2** implementing 6 of 7 CANSLIM components:
+This is **Phase 3** implementing all 7 CANSLIM components:
 - ✅ **C** (Current Earnings) - Implemented
 - ✅ **A** (Annual Growth) - Implemented
 - ✅ **N** (Newness) - Implemented
-- ✅ **S** (Supply/Demand) - Implemented (Phase 2) ← **NEW**
-- ❌ **L** (Leadership/RS Rank) - Not implemented (Phase 3)
-- ✅ **I** (Institutional) - Implemented (Phase 2) ← **NEW**
+- ✅ **S** (Supply/Demand) - Implemented
+- ✅ **L** (Leadership/RS Rank) - Implemented
+- ✅ **I** (Institutional) - Implemented
 - ✅ **M** (Market Direction) - Implemented
 
 **Implications:**
-- Composite scores represent **80% of full CANSLIM methodology**
-- Top scores typically max out at ~95 (full CANSLIM can reach 200+)
-- Missing component: Relative strength rank (L component)
-- Phase 2 provides highly accurate screening with volume and institutional analysis
-
-**Score Conversion:**
-- Phase 2 score 85+ ≈ Full CANSLIM 145-165 (Strong to Exceptional)
-- Phase 2 score 70-84 ≈ Full CANSLIM 125-144 (Above Average to Strong)
-- Phase 2 score 60-69 ≈ Full CANSLIM 110-124 (Average to Above Average)
+- Composite scores represent **100% of full CANSLIM methodology**
 
 ### Finviz Integration Benefits
 
@@ -562,11 +558,6 @@ This is **Phase 2** implementing 6 of 7 CANSLIM components:
 
 ### Future Enhancements
 
-**Phase 3 (Planned):**
-- Add L component: RS Rank estimation (52-week high proxy, 80% accuracy)
-- Full 7-component CANSLIM: C 15%, A 20%, N 15%, S 15%, L 20%, I 10%, M 5%
-- Coverage: 100% of full CANSLIM
-
 **Phase 4 (Planned):**
 - FINVIZ Elite integration for pre-screening
 - Execution time: 2 minutes → 10-15 seconds
@@ -591,9 +582,9 @@ This is **Phase 2** implementing 6 of 7 CANSLIM components:
 
 ---
 
-**Version:** Phase 2
-**Last Updated:** 2026-01-12
+**Version:** Phase 3 (Full CANSLIM)
+**Last Updated:** 2026-02-23
 **API Requirements:** FMP API (free tier sufficient) + BeautifulSoup/requests/lxml for Finviz
 **Execution Time:** ~1 minute 40 seconds for 40 stocks
 **Output Formats:** JSON + Markdown
-**Components Implemented:** C, A, N, S, I, M (6 of 7, 80% coverage)
+**Components Implemented:** C, A, N, S, L, I, M (7 of 7, 100% coverage)

package/.claude/skills/options-strategy-advisor/SKILL.md

@@ -871,11 +871,10 @@ else:
 User: "Explain a covered call"
 
