技能库智客分类：Agent 工作流 stock-analysis

Stock Analysis

利用雅虎金融数据分析股票和密码。支持投资组合管理(创建、增加、去除资产)、加密分析(按市场上限计算,第20段)和定期业绩报告(每日/每周/月/季/年)。 8个分析维度的股票,3个密码。用于股票分析、投资组合跟踪、收益反应或加密监测.

12304 安装量

官方网址：作者主页

技能介绍

先看中文介绍；官方 description 原文单独保留，不改写 SKILL.md。

做什么

何时用

官方 description 未单独写出 Use when。按规范，代理会在用户任务与这段 description 的关键词匹配时激活本技能。

代理如何加载

按 Agent Skills 渐进披露：启动时只加载 name 与 description（约 100 token）；任务匹配后才读入整份 SKILL.md 正文；scripts/、references/、assets/ 仅在需要时再读。本文件正文结构：Stock Analysis (v5.0)、Quick Start、Cryptocurrency Analysis (v5.0)、Portfolio Management (v5.0)、Create portfolio、Add assets。

文件分析

文件分析：除 SKILL.md 外，正文引用了 scripts/analyze_stock.py、scripts/portfolio.py，属于带资源的技能包，这些文件按需再读。

官方 description（原文）

Analyze stocks and cryptocurrencies using Yahoo Finance data. Supports portfolio management (create, add, remove assets), crypto analysis (Top 20 by market cap), and periodic performance reports (daily/weekly/monthly/quarterly/yearly). 8 analysis dimensions for stocks, 3 for crypto. Use for stock analysis, portfolio tracking, earnings reactions, or crypto monitoring.

Stock Analysis (v5.0)Quick StartCryptocurrency Analysis (v5.0)Portfolio Management (v5.0)Create portfolioAdd assetsView holdings with current P&LUpdate/remove assetsList/delete portfoliosPortfolio Analysis (v5.0)Analyze portfolioWith period returns (daily/weekly/monthly/quarterly/yearly)

来源分类：skills.sh agent-skill

来源与网址

市场来源：skills.sh

GitHub 完整包

开源榜 Skill 分类

SKILL.md 与 Agent 调用

官方规范 ↗

name: stock-analysis
description: Analyze stocks and cryptocurrencies using Yahoo Finance data. Supports portfolio management (create, add, remove assets), crypto analysis (Top 20 by market cap), and periodic performance reports (daily/weekly/monthly/quarterly/yearly). 8 analysis dimensions for stocks, 3 for crypto. Use for stock analysis, portfolio tracking, earnings reactions, or crypto monitoring.

发现技能客户端向 Agent 提供名称与描述目录。
匹配与调用用户指定或任务匹配后，载入 SKILL.md 指令。
按需加载按步骤读取参考文档、使用脚本与素材。

指令中引用的文件 · 2

scripts/analyze_stock.py
scripts/portfolio.py

以下路径提取自原文；文件是否齐全请以来源仓库中的完整目录为准。

具体调用语法与可用工具以目标 Agent 客户端为准。查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围，保留技能包的附属文件，安装后检查客户端能否发现该技能。

该技能引用了附属文件，请从来源获取完整目录；仅复制 SKILL.md 可能缺少依赖。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理，确认其中的目标目录与客户端匹配。

把 Agent Skill「stock-analysis」安装到我的项目：SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-b03fa619ab05001c-Stock-Analysis.html
请存为 .cursor/skills/stock-analysis/SKILL.md 或 .claude/skills/stock-analysis/SKILL.md，frontmatter 的 name 与 description 保持原样，不要改写。
该技能还带 scripts/、references/、assets/ 等文件，请从 https://github.com/gracefullight/stock-checker 取完整目录，不要只建一个 SKILL.md。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表，确认实际名称。

npx skills add 'https://github.com/gracefullight/stock-checker' --list

目标客户端安装范围

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

CLI 会交互选择目标 Agent，默认安装到项目；用户级安装使用 -g。先通过查看命令核对仓库内容，再用 npx skills list 检查已安装技能。

SKILL.md 原文可复制，不会改动源文件

---
name: stock-analysis
description: Analyze stocks and cryptocurrencies using Yahoo Finance data. Supports portfolio management (create, add, remove assets), crypto analysis (Top 20 by market cap), and periodic performance reports (daily/weekly/monthly/quarterly/yearly). 8 analysis dimensions for stocks, 3 for crypto. Use for stock analysis, portfolio tracking, earnings reactions, or crypto monitoring.
homepage: https://finance.yahoo.com
metadata: {"clawdbot":{"emoji":"📈","requires":{"bins":["uv"],"env":[]},"install":[{"id":"uv-brew","kind":"brew","formula":"uv","bins":["uv"],"label":"Install uv (brew)"}]}}
---

# 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:

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

Compare multiple tickers:

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

## Cryptocurrency Analysis (v5.0)

Analyze top 20 cryptocurrencies by market cap:

```bash
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):

```bash
# 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:

```bash
# 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:

1. **Earnings Surprise (30% weight)**: Actual vs expected EPS, revenue beats/misses
2. **Fundamentals (20% weight)**: P/E ratio, profit margins, revenue growth, debt levels
3. **Analyst Sentiment (20% weight)**: Consensus ratings, price target vs current price
4. **Historical Patterns (10% weight)**: Past earnings reactions, volatility
5. **Market Context (10% weight)**: VIX, SPY/QQQ trends, market regime
6. **Sector Performance (15% weight)**: Stock vs sector comparison, sector trends
7. **Momentum (15% weight)**: RSI, 52-week range, volume, relative strength
8. **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

觉得这个技能有帮助？

🚀 晒出用它做的作品

阅读排版

name: stock-analysis description: Analyze stocks and cryptocurrencies using Yahoo Finance data. Supports portfolio management (create, add, remove assets), crypto analysis (Top 20 by market cap), and periodic performance reports (daily/weekly/monthly/quarterly/yearly). 8 analysis dimensions for stocks, 3 for crypto. Use for stock analysis, portfolio tracking, earnings reactions, or crypto monitoring. homepage: https://finance.yahoo.com metadata: {"clawdbot":{"emoji":"📈","requires":{"bins":["uv"],"env":[]},"install":[{"id":"uv-brew","kind":"brew","formula":"uv","bins":["uv"],"label":"Install uv (brew)"}]}}

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