[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EB2SJD2F90EPR5T8QTVP13":3,"skill-same:01M7EB2SJD2F90EPR5T8QTVP13":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":14,"repositoryHtmlUrl":32,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M7EB2SJD2F90EPR5T8QTVP13","stock-liquidity",null,"Analyze stock liquidity using bid-ask spreads, volume profiles, order book depth, market impact estimates, and turnover ratios via Yahoo Finance data. Use this skill whenever the user asks about liquidity, trading costs, bid-ask spread, market depth, volume analysis, slippage, market impact, turnover ratio, or how easy\u002Fhard it is to trade a stock without moving the price. Triggers: \"how liquid is AAPL\", \"bid-ask spread\", \"volume analysis\", \"order book depth\", \"market impact of a large order\", \"turnover ratio\", \"slippage estimate\", \"can I trade 100k shares without moving the price\", \"liquidity comparison\", \"spread analysis\", \"ADTV\", \"Amihud illiquidity\", \"dollar volume\", \"execution cost estimate\", \"liquidity score\", penny stocks, small caps, or thinly traded securities.","Mr-Nobody-Anonymous\u002FAll-skills","Mr-Nobody-Anonymous","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F184253119?v=4","01M7AEXFJHKTYQW5R0ZCQQTWFV","anonymous","01M7C00M3GQR4QKP9GZA42GFAK",0,"MIT","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbanking\u002Fstock-liquidity\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: stock-liquidity\ndescription: >\n  Analyze stock liquidity using bid-ask spreads, volume profiles, order book depth,\n  market impact estimates, and turnover ratios via Yahoo Finance data.\n  Use this skill whenever the user asks about liquidity, trading costs, bid-ask spread,\n  market depth, volume analysis, slippage, market impact, turnover ratio, or how\n  easy\u002Fhard it is to trade a stock without moving the price.\n  Triggers: \"how liquid is AAPL\", \"bid-ask spread\", \"volume analysis\", \"order book depth\",\n  \"market impact of a large order\", \"turnover ratio\", \"slippage estimate\",\n  \"can I trade 100k shares without moving the price\", \"liquidity comparison\",\n  \"spread analysis\", \"ADTV\", \"Amihud illiquidity\", \"dollar volume\",\n  \"execution cost estimate\", \"liquidity score\", penny stocks, small caps,\n  or thinly traded securities.\nsource: \"https:\u002F\u002Fgithub.com\u002Fhimself65\u002Ffinance-skills\"\nsource_repository: \"himself65\u002Ffinance-skills\"\nsource_path: \"plugins\u002Fmarket-analysis\u002Fskills\u002Fstock-liquidity\u002FSKILL.md\"\nlicense: \"MIT\"\nimported_at: \"2026-09-20\"\n---\n\n# Stock Liquidity Analysis Skill\n\nAnalyzes 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:\u002F\u002Fgithub.com\u002Franaroussi\u002Fyfinance).\n\nLiquidity 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.\n\n**Important**: This is for research and educational purposes only. Not financial advice. yfinance is not affiliated with Yahoo, Inc.\n\n---\n\n## Step 1: Ensure Dependencies Are Available\n\n**Current environment status:**\n\n```\n!`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\\')')\"`\n```\n\nIf `DEPS_MISSING`, install required packages:\n\n```python\nimport subprocess, sys\nsubprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"-q\", \"yfinance\", \"pandas\", \"numpy\"])\n```\n\nIf already installed, skip and proceed.\n\n---\n\n## Step 2: Route to the Correct Sub-Skill\n\nClassify 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.