 Workflow:
-1. Load strategy reference (references/strategies_guide.md)
-2. Explain concept, risk/reward, when to use
-3. Simulate example on AAPL
-4. Show P/L diagram
-5. Compare to alternatives
+1. Explain concept, risk/reward, when to use
+2. Simulate example on AAPL
+3. Show P/L diagram
+4. Compare to alternatives
 ```
 
 **Use Case 2: Analyze Specific Trade**
@@ -936,15 +935,8 @@ Workflow:
 
 ## Resources
 
-**References:**
-- `references/strategies_guide.md` - All 17+ strategies explained
-- `references/greeks_explained.md` - Greeks deep dive
-- `references/volatility_guide.md` - HV vs IV, when to trade
-
 **Scripts:**
-- `scripts/black_scholes.py` - Pricing engine and Greeks
-- `scripts/strategy_analyzer.py` - Strategy simulation
-- `scripts/earnings_strategy.py` - Earnings-specific analysis
+- `scripts/black_scholes.py` - Pricing engine and Greeks calculation
 
 **External Resources:**
 - Options Playbook: https://www.optionsplaybook.com/

package/.claude/skills/pair-trade-screener/SKILL.md

@@ -101,10 +101,7 @@ GET /v3/historical-price-full/{symbol}?apikey=YOUR_API_KEY
 - Fill minor gaps with forward-fill method
 - Log data quality issues
 
-**Script Execution:**
-```bash
-python scripts/fetch_price_data.py --sector Technology --lookback 730
-```
+Data fetching is handled by `scripts/find_pairs.py` which includes built-in FMP API price retrieval.
 
 ### Step 3: Calculate Correlation and Beta
 

package/.claude/skills/portfolio-manager/SKILL.md

@@ -40,7 +40,7 @@ This skill requires Alpaca MCP Server to be configured and connected. The MCP se
 - `get_portfolio_history` - Historical portfolio performance data
 - Market data tools for price quotes and fundamentals
 
-If Alpaca MCP Server is not connected, inform the user and provide setup instructions from `references/alpaca_mcp_setup.md`.
+If Alpaca MCP Server is not connected, inform the user and provide setup instructions from `references/alpaca-mcp-setup.md`.
 
 ## Workflow
 

package/.claude/skills/theme-detector/SKILL.md

@@ -234,17 +234,17 @@ Save the report to `reports/` directory.
   - Generates JSON + Markdown output
   - Usage: `python3 theme_detector.py [options]`
 
-- `theme_classifier.py` - Maps industries to cross-sector themes
+- `calculators/theme_classifier.py` - Maps industries to cross-sector themes
   - Reads theme definitions from `cross_sector_themes.md`
   - Calculates theme-level aggregated scores
   - Determines direction (bullish/bearish) from constituent industries
 
-- `finviz_industry_scanner.py` - FINVIZ industry data collection
+- `finviz_performance_client.py` - FINVIZ industry data collection
   - Elite mode: CSV export with full stock data per industry
   - Public mode: Web scraping with rate limiting
   - Extracts: performance, volume, change%, avg volume, market cap
 
-- `lifecycle_analyzer.py` - Lifecycle maturity assessment
