Detalle del Skill
yfinance-data
Broad financial and market data retrieval.
Revisar antes de usar
La revisión automática comprueba relevancia, no seguridad ni respaldo. Lee las instrucciones de la fuente antes de usar este Skill.
SKILL.md
Este extracto es una copia guardada durante la revisión. La fuente externa contiene la versión completa y actual.
---
name: yfinance-data
description: >
Fetch financial and market data using the yfinance Python library.
Use this skill whenever the user asks for stock prices, historical data, financial statements,
options chains, dividends, earnings, analyst recommendations, or any market data.
Triggers include: any mention of stock price, ticker symbol (AAPL, MSFT, TSLA, etc.),
"get me the financials", "show earnings", "what's the price of", "download stock data",
"options chain", "dividend history", "balance sheet", "income statement", "cash flow",
"analyst targets", "institutional holders", "compare stocks", "screen for stocks",
or any request involving Yahoo Finance data.
Always use this skill even if the user only provides a ticker — infer intent from context.
---
# yfinance Data Skill
Fetches financial and market data from Yahoo Finance using the [yfinance](https://github.com/ranaroussi/yfinance) Python library.
**Important**: yfinance is not affiliated with Yahoo, Inc. Data is for research and educational purposes.
---
## Step 1: Ensure yfinance Is Available
**Current environment status:**
```
!`python3 -c "import yfinance; print('yfinance ' + yfinance.__version__ + ' installed')" 2>/dev/null || echo "YFINANCE_NOT_INSTALLED"`
```
If `YFINANCE_NOT_INSTALLED`, install it before running any code:
```python
import subprocess, sys
subprocess.check_call([sys.executable, "-m", "pip", "install", "-q", "yfinance"])
```
If yfinance is already installed, skip the install step and proceed directly.
---
## Step 2: Identify What the User Needs
Match the user's request to one or more data categories below, then use the corresponding code from `references/api_reference.md`.
| User Request | Data Category | Primary Method |
|---|---|---|
| Stock price, quote | Current price | `ticker.info` or `ticker.fast_info` |
| Price history, chart data | Historical OHLCV | `ticker.history()` or `yf.download()` |
| Balance sheet | Financial statements | `ticker.balance_sheet` |
| Income statement, revenue | Financial statements | `ticker.income_stmt` |
| Cash flow | Financial statements | `ticker.cashflow` |
| Dividends | Corporate actions | `ticker.dividends` |
| Stock splits | Corporate actions | `ticker.splits` |
| Options chain, calls, puts | Options data | `ticker.option_chain()` |
| Earnings, EPS | Analysis | `ticker.earnings_history` |
| Analyst price targets | Analysis | `ticker.analyst_price_targets` |
| Recommendations, ratings | Analysis | `ticker.recommendations` |
| Upgrades/downgrades | Analysis | `ticker.upgrades_downgrades` |
| Institutional holders | Ownership | `ticker.institutional_holders` |
| Insider transactions | Ownership | `ticker.insider_transactions` |
| Company overview, sector | General info | `ticker.info` |
| Compare multiple stocks | Bulk download | `yf.download()` |
| Screen/filter stocks | Screener | `yf.Screener` + `yf.EquityQuery` |
| Sector/industry data | Market data | `yf.Sector` / `yf.Industry` |
| News | News | `ticker.news` |
---
## Step 3: Write and Execute the Code
### General pattern
```python
import subprocess, sys
subprocess.check_call([sys.executable, "-m", "pip", "install", "-q", "yfinance"])
import yfinance as yf
ticker = yf.Ticker("AAPL")
# ... use the appropriate method from the reference
```
### Key rules
1. **Always wrap in try/except** — Yahoo Finance may rate-limit or return empty data
2. **Use `yf.download()` for multi-ticker comparisons** — it's faster with multi-threading
3. **For options, list expiration dates first** with `ticker.options` before calling `ticker.option_chain(date)`
4. **For quarterly data**, use `quarterly_` prefix: `ticker.quarterly_income_stmt`, `ticker.quarterly_balance_sheet`, `ticker.quarterly_cashflow`
5. **For large date ranges**, be mindful of intraday limits — 1m data only goes back ~7 days, 1h data ~730 days
6. **Print DataFrames clearly** — use `.to_string()` or `.to_markdown()` for readability, or select key columns
7. **Timezone handlLeer la fuente completa en GitHub (abre una página externa)