\n\n| User Request | Route To | Examples |\n|---|---|---|\n| 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\" |\n| 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\" |\n| Volume, ADTV, dollar volume, volume profile | **Sub-Skill C: Volume Analysis** | \"volume analysis MSFT\", \"average daily volume\", \"volume profile for SPY\" |\n| Order book depth, market depth, level 2 | **Sub-Skill D: Order Book Depth** | \"order book depth for AAPL\", \"market depth\", \"show me the book\" |\n| 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\" |\n| Turnover ratio, trading activity relative to float | **Sub-Skill F: Turnover Ratio** | \"turnover ratio for GME\", \"float turnover\", \"how actively traded is this\" |\n| Compare liquidity across multiple stocks | **Sub-Skill A** (multi-ticker mode) | \"compare liquidity AAPL vs TSLA\", \"which is more liquid AMD or INTC\" |\n\n### Defaults\n\n| Parameter | Default |\n|---|---|\n| Lookback period | `3mo` (3 months) |\n| Data interval | `1d` (daily) |\n| Market impact model | Square-root model |\n| Intraday interval (when needed) | `5m` |\n\n---\n\n## Sub-Skill A: Liquidity Dashboard\n\n**Goal**: Produce a comprehensive liquidity snapshot combining all key metrics for one or more tickers.\n\n### A1: Fetch data and compute all metrics\n\n```python\nimport yfinance as yf\nimport pandas as pd\nimport numpy as np\n\ndef liquidity_dashboard(ticker_symbol, period=\"3mo\"):\n    ticker = yf.Ticker(ticker_symbol)\n    info = ticker.info\n    hist = ticker.history(period=period)\n\n    if hist.empty:\n        return None\n\n    # --- Spread metrics (from current quote) ---\n    bid = info.get(\"bid\", None)\n    ask = info.get(\"ask\", None)\n    current_price = info.get(\"currentPrice\") or info.get(\"regularMarketPrice\") or hist[\"Close\"].iloc[-1]\n\n    spread = None\n    spread_pct = None\n    if bid and ask and bid > 0 and ask > 0:\n        spread = round(ask - bid, 4)\n        midpoint = (ask + bid) \u002F 2\n        spread_pct = round((spread \u002F midpoint) * 100, 4)\n\n    # --- Volume metrics ---\n    avg_volume = hist[\"Volume\"].mean()\n    median_volume = hist[\"Volume\"].median()\n    avg_dollar_volume = (hist[\"Close\"] * hist[\"Volume\"]).mean()\n    volume_std = hist[\"Volume\"].std()\n    volume_cv = volume_std \u002F avg_volume if avg_volume > 0 else None  # coefficient of variation\n\n    # --- Turnover ratio ---\n    shares_outstanding = info.get(\"sharesOutstanding\", None)\n    float_shares = info.get(\"floatShares\", None)\n    base_shares = float_shares or shares_outstanding\n    turnover_ratio = round(avg_volume \u002F base_shares, 6) if base_shares else None\n\n    # --- Amihud illiquidity ratio ---\n    # Average of |daily return| \u002F daily dollar volume\n    returns = hist[\"Close\"].pct_change().dropna()\n    dollar_volume = (hist[\"Close\"] * hist[\"Volume\"]).iloc[1:]  # align with returns\n    amihud_values = returns.abs() \u002F dollar_volume\n    amihud = amihud_values[amihud_values.replace([np.inf, -np.inf], np.nan).notna()].mean()\n\n    # --- Market impact estimate (square-root model) ---\n    # For a hypothetical order of 1% of ADV\n    adv = avg_volume\n    order_size = adv * 0.01\n    daily_volatility = returns.std()\n    sigma = daily_volatility\n    participation_rate = order_size \u002F adv if adv > 0 else 0\n    impact_bps = sigma * np.sqrt(participation_rate) * 10000  # in basis points\n\n    return {\n        \"ticker\": ticker_symbol,\n        \"current_price\": round(current_price, 2),\n        \"bid\": bid,\n        \"ask\": ask,\n        \"spread\": spread,\n        \"spread_pct\": spread_pct,\n        \"avg_daily_volume\": int(avg_volume),\n        \"median_daily_volume\": int(median_volume),\n        \"avg_dollar_volume\": round(avg_dollar_volume, 0),\n        \"volume_cv\": round(volume_cv, 3) if volume_cv else None,\n        \"shares_outstanding\": shares_outstanding,\n        \"float_shares\": float_shares,\n        \"turnover_ratio\": turnover_ratio,\n        \"amihud_illiquidity\": round(amihud * 1e9, 4) if not np.isnan(amihud) else None,\n        \"daily_volatility\": round(daily_volatility * 100, 2),\n        \"impact_1pct_adv_bps\": round(impact_bps, 2),\n        \"observations\": len(hist),\n    }\n```\n\n### A2: Interpret and present\n\nPresent as a summary card. For the Amihud illiquidity ratio, multiply by 1e9 for readability (standard convention).