股票与加密货币分析工具 - 投资组合管理与技术分析（雅虎财经数据）

stock-analysis by gracefullight/stock-checker

7,000 周安装量

11 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/gracefullight/stock-checker --skill stock-analysis

AI/机器学习开发数据分析

🇨🇳中文介绍

股票分析 (v5.0)

使用雅虎财经数据分析和加密货币。包含投资组合管理、加密货币支持和周期性分析。

快速开始

重要提示： 命令中仅传递股票代码符号。不要在命令中添加额外的文本、标题或格式。

分析单个代码：

uv run {baseDir}/scripts/analyze_stock.py AAPL
uv run {baseDir}/scripts/analyze_stock.py MSFT --output json

比较多个代码：

uv run {baseDir}/scripts/analyze_stock.py AAPL MSFT GOOGL

加密货币分析 (v5.0)

按市值分析前 20 名加密货币：

uv run {baseDir}/scripts/analyze_stock.py BTC-USD
uv run {baseDir}/scripts/analyze_stock.py ETH-USD SOL-USD

支持的加密货币： BTC-USD, ETH-USD, BNB-USD, SOL-USD, XRP-USD, ADA-USD, DOGE-USD, AVAX-USD, DOT-USD, MATIC-USD, LINK-USD, ATOM-USD, UNI-USD, LTC-USD, BCH-USD, XLM-USD, ALGO-USD, VET-USD, FIL-USD, NEAR-USD

加密货币分析维度：

市值（大/中/小盘分类）
类别（智能合约 L1、DeFi、支付等）
与 BTC 相关性（30 天）
动量（RSI，价格区间）
市场环境（VIX，整体市场状况）

投资组合管理 (v5.0)

创建和管理包含混合资产（股票 + 加密货币）的投资组合：

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

联系我们

投资组合分析 (v5.0)

分析投资组合中的所有资产，可选择包含周期回报：

# 分析投资组合
uv run {baseDir}/scripts/analyze_stock.py --portfolio "My Portfolio"

# 包含周期回报（日/周/月/季/年）
uv run {baseDir}/scripts/analyze_stock.py --portfolio "My Portfolio" --period weekly
uv run {baseDir}/scripts/analyze_stock.py -p "My Portfolio" --period monthly

投资组合摘要包括：

总成本、当前价值、盈亏
周期回报（如指定）
集中度警告（单一资产 >30%）
建议摘要（买入/持有/卖出数量）

✅ 正确：uv run {baseDir}/scripts/analyze_stock.py BAC
✅ 正确：uv run {baseDir}/scripts/analyze_stock.py BTC-USD
❌ 错误：uv run {baseDir}/scripts/analyze_stock.py === BANK OF AMERICA (BAC) - Q4 2025 EARNINGS ===
❌ 错误：uv run {baseDir}/scripts/analyze_stock.py "Bank of America"

请仅使用股票代码符号（例如 BAC，而不是 "Bank of America"）。对于加密货币，请使用 -USD 后缀（例如 BTC-USD）。

该脚本评估八个关键维度：

盈利惊喜（30% 权重） ：实际 vs 预期每股收益，营收超出/不及预期
基本面（20% 权重） ：市盈率、利润率、营收增长、债务水平
分析师情绪（20% 权重） ：共识评级、目标价 vs 当前价格
历史模式（10% 权重） ：过往盈利反应、波动性
市场环境（10% 权重） ：VIX、SPY/QQQ 趋势、市场状况
行业表现（15% 权重） ：股票 vs 行业比较、行业趋势
动量（15% 权重） ：RSI、52 周区间、成交量、相对强度
情绪分析（10% 权重） ：恐惧/贪婪指数、空头头寸、VIX 期限结构、内幕交易、看跌/看涨比率

情绪子指标：

恐惧与贪婪指数（CNN） ：逆向信号（极度恐惧 = 买入机会，极度贪婪 = 谨慎）
空头头寸 ：高空头头寸 + 轧空潜力 = 看涨；合理的空头头寸 = 看跌
VIX 期限结构 ：期货升水 = 自满/看涨；期货贴水 = 压力/看跌
内幕活动 ：SEC 表格 4 申报中的净买入/卖出（90 天窗口期）
看跌/看涨比率 ：高比率 = 过度恐惧/看涨；低比率 = 自满/看跌

