Stock LiquiditySAFE

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: stock-liquidity
description: >
  Analyze how liquid a stock is using Yahoo Finance data (yfinance): bid-ask spreads,
  volume and dollar volume (ADTV), top-of-book and options depth, square-root market
  impact and slippage estimates, turnover ratio, and Amihud illiquidity, rolled into a
  liquidity grade. Use this skill whenever the user asks about liquidity or trading
  costs — how easily a position can be entered or exited, what a large order would do
  to the price, spread or execution-cost estimates, order book depth, volume patterns,
  or liquidity comparisons — especially for small caps, penny stocks, and thinly
  traded names.
---

# Stock Liquidity Analysis Skill

Analyzes stock liquidity across multiple dimensions — bid-ask spreads, volume patterns, order book depth, estimated market impact, and turnover ratios — using data from Yahoo Finance via [yfinance](https://github.com/ranaroussi/yfinance).

Liquidity matters because it determines the real cost of trading. The quoted price is not what you actually pay — spreads, slippage, and market impact all eat into returns, especially for larger positions or less liquid names.

**Important**: This is for research and educational purposes only. Not financial advice. yfinance is not affiliated with Yahoo, Inc.

---

## Step 1: Ensure Dependencies Are Available

**Current environment status:**

```
!`python3 -c "exec('try:\n import yfinance, pandas, numpy\n print(f\'yfinance={yfinance.__version__} pandas={pandas.__version__} numpy={numpy.__version__}\')\nexcept Exception:\n print(\'DEPS_MISSING\')')"`
```

If `DEPS_MISSING`, install required packages:

```python
import subprocess, sys
subprocess.check_call([sys.executable, "-m", "pip", "install", "-q", "yfinance", "pandas", "numpy"])
```

If already installed, skip and proceed.

---

## Step 2: Route to the Correct Sub-Skill

Classify the user's request and jump to the matching section. If the user asks for a general liquidity assessment without specifying a particular metric, run **Sub-Skill A** (Liquidity Dashboard) which computes all key metrics together.

| User Request | Route To | Examples |
|---|---|---|
| General liquidity check, "how liquid is X" | **Sub-Skill A: Liquidity Dashboard** | "how liquid is AAPL", "liquidity analysis for TSLA", "is this stock liquid enough" |
| Bid-ask spread, trading costs, effective spread | **Sub-Skill B: Spread Analysis** | "bid-ask spread for AMD", "what's the spread on NVDA options", "trading cost estimate" |
| Volume, ADTV, dollar volume, volume profile | **Sub-Skill C: Volume Analysis** | "volume analysis MSFT", "average daily volume", "volume profile for SPY" |
| Order book depth, market depth, level 2 | **Sub-Skill D: Order Book Depth** | "order book depth for AAPL", "market depth", "show me the book" |
| Market impact, slippage, execution cost for large orders | **Sub-Skill E: Market Impact** | "how much would 50k shares move the price", "slippage estimate", "market impact of $1M order" |
| Turnover ratio, trading activity relative to float | **Sub-Skill F: Turnover Ratio** | "turnover ratio for GME", "float turnover", "how actively traded is this" |
| Compare liquidity across multiple stocks | **Sub-Skill A** (multi-ticker mode) | "compare liquidity AAPL vs TSLA", "which is more liquid AMD or INTC" |

### Defaults

| Parameter | Default |
|---|---|
| Lookback period | `3mo` (3 months) |
| Data interval | `1d` (daily) |
| Market impact model | Square-root model |
| Intraday interval (when needed) | `5m` |

---

## Sub-Skill A: Liquidity Dashboard

**Goal**: Produce a comprehensive liquidity snapshot combining all key metrics for one or more tickers.

### A1: Fetch data and compute all metrics

```python
import yfinance as yf
import pandas as pd
import numpy as np

def liquidity_dashboard(ticker_symbol, period="3mo"):
    ticker = yf.Ticker(ticker_symbol)
    info = ticker.info
    hist = ticker.history(period=period)

    if hist.empty:
        return None

    # --- Spread metrics (from current quote) ---
    bid = info.get("bid", None)
    ask = info.get("ask", None)
    current_price = info.get("currentPrice") or info.get("regularMarketPrice") or hist["Close"].iloc[-1]

    spread = None
    spread_pct = None
    if bid and ask and bid > 0 and ask > 0:
        spread = round(ask - bid, 4)
        midpoint = (ask + bid) / 2
        spread_pct = round((spread / midpoint) * 100, 4)

    # --- Volume metrics ---
    avg_volume = hist["Volume"].mean()
    median_volume = hist["Volume"].median()
    avg_dollar_volume = (hist["Close"] * hist["Volume"]).mean()
    volume_std = hist["Volume"].std()
    volume_cv = volume_std / avg_volume if avg_volume > 0 else None  # coefficient of variation

    # --- Turnover ratio ---
    shares_outstanding = info.get("sharesOutstanding", None)
    float_shares = info.get("floatShares", None)
    base_shares = float_shares or shares_outstanding
    turnover_ratio = round(avg_volume / base_shares, 6) if base_shares else None

    # --- Amihud illiquidity ratio ---
    # Average of |daily return| / daily dollar volume
    returns = hist["Close"].pct_change().dropna()
    dollar_volume = (hist["Close"] * hist["Volume"]).iloc[1:]  # align with returns
    amihud_values = returns.abs() / dollar_volume
    amihud = amihud_values[amihud_values.replace([np.inf, -np.inf], np.nan).notna()].mean()

    # --- Market impact estimate (square-root model) ---
    # For a hypothetical order of 1% of ADV
    adv = avg_volume
    order_size = adv * 0.01
    daily_volatility = returns.std()
    sigma = daily_volatility
    participation_rate = order_size / adv if adv > 0 else 0
    impact_bps = sigma * np.sqrt(participation_rate) * 10000  # in basis points

    return {
        "ticker": ticker_symbol,
        "current_price": round(current_price, 2),
        "bid": bid,
        "ask": ask,
        "spread": spread,
        "spread_pct": spread_pct,
        "avg_daily_volume": int(avg_volume),
        "median_daily_vo

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.