\n\n**Liquidity grade** (use these rough thresholds for US equities):\n\n| Grade | Avg Dollar Volume | Spread (%) | Amihud (×10⁹) |\n|---|---|---|---|\n| Very High | > $500M\u002Fday | \u003C 0.03% | \u003C 0.01 |\n| High | $50M–$500M\u002Fday | 0.03–0.10% | 0.01–0.1 |\n| Moderate | $5M–$50M\u002Fday | 0.10–0.50% | 0.1–1.0 |\n| Low | $500K–$5M\u002Fday | 0.50–2.00% | 1.0–10 |\n| Very Low | \u003C $500K\u002Fday | > 2.00% | > 10 |\n\nWhen comparing multiple tickers, show a side-by-side table and highlight which is more liquid and why.\n\n---\n\n## Sub-Skill B: Spread Analysis\n\n**Goal**: Detailed bid-ask spread analysis including current spread, historical context from options data, and effective spread estimates.\n\n### B1: Current spread from quote\n\n```python\nimport yfinance as yf\n\ndef spread_analysis(ticker_symbol):\n    ticker = yf.Ticker(ticker_symbol)\n    info = ticker.info\n\n    bid = info.get(\"bid\", 0)\n    ask = info.get(\"ask\", 0)\n    bid_size = info.get(\"bidSize\", None)\n    ask_size = info.get(\"askSize\", None)\n    current_price = info.get(\"currentPrice\") or info.get(\"regularMarketPrice\", 0)\n\n    result = {\"bid\": bid, \"ask\": ask, \"bid_size\": bid_size, \"ask_size\": ask_size}\n\n    if bid > 0 and ask > 0:\n        midpoint = (bid + ask) \u002F 2\n        result[\"absolute_spread\"] = round(ask - bid, 4)\n        result[\"relative_spread_pct\"] = round((ask - bid) \u002F midpoint * 100, 4)\n        result[\"relative_spread_bps\"] = round((ask - bid) \u002F midpoint * 10000, 2)\n    return result\n```\n\n### B2: Options spread context\n\nOptions data from yfinance includes bid\u002Fask for each strike, which gives a sense of derivatives liquidity. Use the nearest expiration, extract near-the-money calls and puts, and compute spread and spread percentage for each.\n\nSee `references\u002Fliquidity_reference.md` § \"Options Spread Analysis\" for the full code template.\n\n### B3: Present results\n\nShow:\n- Current quoted spread (absolute, relative %, basis points)\n- Bid\u002Fask sizes if available\n- Near-the-money options spreads for context\n- How the spread compares to typical ranges for this market cap tier\n\n---\n\n## Sub-Skill C: Volume Analysis\n\n**Goal**: Analyze trading volume patterns — averages, trends, relative volume, and dollar volume.\n\n### C1: Compute volume metrics\n\n```python\nimport yfinance as yf\nimport pandas as pd\nimport numpy as np\n\ndef volume_analysis(ticker_symbol, period=\"3mo\"):\n    ticker = yf.Ticker(ticker_symbol)\n    hist = ticker.history(period=period)\n\n    if hist.empty:\n        return None\n\n    vol = hist[\"Volume\"]\n    close = hist[\"Close\"]\n    dollar_vol = vol * close\n\n    # Relative volume (today vs average)\n    rvol = vol.iloc[-1] \u002F vol.mean() if vol.mean() > 0 else None\n\n    # Volume trend (linear regression slope over the period)\n    x = np.arange(len(vol))\n    slope, _ = np.polyfit(x, vol.values, 1) if len(vol) > 1 else (0, 0)\n    trend_pct = (slope * len(vol)) \u002F vol.mean() * 100  # % change over period\n\n    # Volume profile by day of week\n    hist_copy = hist.copy()\n    hist_copy[\"DayOfWeek\"] = hist_copy.index.dayofweek\n    day_names = {0: \"Mon\", 1: \"Tue\", 2: \"Wed\", 3: \"Thu\", 4: \"Fri\"}\n    vol_by_day = hist_copy.groupby(\"DayOfWeek\")[\"Volume\"].mean()\n    vol_by_day.index = vol_by_day.index.map(day_names)\n\n    # High\u002Flow volume days\n    high_vol_days = hist.nlargest(5, \"Volume\")[[\"Close\", \"Volume\"]]\n    low_vol_days = hist.nsmallest(5, \"Volume\")[[\"Close\", \"Volume\"]]\n\n    return {\n        \"avg_volume\": int(vol.mean()),\n        \"median_volume\": int(vol.median()),\n        \"avg_dollar_volume\": round(dollar_vol.mean(), 0),\n        \"current_volume\": int(vol.iloc[-1]),\n        \"relative_volume\": round(rvol, 2) if rvol else None,\n        \"volume_trend_pct\": round(trend_pct, 1),\n        \"volume_by_day\": vol_by_day.to_dict(),\n        \"high_vol_days\": high_vol_days,\n        \"low_vol_days\": low_vol_days,\n        \"max_volume\": int(vol.max()),\n        \"min_volume\": int(vol.min()),\n    }\n```\n\n### C2: Present results\n\nShow:\n- Average daily volume (shares and dollar) with median for comparison\n- Relative volume (RVOL) — today's volume vs. the average. RVOL > 1.5 is elevated; RVOL \u003C 0.5 is unusually quiet\n- Volume trend — is trading activity increasing or declining?