macro-regime-detector by tradermonty/claude-trading-skills
npx skills add https://github.com/tradermonty/claude-trading-skills --skill macro-regime-detector使用月度频率的跨资产比率分析来检测结构性宏观状态转换。此技能可识别持续1-2年的状态转变,为战略性投资组合配置提供信息。
加载参考文档以了解方法背景:
references/regime_detection_methodology.mdreferences/indicator_interpretation_guide.md执行主分析脚本:
python3 skills/macro-regime-detector/scripts/macro_regime_detector.py
此操作将获取 9 只 ETF + 国债利率的 600 天数据(总计 10 次 API 调用)。
references/historical_regimes.md 提供额外背景信息。广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
FMP_API_KEY 环境变量或传递 --api-key 参数---|---|---|---|---
1 | 市场集中度 | RSP/SPY | 25% | 超大市值集中 vs 市场扩散
2 | 收益率曲线 | 10Y-2Y 利差 | 20% | 利率周期转换
3 | 信用状况 | HYG/LQD | 15% | 信用周期风险偏好
4 | 规模因子 | IWM/SPY | 15% | 小盘股 vs 大盘股轮动
5 | 股债关系 | SPY/TLT + 相关性 | 15% | 股票-债券关系状态
6 | 板块轮动 | XLY/XLP | 10% | 周期性 vs 防御性偏好
macro_regime_YYYY-MM-DD_HHMMSS.json — 用于程序化处理的结构化数据macro_regime_YYYY-MM-DD_HHMMSS.md — 人类可读的报告,包含:
| 方面 | 宏观状态检测器 | 市场顶部检测器 | 市场广度分析器 |
|---|---|---|---|
| 时间范围 | 1-2 年(结构性) | 2-8 周(战术性) | 当前快照 |
| 数据粒度 | 月度(6M/12M SMA) | 日度(25 个交易日) | 日度 CSV |
| 检测目标 | 状态转换 | 10-20% 的回调 | 广度健康度评分 |
| API 调用 | ~10 | ~33 | 0(免费 CSV) |
python3 macro_regime_detector.py [options]
Options:
--api-key KEY FMP API key (default: $FMP_API_KEY)
--output-dir DIR 输出目录(默认:当前目录)
--days N 获取的历史天数(默认:600)
references/regime_detection_methodology.md — 检测方法和信号解读references/indicator_interpretation_guide.md — 跨资产比率解读指南references/historical_regimes.md — 用于背景参考的历史状态示例每周安装量
155
代码仓库
GitHub 星标数
398
首次出现
2026年2月16日
安全审计
安装于
gemini-cli149
cursor149
github-copilot148
amp148
codex148
kimi-cli148
Detect structural macro regime transitions using monthly-frequency cross-asset ratio analysis. This skill identifies 1-2 year regime shifts that inform strategic portfolio positioning.
Load reference documents for methodology context:
references/regime_detection_methodology.mdreferences/indicator_interpretation_guide.mdExecute the main analysis script:
python3 skills/macro-regime-detector/scripts/macro_regime_detector.py
This fetches 600 days of data for 9 ETFs + Treasury rates (10 API calls total).
Read the generated Markdown report and present findings to user.
Provide additional context using references/historical_regimes.md when user asks about historical parallels.
FMP_API_KEY environment variable or pass --api-key---|---|---|---|---
1 | Market Concentration | RSP/SPY | 25% | Mega-cap concentration vs market broadening
2 | Yield Curve | 10Y-2Y spread | 20% | Interest rate cycle transitions
3 | Credit Conditions | HYG/LQD | 15% | Credit cycle risk appetite
4 | Size Factor | IWM/SPY | 15% | Small vs large cap rotation
5 | Equity-Bond | SPY/TLT + correlation | 15% | Stock-bond relationship regime
6 | Sector Rotation | XLY/XLP | 10% | Cyclical vs defensive appetite
macro_regime_YYYY-MM-DD_HHMMSS.json — Structured data for programmatic usemacro_regime_YYYY-MM-DD_HHMMSS.md — Human-readable report with:
| Aspect | Macro Regime Detector | Market Top Detector | Market Breadth Analyzer |
|---|---|---|---|
| Time Horizon | 1-2 years (structural) | 2-8 weeks (tactical) | Current snapshot |
| Data Granularity | Monthly (6M/12M SMA) | Daily (25 business days) | Daily CSV |
| Detection Target | Regime transitions | 10-20% corrections | Breadth health score |
| API Calls | ~10 | ~33 | 0 (Free CSV) |
python3 macro_regime_detector.py [options]
Options:
--api-key KEY FMP API key (default: $FMP_API_KEY)
--output-dir DIR Output directory (default: current directory)
--days N Days of history to fetch (default: 600)
references/regime_detection_methodology.md — Detection methodology and signal interpretationreferences/indicator_interpretation_guide.md — Guide for interpreting cross-asset ratiosreferences/historical_regimes.md — Historical regime examples for contextWeekly Installs
155
Repository
GitHub Stars
398
First Seen
Feb 16, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
gemini-cli149
cursor149
github-copilot148
amp148
codex148
kimi-cli148
Python PDF处理教程:合并拆分、提取文本表格、创建PDF文件
61,100 周安装