如果某些组件不可用，权重会自动归一化。

特殊时机检查：

盈利发布前警告（< 14 天）：建议持有而非买入
盈利发布后飙升检测（5 天内 > 15%）：标记“涨幅已计入”
超买状况（RSI > 70 + 接近 52 周高点）：降低信心度

时机警告与风险标记

该脚本检测高风险场景：

盈利发布前期 ：如果盈利发布 < 14 天，买入信号变为持有
盈利发布后飙升 ：如果盈利发布后 5 天内股票上涨 > 15%，警告“涨幅可能已计入”

超买状况 ：RSI > 70 + 接近 52 周高点 = 高风险入场点

高 VIX ：市场恐惧（VIX > 30）降低对买入信号的信心
避险模式（v4.0.0） ：当避险资产（GLD, TLT, UUP）一同上涨时，将买入信心降低 30%
- 检测资金流向黄金、国债和美元的安全性
- 当 GLD ≥ +2%、TLT ≥ +1%、UUP ≥ +1%（5 日变化）时触发

行业疲软 ：股票可能看起来不错，但行业正在轮动流出

地缘政治风险（v4.0.0）

该脚本现在会扫描突发新闻（过去 24 小时）以查找危机关键词，并自动标记受影响的股票：

台湾冲突 ：半导体（NVDA, AMD, TSM, INTC 等）→ 30% 信心度惩罚
中国紧张局势 ：科技/消费（AAPL, QCOM, NKE, SBUX 等）→ 30% 信心度惩罚
俄罗斯-乌克兰 ：能源/材料（XOM, CVX, MOS, CF 等）→ 30% 信心度惩罚
中东：石油/国防（XOM, LMT, RTX 等）→ 30% 信心度惩罚
银行业危机 ：金融（JPM, BAC, WFC, C 等）→ 30% 信心度惩罚

如果某个股票代码不在受影响列表中但其行业暴露，则应用 15% 的信心度惩罚。

⚠️ 行业风险：科技供应链和消费市场暴露（检测到：china, tariff）

突发新闻警报（v4.0.0）

扫描 Google News RSS 以查找危机关键词（战争、衰退、制裁、灾难等）
在注意事项中显示最多 2 条突发新闻警报（过去 24 小时）
使用 1 小时缓存以避免过多的 API 调用

默认（文本） ：简洁的买入/持有/卖出信号，附带 3-5 个要点和注意事项

JSON ：包含分数、指标和原始数据的结构化数据，用于进一步分析

数据新鲜度 ：雅虎财经数据可能滞后 15-20 分钟
情绪数据陈旧性 ：
- 空头头寸数据滞后约 2 周（FINRA 报告计划）
- 内幕交易可能滞后申报 2-3 天
- VIX 期限结构仅在期货交易时段更新
突发新闻局限性（v4.0.0） ：
- Google News RSS 可能滞后 15-60 分钟
- 关键词匹配可能存在误报/漏报
- 不分析情绪，仅检测关键词
- 1 小时缓存意味着警报可能略有延迟
数据缺失 ：并非所有股票都有分析师覆盖、期权链或完整的基本面数据
执行时间 ：每只股票 3-5 秒，使用异步并行获取和缓存（共享指标缓存 1 小时）
免责声明 ：所有输出都包含显著的“非财务建议”警告
仅限美国市场 ：非美国股票代码可能数据不完整

该脚本优雅地处理：

无效股票代码 → 清晰的错误信息
缺少分析师数据 → 仅基于可用指标的信号
API 故障 → 指数退避重试，3 次尝试后失败

🇺🇸English

Stock Analysis (v5.0)

Analyze US stocks and cryptocurrencies using Yahoo Finance data. Includes portfolio management, crypto support, and periodic analysis.

Quick Start

IMPORTANT: Pass ONLY the stock ticker symbol(s) as arguments. Do NOT add extra text, headers, or formatting in the command.