\n- Day-of-week pattern (if meaningful variation exists)\n- Top 5 highest-volume days with context (earnings? news?)\n\n---\n\n## Sub-Skill D: Order Book Depth\n\n**Goal**: Estimate order book depth using available bid\u002Fask data from the equity quote and options chain.\n\nYahoo Finance does not provide full Level 2 \u002F order book data. Be upfront about this limitation. What we can do:\n\n1. **Equity quote**: bid, ask, bid size, ask size (top of book only)\n2. **Options chain**: bid\u002Fask and open interest across strikes give a proxy for derivatives depth\n3. **Intraday volume distribution**: how volume is distributed within the day suggests how deep the continuous market is\n\n### D1: Gather available depth data\n\nCollect three data points:\n\n1. **Top of book** — bid, ask, bidSize, askSize from `ticker.info`\n2. **Intraday volume distribution** — 5-min bars over the last 5 days, grouped by time-of-day and normalized to percentage of daily volume\n3. **Options open interest** — total call\u002Fput OI and volume from the nearest expiration as a derivatives depth proxy\n\nSee `references\u002Fliquidity_reference.md` § \"Order Book Depth Proxy\" for the full code template.\n\n### D2: Present results\n\nShow:\n- **Top of book**: current bid\u002Fask with sizes\n- **Intraday volume shape**: where volume concentrates (open\u002Fclose vs. midday)\n- **Options depth**: total open interest and volume as a proxy for derivatives liquidity\n- **Honest limitation**: \"Yahoo Finance provides top-of-book only. For full Level 2 depth, a direct market data feed (e.g., NYSE OpenBook, NASDAQ TotalView) is needed.\"\n\n---\n\n## Sub-Skill E: Market Impact\n\n**Goal**: Estimate how much a given order size would move the price, using the square-root market impact model.\n\nThe standard model in practice is: **Impact (%) = σ × √(Q \u002F V)** where σ is daily volatility, Q is order size in shares, and V is average daily volume. This is a simplified version of the Almgren-Chriss framework used by institutional traders.\n\n### E1: Compute market impact estimate\n\n```python\nimport yfinance as yf\nimport numpy as np\n\ndef market_impact(ticker_symbol, order_shares=None, order_dollars=None, period=\"3mo\"):\n    ticker = yf.Ticker(ticker_symbol)\n    hist = ticker.history(period=period)\n    info = ticker.info\n\n    if hist.empty:\n        return None\n\n    current_price = info.get(\"currentPrice\") or hist[\"Close\"].iloc[-1]\n    avg_volume = hist[\"Volume\"].mean()\n    daily_volatility = hist[\"Close\"].pct_change().dropna().std()\n\n    # Determine order size in shares\n    if order_dollars and not order_shares:\n        order_shares = order_dollars \u002F current_price\n    elif not order_shares:\n        # Default: estimate for various sizes\n        order_shares = avg_volume * 0.01  # 1% of ADV\n\n    participation_rate = order_shares \u002F avg_volume if avg_volume > 0 else 0\n    pct_adv = (order_shares \u002F avg_volume * 100) if avg_volume > 0 else 0\n\n    # Square-root impact model\n    impact_pct = daily_volatility * np.sqrt(participation_rate) * 100\n    impact_bps = impact_pct * 100\n    impact_dollars = impact_pct \u002F 100 * current_price * order_shares\n\n    # Generate impact curve for multiple order sizes\n    sizes = [0.001, 0.005, 0.01, 0.02, 0.05, 0.10, 0.20, 0.50]  # as fraction of ADV\n    curve = []\n    for s in