+- `calculators/lifecycle_calculator.py` - Lifecycle maturity assessment
   - Duration scoring, extremity clustering, valuation analysis
   - ETF proliferation scoring from thematic_etf_catalog.md
   - Stage classification: Early / Mid / Late / Exhaustion
@@ -254,6 +254,17 @@ Save the report to `reports/` directory.
   - JSON structured output
   - Theme dashboard formatting
 
+**Additional Scripts:**
+- `scorer.py` - Theme scoring engine
+- `etf_scanner.py` - ETF data scanning for proliferation analysis
+- `uptrend_client.py` - Uptrend dashboard data integration
+- `config_loader.py` - Theme configuration loading (YAML/defaults)
+- `default_theme_config.py` - Built-in theme configuration fallback
+- `representative_stock_selector.py` - Select representative stocks per theme
+- `calculators/heat_calculator.py` - Theme heat score calculation
+- `calculators/industry_ranker.py` - Industry ranking by performance
+- `calculators/theme_discoverer.py` - Emerging theme discovery
+
 ### References Directory (`references/`)
 
 **Knowledge Bases:**

package/.claude/skills/weekly-trade-strategy/SKILL.md

@@ -0,0 +1,353 @@
+---
+name: weekly-trade-strategy
+description: 生成美股周交易策略博客。通过4步工作流（技术分析→市场环境评估→新闻分析→博客生成），为兼职交易者创建200-300行的周策略报告。可选第5步生成Druckenmiller风格18个月中长期战略。当用户请求周交易策略、周报生成、weekly blog、周末市场分析时使用。
+---
+
+# Weekly Trade Strategy Blog Generator
+
+## Overview
+
+自动生成美股周交易策略博客的多步编排技能。系统按顺序执行4个分析阶段，最终整合为面向兼职交易者的实用周策略文章（200-300行）。
+
+**核心流程：**
+```
+图表图片 → [技术分析] → [市场评估] → [新闻分析] → [博客生成] → 周策略博客
+```
+
+**依赖的技能：**
+- technical-analyst, breadth-chart-analyst, sector-analyst
+- market-environment-analysis, us-market-bubble-detector
+- market-news-analyst, economic-calendar-fetcher, earnings-calendar
+- stanley-druckenmiller-investment（可选，中长期策略）
+
+**输出格式：** Markdown 博客文章
+
+---
+
+## When to Use This Skill
+
+**触发关键词：**
+- "生成本周交易策略"
+- "创建周策略博客"
+- "weekly trade strategy"
+- "周末市场分析并生成博客"
+- "本周交易计划"
+
+**不适用场景：**
+- 单纯的技术分析（用 technical-analyst）
+- 单纯的新闻分析（用 market-news-analyst）
+- 个股分析（用 us-stock-analysis）
+
+---
+
+## Workflow
+
+### Step 0: 准备工作
+
+**确定日期：** 使用当前周的周一日期作为 DATE（格式 YYYY-MM-DD）。
+
+**检查图表图片：**
+
+```bash
+# 检查图表目录
+ls skills/weekly-trade-strategy/charts/$DATE/
+```
+
+如果图表目录不存在或为空：
+1. 创建目录：`mkdir -p skills/weekly-trade-strategy/charts/$DATE`
+2. 提示用户放入图表图片（推荐18张周线图表）：
+   - VIX、美国10年期国债收益率
+   - S&P 500 Breadth Index（200日均线 + 8日均线）
+   - Nasdaq 100、S&P 500、Russell 2000、Dow Jones（周线）
+   - 黄金、铜、原油、天然气、铀ETF（周线）
+   - Uptrend Stock Ratio（全市场）
+   - 板块表现（1周、1个月）
+   - 行业表现（涨幅/跌幅排名）
+   - 财报日历、主要个股热力图
+
+**创建输出目录：**
+```bash
+mkdir -p skills/weekly-trade-strategy/reports/$DATE
+```
+
+**检查上周博客（连续性参考）：**
+```bash
+ls skills/weekly-trade-strategy/blogs/
+```
+
+如果没有图表图片且用户未提供，跳过 Step 1 的图表分析部分，直接用 WebSearch 获取市场数据执行 Step 1。
+
+---
+
+### Step 1: Technical Market Analysis（技术分析）
+
+**目的：** 分析图表图片和市场数据，评估市场技术面
+
