Financial Data Analysis

What it does

When your agent uses it

• Tasks that involve Data analysis

Example prompts

• “Use the financial-data-analysis skill to method for acquiring, cleaning, and analyzing financial datasets for research”
• “/financial-data-analysis”

Requirements

• Python 3
• A credential in FRED_API_KEY

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Define the event window (e.g., [-5, +5] trading days around earnings announcement)
2. 2Estimate normal returns using the market model over the estimation window (e.g., [-250, -30])
3. 3Compute abnormal returns: AR = R_actual - R_expected
4. 4Aggregate cumulative abnormal returns (CAR) across firms
5. 5Test statistical significance using parametric (Patell test) and non-parametric (sign test) methods

What it can do on your machine

Read from SKILL.md and the folder at commit bf44b3c. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • FRED_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Financial Data Analysis loads about 1.3k tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 222 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~26

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from wentorai/research-plugins at commit bf44b3c, republished under its MIT licence (© wentorai). 222 words, ~1,278 tokens.

name

financial-data-analysis

description

Methods for acquiring, cleaning, and analyzing financial datasets for research

import yfinance as yf
import pandas as pd

def fetch_stock_data(tickers: list[str], start: str, end: str) -> pd.DataFrame:
    """
    Fetch adjusted close prices for a list of tickers.

    Args:
        tickers: List of ticker symbols (e.g., ['AAPL', 'MSFT'])
        start: Start date (YYYY-MM-DD)
        end: End date (YYYY-MM-DD)
    Returns:
        DataFrame with adjusted close prices
    """
    data = yf.download(tickers, start=start, end=end, auto_adjust=True)
    prices = data['Close'] if len(tickers) > 1 else data[['Close']]
    prices.columns = tickers if len(tickers) > 1 else tickers
    return prices

# Fetch 5 years of data
prices = fetch_stock_data(['AAPL', 'MSFT', 'GOOGL'], '2020-01-01', '2025-01-01')
print(prices.head())

from fredapi import Fred

fred = Fred(api_key=os.environ["FRED_API_KEY"])

# Common series for finance research
series_ids = {
    'GDP': 'GDP',
    'CPI': 'CPIAUCSL',
    'Fed_Funds_Rate': 'FEDFUNDS',
    'Unemployment': 'UNRATE',
    '10Y_Treasury': 'DGS10',
    'VIX': 'VIXCLS'
}

macro_data = pd.DataFrame()
for name, sid in series_ids.items():
    macro_data[name] = fred.get_series(sid, observation_start='2000-01-01')

def clean_financial_data(df: pd.DataFrame) -> pd.DataFrame:
    """Standard cleaning pipeline for financial time series."""
    cleaned = df.copy()

    # 1. Handle missing values
    missing_pct = cleaned.isnull().sum() / len(cleaned) * 100
    print(f"Missing data:\n{missing_pct}")

    # 2. Forward-fill for market holidays (max 5 days)
    cleaned = cleaned.ffill(limit=5)

    # 3. Remove remaining NaN rows
    cleaned = cleaned.dropna()

    # 4. Detect and flag outliers (>5 sigma daily returns)
    returns = cleaned.pct_change()
    z_scores = (returns - returns.mean()) / returns.std()
    outliers = (z_scores.abs() > 5).any(axis=1)
    print(f"Outlier days flagged: {outliers.sum()}")

    # 5. Verify data integrity
    assert cleaned.index.is_monotonic_increasing, "Index must be sorted"
    assert not cleaned.duplicated().any(), "No duplicate rows allowed"

    return cleaned

def compute_returns(prices: pd.DataFrame) -> dict:
    """Compute standard return metrics."""
    simple_returns = prices.pct_change().dropna()
    log_returns = np.log(prices / prices.shift(1)).dropna()

    annualized_return = simple_returns.mean() * 252
    annualized_vol = simple_returns.std() * np.sqrt(252)
    sharpe_ratio = annualized_return / annualized_vol

    # Maximum drawdown
    cumulative = (1 + simple_returns).cumprod()
    rolling_max = cumulative.cummax()
    drawdown = (cumulative - rolling_max) / rolling_max
    max_drawdown = drawdown.min()

    return {
        'annualized_return': annualized_return,
        'annualized_volatility': annualized_vol,
        'sharpe_ratio': sharpe_ratio,
        'max_drawdown': max_drawdown
    }

© wentorai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/domains/finance/financial-data-analysis of wentorai/research-plugins.

Open the folder on GitHubat commit bf44b3c

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in wentorai/research-plugins, which our catalogue first saw on October 7, 2026.

• brycewang-stanford/Auto-Empirical-Research-Skillsskills/43-wentorai-research-plugins/skills/domains/finance/financial-data-analysis