sizes:\n        q = avg_volume * s\n        imp = daily_volatility * np.sqrt(s) * 100\n        curve.append({\n            \"pct_adv\": round(s * 100, 1),\n            \"shares\": int(q),\n            \"dollars\": round(q * current_price, 0),\n            \"impact_bps\": round(imp * 100, 1),\n            \"impact_dollars_per_share\": round(imp \u002F 100 * current_price, 4),\n        })\n\n    return {\n        \"ticker\": ticker_symbol,\n        \"current_price\": round(current_price, 2),\n        \"avg_daily_volume\": int(avg_volume),\n        \"daily_volatility_pct\": round(daily_volatility * 100, 2),\n        \"order_shares\": int(order_shares),\n        \"order_dollars\": round(order_shares * current_price, 0),\n        \"pct_of_adv\": round(pct_adv, 2),\n        \"estimated_impact_bps\": round(impact_bps, 1),\n        \"estimated_impact_pct\": round(impact_pct, 4),\n        \"estimated_impact_total_dollars\": round(impact_dollars, 2),\n        \"impact_curve\": curve,\n    }\n```\n\n### E2: Present results\n\nShow:\n- The estimated impact for the user's specific order size\n- An impact curve table showing how cost scales with order size\n- Context: \"This uses the square-root market impact model, a standard institutional estimate. Actual impact depends on execution strategy (VWAP, TWAP, etc.), time of day, and current market conditions.\"\n- If impact > 50 bps, flag that the order is large relative to liquidity and suggest the user consider algorithmic execution or splitting the order across days\n\n---\n\n## Sub-Skill F: Turnover Ratio\n\n**Goal**: Measure how actively a stock trades relative to its shares outstanding and free float.\n\n### F1: Compute turnover metrics\n\n```python\nimport yfinance as yf\nimport pandas as pd\nimport numpy as np\n\ndef turnover_analysis(ticker_symbol, period=\"3mo\"):\n    ticker = yf.Ticker(ticker_symbol)\n    hist = ticker.history(period=period)\n    info = ticker.info\n\n    if hist.empty:\n        return None\n\n    avg_volume = hist[\"Volume\"].mean()\n    shares_outstanding = info.get(\"sharesOutstanding\")\n    float_shares = info.get(\"floatShares\")\n\n    result = {\n        \"avg_daily_volume\": int(avg_volume),\n        \"shares_outstanding\": shares_outstanding,\n        \"float_shares\": float_shares,\n    }\n\n    if shares_outstanding:\n        daily_turnover = avg_volume \u002F shares_outstanding\n        result[\"daily_turnover_ratio\"] = round(daily_turnover, 6)\n        result[\"annualized_turnover\"] = round(daily_turnover * 252, 2)\n        result[\"days_to_trade_float\"] = round(\n            (float_shares or shares_outstanding) \u002F avg_volume, 1\n        ) if avg_volume > 0 else None\n\n    if float_shares:\n        float_turnover = avg_volume \u002F float_shares\n        result[\"float_turnover_daily\"] = round(float_turnover, 6)\n        result[\"float_turnover_annualized\"] = round(float_turnover * 252, 2)\n\n    # Turnover trend\n    vol = hist[\"Volume\"]\n    base = float_shares or shares_outstanding\n    if base:\n        hist_copy = hist.copy()\n        hist_copy[\"turnover\"] = hist_copy[\"Volume\"] \u002F base\n        recent_turnover = hist_copy[\"turnover\"].tail(20).mean()\n        older_turnover = hist_copy[\"turnover\"].head(20).mean()\n        if older_turnover > 0:\n            result[\"turnover_trend_pct\"] = round(\n                (recent_turnover - older_turnover) \u002F older_turnover * 100, 1\n            )\n\n    return result\n```\n\n### F2: Present results\n\nShow:\n- Daily and annualized turnover ratios (vs. outstanding and float)\n- \"Days to trade the float\" — how many days at average volume to turn over the entire free float\n- Turnover trend — is the stock becoming more or less actively traded?