+**使用技能：** technical-analyst, breadth-chart-analyst, sector-analyst
+
+**执行方式：**
+
+1. **如果有图表图片**：逐一分析 `charts/$DATE/` 中的图表，运用 technical-analyst 和 breadth-chart-analyst 的方法论
+2. **如果没有图表**：通过 WebSearch 和 MCP 工具获取以下数据：
+   - 主要指数（SPY, QQQ, IWM, DIA）的周线技术状态
+   - VIX 当前值和趋势
+   - 10年期国债收益率
+   - 市场广度指标
+
+3. 使用 sector-analyst 的板块轮动框架分析板块表现
+
+**分析内容：**
+- VIX、10年期国债收益率、Breadth 指标的当前值和趋势评估
+- 主要指数的技术分析（趋势、支撑/阻力、移动平均线）
+- 大宗商品趋势分析（黄金、铜、原油、铀）
+- 板块轮动分析（进攻型 vs 防御型板块表现对比）
+- 情景概率评估（Bull / Base / Bear）
+
+**输出：** 保存至 `skills/weekly-trade-strategy/reports/$DATE/technical-market-analysis.md`
+
+---
+
+### Step 2: US Market Analysis（市场环境评估）
+
+**目的：** 综合评估市场阶段和系统性风险
+
+**使用技能：** market-environment-analysis, us-market-bubble-detector
+
+**输入：** Step 1 的 technical-market-analysis.md + 实时市场数据
+
+**执行方式：**
+
+1. 读取 Step 1 的技术分析报告
+2. 运用 market-environment-analysis 框架评估：
+   - 当前市场阶段（Risk-On / Base / Caution / Stress）
+   - 风险偏好 vs 风险规避指标
+3. 运用 us-market-bubble-detector 框架评估：
+   - 泡沫风险评分
+   - 各维度指标（估值、情绪、杠杆、广度等）
+
+**分析内容：**
+- 当前市场阶段判定及依据
+- 泡沫风险评分（Minsky/Kindleberger 框架）
+- 板块轮动模式（周期性 vs 防御性）
+- 波动率状态和趋势
+- 关键风险因素和催化剂
+
+**输出：** 保存至 `skills/weekly-trade-strategy/reports/$DATE/us-market-analysis.md`
+
+---
+
+### Step 3: Market News Analysis（新闻与事件分析）
+
+**目的：** 分析近期新闻影响和未来事件预测
+
+**使用技能：** market-news-analyst, economic-calendar-fetcher, earnings-calendar
+
+**输入：** Step 1 + Step 2 的报告 + 实时新闻数据
+
+**执行方式：**
+
+1. 使用 market-news-analyst 分析过去10天的市场重要新闻
+2. 使用 economic-calendar-fetcher 获取未来7天的经济事件日历
+3. 使用 earnings-calendar 获取未来7天的重要财报日程
+
+**分析内容：**
+- 过去10天的主要新闻及其对市场的影响评级
+- 未来7天的经济指标发布日程（FOMC、就业、CPI等）
+- 主要财报发布（市值$2B以上的公司）
+- 按事件的情景分析（附概率）
+- 风险事件优先级排序
+
+**输出：** 保存至 `skills/weekly-trade-strategy/reports/$DATE/market-news-analysis.md`
+
+---
+
+### Step 4: Weekly Blog Generation（博客生成）
+
+**目的：** 整合3份报告，生成面向兼职交易者的周策略博客
+
+**输入：**
+- `reports/$DATE/technical-market-analysis.md`
+- `reports/$DATE/us-market-analysis.md`
+- `reports/$DATE/market-news-analysis.md`
+- `blogs/` 目录中上周的博客文章（用于连续性检查）
+
+**博客文章结构（200-300行）：**
+
+```markdown
+# Weekly Trading Strategy - [DATE]
+
+## 📌 3句话总结
+- [市场环境一句话]
+- [本周焦点一句话]
+- [策略方向一句话]
+
+## 📋 本周操作
+### 仓位管理
+[总体仓位建议：股票 X%、现金 X%]
+
+### 板块配置
+| 板块 | 本周配置 | 上周配置 | 变动 | 理由 |
+|------|---------|---------|------|------|
+
+### 关键价位
+[主要指数支撑/阻力位]
+
+### 重要事件
+[本周必须关注的事件和时间]
+
+## 🎯 情景计划
+### Base Case (XX%)
+[最可能的情景和对应操作]
+
+### Risk-On Case (XX%)
+[乐观情景和对应操作]
+
+### Caution Case (XX%)
+[风险情景和对应操作]
+
+## 📊 市场状况
+### 触发指标
+| 指标 | 当前值 | 警戒线 | 状态 |
+|------|--------|--------|------|
+| 10Y 收益率 | | | |
+| VIX | | | |
+| Breadth Index | | | |
+
+## 🏭 商品与板块策略
+[黄金、铜、原油、铀的策略建议]
+
+## ⏰ 兼职交易指南
+### 早间检查（开盘前5分钟）
+- [ ] [检查项1]
+- [ ] [检查项2]
+
+### 晚间检查（收盘后5分钟）
+- [ ] [检查项1]
+- [ ] [检查项2]
+
+## ⚠️ 风险管理
+[本周特有风险和应对措施]
+
+## 📝 总结
+[3-5句话总结本周策略]
+
+---
+*Generated on [DATE] | Data sources: FMP API, WebSearch*
+```
+
+**关键约束：**