Analyze a single ticker:

uv run {baseDir}/scripts/analyze_stock.py AAPL
uv run {baseDir}/scripts/analyze_stock.py MSFT --output json

Compare multiple tickers:

uv run {baseDir}/scripts/analyze_stock.py AAPL MSFT GOOGL

Cryptocurrency Analysis (v5.0)

Analyze top 20 cryptocurrencies by market cap:

uv run {baseDir}/scripts/analyze_stock.py BTC-USD
uv run {baseDir}/scripts/analyze_stock.py ETH-USD SOL-USD

Supported Cryptos: BTC-USD, ETH-USD, BNB-USD, SOL-USD, XRP-USD, ADA-USD, DOGE-USD, AVAX-USD, DOT-USD, MATIC-USD, LINK-USD, ATOM-USD, UNI-USD, LTC-USD, BCH-USD, XLM-USD, ALGO-USD, VET-USD, FIL-USD, NEAR-USD

Crypto Analysis Dimensions:

Market cap (large/mid/small classification)
Category (Smart Contract L1, DeFi, Payment, etc.)
BTC correlation (30-day)
Momentum (RSI, price range)
Market context (VIX, general market regime)

Portfolio Management (v5.0)

Create and manage portfolios with mixed assets (stocks + crypto):

# Create portfolio
uv run {baseDir}/scripts/portfolio.py create "My Portfolio"

# Add assets
uv run {baseDir}/scripts/portfolio.py add AAPL --quantity 100 --cost 150.00
uv run {baseDir}/scripts/portfolio.py add BTC-USD --quantity 0.5 --cost 40000 --portfolio "My Portfolio"

# View holdings with current P&L
uv run {baseDir}/scripts/portfolio.py show

# Update/remove assets
uv run {baseDir}/scripts/portfolio.py update AAPL --quantity 150
uv run {baseDir}/scripts/portfolio.py remove BTC-USD

# List/delete portfolios
uv run {baseDir}/scripts/portfolio.py list
uv run {baseDir}/scripts/portfolio.py delete "My Portfolio"

Portfolio Storage: ~/.clawdbot/skills/stock-analysis/portfolios.json

Portfolio Analysis (v5.0)

Analyze all assets in a portfolio with optional period returns:

# Analyze portfolio
uv run {baseDir}/scripts/analyze_stock.py --portfolio "My Portfolio"

# With period returns (daily/weekly/monthly/quarterly/yearly)
uv run {baseDir}/scripts/analyze_stock.py --portfolio "My Portfolio" --period weekly
uv run {baseDir}/scripts/analyze_stock.py -p "My Portfolio" --period monthly

Portfolio Summary includes:

Total cost, current value, P&L
Period return (if specified)
Concentration warnings (>30% in single asset)
Recommendation summary (BUY/HOLD/SELL counts)

Examples:

✅ CORRECT: uv run {baseDir}/scripts/analyze_stock.py BAC
✅ CORRECT: uv run {baseDir}/scripts/analyze_stock.py BTC-USD
❌ WRONG: uv run {baseDir}/scripts/analyze_stock.py === BANK OF AMERICA (BAC) - Q4 2025 EARNINGS ===
❌ WRONG: uv run {baseDir}/scripts/analyze_stock.py "Bank of America"

Use the ticker symbol only (e.g., BAC, not "Bank of America"). For crypto, use the -USD suffix (e.g., BTC-USD).

Analysis Components

The script evaluates eight key dimensions:

Earnings Surprise (30% weight) : Actual vs expected EPS, revenue beats/misses
Fundamentals (20% weight) : P/E ratio, profit margins, revenue growth, debt levels
Analyst Sentiment (20% weight) : Consensus ratings, price target vs current price
Historical Patterns (10% weight) : Past earnings reactions, volatility
Market Context (10% weight) : VIX, SPY/QQQ trends, market regime
Sector Performance (15% weight) : Stock vs sector comparison, sector trends
Momentum (15% weight) : RSI, 52-week range, volume, relative strength
Sentiment Analysis (10% weight) : Fear/Greed Index, short interest, VIX term structure, insider trading, put/call ratio

Sentiment Sub-Indicators:

Fear & Greed Index (CNN): Contrarian signal (extreme fear = buy opportunity, extreme greed = caution)
Short Interest : High shorts + squeeze potential = bullish; justified shorts = bearish
VIX Term Structure : Contango = complacency/bullish; backwardation = stress/bearish
Insider Activity : Net buying/selling from SEC Form 4 filings (90-day window)
Put/Call Ratio : High ratio = excessive fear/bullish; low ratio = complacency/bearish

Weights auto-normalize if some components unavailable.