\n- Context:\n\n| Turnover (Annualized) | Interpretation |\n|---|---|\n| > 500% | Extremely active — likely speculative or momentum-driven |\n| 100–500% | Actively traded |\n| 30–100% | Moderate activity |\n| \u003C 30% | Thinly traded — likely institutional buy-and-hold or neglected |\n\n---\n\n## Step 3: Respond to the User\n\nAfter running the appropriate sub-skill:\n\n### Always include\n\n- The **lookback period** used for historical metrics\n- The **data timestamp** — spreads and quotes are snapshots, not real-time\n- Any tickers that returned **empty data** (invalid symbol, delisted, etc.)\n\n### Always caveat\n\n- Yahoo Finance quote data has a **15-minute delay** for most exchanges — spreads shown may not reflect the current live market\n- Full order book (Level 2) data is **not available** through Yahoo Finance\n- Market impact estimates are **models, not guarantees** — actual execution costs depend on strategy, timing, and market conditions\n- Liquidity can **change rapidly** — a stock that's liquid today may not be tomorrow (especially around events, halts, or during extended hours)\n\n### Practical guidance (mention when relevant)\n\n- **Position sizing**: If estimated impact exceeds 25 bps, the position may be too large for the stock's liquidity\n- **Small\u002Fmicro-cap warning**: Stocks with \u003C $1M daily dollar volume require careful execution\n- **Spread costs compound**: A 0.10% spread on a round-trip (buy + sell) costs 0.20% — this adds up for active strategies\n- **Illiquidity premium**: Less liquid stocks historically earn higher returns as compensation — but the transaction costs can eat this premium\n\n**Important**: Never recommend specific trades. Present liquidity data and let the user make their own decisions.\n\n---\n\n## Reference Files\n\n- `references\u002Fliquidity_reference.md` — Detailed formulas, extended code templates, metric interpretation guides, and academic references for all liquidity measures\n\nRead the reference file when you need exact formulas, edge case handling, or deeper background on liquidity metrics.\n","# Stock Liquidity Analysis Skill\n\nAnalyzes 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:\u002F\u002Fgithub.com\u002Franaroussi\u002Fyfinance).\n\nLiquidity 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.\n\n**Important**: This is for research and educational purposes only. Not financial advice. yfinance is not affiliated with Yahoo, Inc.\n\n---\n\n## Step 1: Ensure Dependencies Are Available\n\n**Current environment status:**\n\n```\n!`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\\')')\"`\n```\n\nIf `DEPS_MISSING`, install required packages:\n\n```python\nimport subprocess, sys\nsubprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"-q\", \"yfinance\", \"pandas\", \"numpy\"])\n```\n\nIf already installed, skip and proceed.\n\n---\n\n## Step 2: Route to the Correct Sub-Skill\n\nClassify 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.\n\n| User Request | Route To | Examples |\n|---|---|---|\n| 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\" |\n| 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\" |\n| Volume, ADTV, dollar volume, volume profile | **Sub-Skill C: Volume Analysis** | \"volume analysis MSFT\", \"average daily volume\", \"volume profile for SPY\" |\n| Order book depth, market depth, level 2 | **Sub-Skill D: Order Book Depth** | \"order book depth for AAPL\", \"market depth\", \"show me the book\" |\n| 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\" |\n| Turnover ratio, trading activity relative to float | **Sub-Skill F: Turnover Ratio** | \"turnover ratio for GME\", \"float turnover\", \"how actively traded is this\" |\n| Compare liquidity across multiple stocks | **Sub-Skill A** (multi-ticker mode) | \"compare liquidity AAPL vs TSLA\", \"which is more liquid AMD or INTC\" |\n\n### Defaults\n\n| Parameter | Default |\n|---|---|\n| Lookback period | `3mo` (3 months) |\n| Data interval | `1d` (daily) |\n| Market impact model | Square-root model |\n| Intraday interval (when needed) | `5m` |\n\n---\n\n## Sub-Skill A: Liquidity Dashboard\n\n**Goal**: Produce a comprehensive liquidity snapshot combining all key metrics for one or more tickers.