+- 与上周的板块配置变动 **控制在 ±10-15% 以内**（渐进式调整）
+- 在历史新高+Base触发条件下，避免大幅削减仓位
+- 现金配置应渐进增加（例：10% → 20-25% → 30-35%）
+- 文章长度严格控制在 200-300 行
+
+**输出：** 保存至 `skills/weekly-trade-strategy/blogs/$DATE-weekly-strategy.md`
+
+---
+
+### Step 5（可选）: Druckenmiller Strategy Planning
+
+**触发条件：** 用户明确要求，或每季度执行一次
+
+**目的：** 制定18个月中长期投资战略
+
+**使用技能：** stanley-druckenmiller-investment
+
+**输入：** Step 1-3 的3份报告
+
+**输出结构：**
+```markdown
+# Strategic Investment Outlook - [DATE]
+
+## Executive Summary
+## Market Context & Current Environment
+## 18-Month Scenario Analysis
+### Base Case (XX%)
+### Bull Case (XX%)
+### Bear Case (XX%)
+### Tail Risk (XX%)
+## Recommended Strategic Actions
+### High Conviction Trades
+### Medium Conviction Positions
+### Hedges & Protective Strategies
+## Key Monitoring Indicators
+## Conclusion & Next Review Date
+```
+
+**输出：** 保存至 `skills/weekly-trade-strategy/reports/$DATE/druckenmiller-strategy.md`
+
+---
+
+## Data Flow
+
+```
+charts/$DATE/*.jpeg (用户提供)
+  │
+  ├─→ [Step 1: 技术分析] ──→ technical-market-analysis.md
+  │     skills: technical-analyst, breadth-chart-analyst, sector-analyst
+  │                                    │
+  │                                    ├─→ [Step 2: 市场评估] ──→ us-market-analysis.md
+  │                                    │     skills: market-environment-analysis, bubble-detector
+  │                                    │                              │
+  │                                    │                              ├─→ [Step 3: 新闻分析] ──→ market-news-analysis.md
+  │                                    │                              │     skills: market-news-analyst, calendars
+  │                                    │                              │
+  └────────────────────────────────────┴──────────────────────────────┴─→ [Step 4: 博客生成]
+                                                                              │
+                                                                              └─→ blogs/$DATE-weekly-strategy.md
+  上周博客 (blogs/) ──────────────────────────────────────────────────────────────┘ (连续性参考)
+```
+
+---
+
+## Quality Standards
+
+**内容质量：**
+- 所有分析和输出使用英文
+- 数据驱动，避免主观臆断
+- 每个判断附带具体数据支撑
+- 概率评估需合理且总和约100%
+
+**连续性：**
+- 板块配置变动 ≤ ±15%（除非出现重大事件）
+- 引用上周策略执行情况
+- 标注策略变更的具体原因
+
+**实用性：**
+- 面向每周投入5-10小时的兼职交易者
+- 提供具体的价位和操作建议
+- 早/晚各5分钟的检查清单
+- 明确的风险管理规则
+
+---
+
+## Troubleshooting
+
+**问题：没有图表图片**
+→ 跳过图表分析，用 WebSearch + MCP 工具获取数据执行 Step 1
+
+**问题：上周博客不存在**
+→ 不做连续性检查，生成独立的首期博客
+
+**问题：经济日历/财报日历获取失败**
+→ 用 WebSearch 作为 fallback 获取事件信息
+
+**问题：博客超过300行**
+→ 精简各板块内容，优先保留操作建议，削减背景分析
+
+---
+
+## Important Notes
+
+- 本技能为**编排型技能**，按顺序调用多个子技能完成工作流
+- 每步完成后应向用户确认结果，再进入下一步
+- 所有分析输出使用英文
+- 这是教育和信息用途，不构成投资建议
+
+---
+
+**Version:** 2.0
+**Last Updated:** 2026-02-23
+**Execution Time:** ~15-30 分钟（含数据获取和分析）
+**Output:** Markdown 博客文章 + 3份分析报告
+**Dependencies:** 9个子技能 + WebSearch + FMP API