Special Timing Checks:

Pre-earnings warning (< 14 days): Recommends HOLD instead of BUY
Post-earnings spike detection (> 15% in 5 days): Flags "gains priced in"
Overbought conditions (RSI > 70 + near 52w high): Reduces confidence

Timing Warnings & Risk Flags

The script detects high-risk scenarios:

Earnings Timing

Pre-Earnings Period : If earnings < 14 days away, BUY signals become HOLD
Post-Earnings Spike : If stock up > 15% in 5 days after earnings, warns "gains may be priced in"

Technical Risk

Overbought Conditions : RSI > 70 + near 52-week high = high-risk entry

Market Risk

High VIX : Market fear (VIX > 30) reduces confidence in BUY signals
Risk-Off Mode (v4.0.0) : When safe-havens (GLD, TLT, UUP) rise together, reduces BUY confidence by 30%
- Detects flight to safety across gold, treasuries, and USD
- Triggers when GLD ≥ +2%, TLT ≥ +1%, UUP ≥ +1% (5-day change)

Sector Risk

Sector Weakness : Stock may look good but sector is rotating out

Geopolitical Risk (v4.0.0)

The script now scans breaking news (last 24h) for crisis keywords and automatically flags affected stocks:

Taiwan Conflict : Semiconductors (NVDA, AMD, TSM, INTC, etc.) → 30% confidence penalty
China Tensions : Tech/Consumer (AAPL, QCOM, NKE, SBUX, etc.) → 30% confidence penalty
Russia-Ukraine : Energy/Materials (XOM, CVX, MOS, CF, etc.) → 30% confidence penalty
Middle East : Oil/Defense (XOM, LMT, RTX, etc.) → 30% confidence penalty
Banking Crisis : Financials (JPM, BAC, WFC, C, etc.) → 30% confidence penalty

If a ticker is not in the affected list but its sector is exposed, applies a 15% confidence penalty.

Example Alert:

⚠️ SECTOR RISK: Tech supply chain and consumer market exposure (detected: china, tariff)

Breaking News Alerts (v4.0.0)

Scans Google News RSS for crisis keywords (war, recession, sanctions, disasters, etc.)
Displays up to 2 breaking news alerts in caveats (last 24 hours)
Uses 1-hour cache to avoid excessive API calls

Output Format

Default (text) : Concise buy/hold/sell signal with 3-5 bullet points and caveats

JSON : Structured data with scores, metrics, and raw data for further analysis

Limitations

Data freshness : Yahoo Finance may lag 15-20 minutes
Sentiment data staleness :
- Short interest data lags ~2 weeks (FINRA reporting schedule)
- Insider trades may lag filing by 2-3 days
- VIX term structure only updates during futures trading hours
Breaking news limitations (v4.0.0) :
- Google News RSS may lag by 15-60 minutes
- Keyword matching may have false positives/negatives
- Does not analyze sentiment, only detects keywords
- 1-hour cache means alerts may be slightly stale
Missing data : Not all stocks have analyst coverage, options chains, or complete fundamentals
Execution time : 3-5s per stock with async parallel fetching and caching (shared indicators cached for 1h)
Disclaimer : All outputs include prominent "not financial advice" warning
US markets only : Non-US tickers may have incomplete data

Error Handling

The script gracefully handles:

Invalid tickers → Clear error message
Missing analyst data → Signal based on available metrics only
API failures → Retry with exponential backoff, fail after 3 attempts

Weekly Installs

7.0K

Repository

gracefullight/s…-checker

GitHub Stars

First Seen

Jan 27, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

Installed on

opencode6.5K

gemini-cli6.4K

codex6.4K

github-copilot6.4K

kimi-cli6.3K

amp6.3K