\n\n### A1: Fetch data and compute all metrics\n\n```python\nimport yfinance as yf\nimport pandas as pd\nimport numpy as np\n\ndef liquidity_dashboard(ticker_symbol, period=\"3mo\"):\n    ticker = yf.Ticker(ticker_symbol)\n    info = ticker.info\n    hist = ticker.history(period=period)\n\n    if hist.empty:\n        return None\n\n    # --- Spread metrics (from current quote) ---\n    bid = info.get(\"bid\", None)\n    ask = info.get(\"ask\", None)\n    current_price = info.get(\"currentPrice\") or info.get(\"regularMarketPrice\") or hist[\"Close\"].iloc[-1]\n\n    spread = None\n    spread_pct = None\n    if bid and ask and bid > 0 and ask > 0:\n        spread = round(ask - bid, 4)\n        midpoint = (ask + bid) \u002F 2\n        spread_pct = round((spread \u002F midpoint) * 100, 4)\n\n    # --- Volume metrics ---\n    avg_volume = hist[\"Volume\"].mean()\n    median_volume = hist[\"Volume\"].median()\n    avg_dollar_volume = (hist[\"Close\"] * hist[\"Volume\"]).mean()\n    volume_std = hist[\"Volume\"].std()\n    volume_cv = volume_std \u002F avg_volume if avg_volume > 0 else None  # coefficient of variation\n\n    # --- Turnover ratio ---\n    shares_outstanding = info.get(\"sharesOutstanding\", None)\n    float_shares = info.get(\"floatShares\", None)\n    base_shares = float_shares or shares_outstanding\n    turnover_ratio = round(avg_volume \u002F base_shares, 6) if base_shares else None\n\n    # --- Amihud illiquidity ratio ---\n    # Average of |daily return| \u002F daily dollar volume\n    returns = hist[\"Close\"].pct_change().dropna()\n    dollar_volume = (hist[\"Close\"] * hist[\"Volume\"]).iloc[1:]  # align with returns\n    amihud_values = returns.abs() \u002F dollar_volume\n    amihud = amihud_values[amihud_values.replace([np.inf, -np.inf], np.nan).notna()].mean()\n\n    # --- Market impact estimate (square-root model) ---\n    # For a hypothetical order of 1% of ADV\n    adv = avg_volume\n    order_size = adv * 0.01\n    daily_volatility = returns.std()\n    sigma = daily_volatility\n    participation_rate = order_size \u002F adv if adv > 0 else 0\n    impact_bps = sigma * np.sqrt(participation_rate) * 10000  # in basis points\n\n    return {\n        \"ticker\": ticker_symbol,\n        \"current_price\": round(current_price, 2),\n        \"bid\": bid,\n        \"ask\": ask,\n        \"spread\": spread,\n        \"spread_pct\": spread_pct,\n        \"avg_daily_volume\": int(avg_volume),\n        \"median_daily_volume\": int(median_volume),\n        \"avg_dollar_volume\": round(avg_dollar_volume, 0),\n        \"volume_cv\": round(volume_cv, 3) if volume_cv else None,\n        \"shares_outstanding\": shares_outstanding,\n        \"float_shares\": float_shares,\n        \"turnover_ratio\": turnover_ratio,\n        \"amihud_illiquidity\": round(amihud * 1e9, 4) if not np.isnan(amihud) else None,\n        \"daily_volatility\": round(daily_volatility * 100, 2),\n        \"impact_1pct_adv_bps\": round(impact_bps, 2),\n        \"observations\": len(hist),\n    }\n```\n\n### A2: Interpret and present\n\nPresent as a summary card. For the Amihud illiquidity ratio, multiply by 1e9 for readability (standard convention).\n\n**Liquidity grade** (use these rough thresholds for US equities):\n\n| Grade | Avg Dollar Volume | Spread (%) | Amihud (×10⁹) |\n|---|---|---|---|\n| Very High | > $500M\u002Fday | \u003C 0.03% | \u003C 0.01 |\n| High | $50M–$500M\u002Fday | 0.03–0.10% | 0.01–0.1 |\n| Moderate | $5M–$50M\u002Fday | 0.10–0.50% | 0.1–1.0 |\n| Low | $500K–$5M\u002Fday | 0.50–2.00% | 1.0–10 |\n| Very Low | \u003C $500K\u002Fday | > 2.00% | > 10 |\n\nWhen comparing multiple tickers, show a side-by-side table and highlight which is more liquid and why.\n\n---\n\n## Sub-Skill B: Spread Analysis\n\n**Goal**: Detailed bid-ask spread analysis including current spread, historical context from options data, and effective spread estimates.\n\n### B1: Current spread from quote\n\n```python\nimport yfinance as yf\n\ndef spread_analysis(ticker_symbol):\n    ticker = yf.Ticker(ticker_symbol)\n    info = ticker.info\n\n    bid = info.get(\"bid\", 0)\n    ask = info.get(\"ask\", 0)\n    bid_size = info.get(\"bidSize\", None)\n    ask_size = info.get(\"askSize\", None)\n    current_price = info.get(\"currentPrice\") or info.get(\"regularMarketPrice\", 0)\n\n    result = {\"bid\": bid, \"ask\": ask, \"bid_size\": bid_size, \"ask_size\": ask_size}\n\n    if bid > 0 and ask > 0:\n        midpoint = (bid + ask) \u002F 2\n        result[\"absolute_spread\"] = round(ask - bid, 4)\n        result[\"relative_spread_pct\"] = round((ask - bid) \u002F midpoint * 100, 4)\n        result[\"relative_spread_bps\"] = round((ask - bid) \u002F midpoint * 10000, 2)\n    return result\n```\n\n### B2: Options spread context\n\nOptions data from yfinance includes bid\u002Fask for each strike, which gives a sense of derivatives liquidity. Use the nearest expiration, extract near-the-money calls and puts, and compute spread and spread percentage for each.\n\nSee `references\u002Fliquidity_reference.md` § \"Options Spread Analysis\" for the full code template.\n\n### B3: Present results\n\nShow:\n- Current quoted spread (absolute, relative %, basis points)\n- Bid\u002Fask sizes if available\n- Near-the-money options spreads for context\n- How the spread compares to typical ranges for this market cap tier\n\n---\n\n## Sub-Skill C: Volume Analysis\n\n**Goal**: Analyze trading volume patterns — averages, trends, relative volume, and dollar volume.\n\n### C1: Compute volume metrics\n\n```python\nimport yfinance as yf\nimport pandas as pd\nimport numpy as np\n\ndef volume_analysis(ticker_symbol, period=\"3mo\"):\n    ticker = yf.Ticker(ticker_symbol)\n    hist = ticker.history(period=period)\n\n    if hist.empty:\n        return None\n\n    vol = hist[\"Volume\"]\n    close = hist[\"Close\"]\n    dollar_vol = vol * close\n\n    # Relative volume (today vs average)\n    rvol = vol.iloc[-1] \u002F vol.mean() if vol.mean() > 0 else None\n\n    # Volume trend (linear regression slope over the period)\n    x = np.arange(len(vol))\n    slope, _ = np.polyfit(x, vol.values, 1) if len(vol) > 1 else (0, 0)\n    trend_pct = (slope * len(vol)) \u002F vol.mean() * 100  # % change over period\n\n    # Volume profile by day of week\n    hist_copy = hist.copy()\n    hist_copy[\"DayOfWeek\"] = hist_copy.index.dayofweek\n    day_names = {0: \"Mon\", 1: \"Tue\", 2: \"Wed\", 3: \"Thu\", 4: \"Fri\"}\n    vol_by_day = hist_copy.groupby(\"DayOfWeek\")[\"Volume\"].mean()\n    vol_by_day.index = vol_by_day.index.map(day_names)\n\n    # High\u002Flow volume days\n    high_vol_days = hist.nlargest(5, \"Volume\")[[\"Close\", \"Volume\"]]\n    low_vol_days = hist.nsmallest(5, \"Volume\")[[\"Close\", \"Volume\"]]\n\n    return {\n        \"avg_volume\": int(vol.mean()),\n        \"median_volume\": int(vol.median()),\n        \"avg_dollar_volume\": round(dollar_vol.mean(), 0),\n        \"current_volume\": int(vol.iloc[-1]),\n        \"relative_volume\": round(rvol, 2) if rvol else None,\n        \"volume_trend_pct\": round(trend_pct, 1),\n        \"volume_by_day\": vol_by_day.to_dict(),\n        \"high_vol_days\": high_vol_days,\n        \"low_vol_days\": low_vol_days,\n        \"max_volume\": int(vol.max()),\n        \"min_volume\": int(vol.min()),\n    }\n```\n\n### C2: Present results\n\nShow:\n- Average daily volume (shares and dollar) with median for comparison\n- Relative volume (RVOL) — today's volume vs. the average. RVOL > 1.5 is elevated; RVOL \u003C 0.5 is unusually quiet\n- Volume trend — is trading activity increasing or declining?\n- Day-of-week pattern (if meaningful variation exists)\n- Top 5 highest-volume days with context (earnings? news?)\n\n---\n\n## Sub-Skill D: Order Book Depth\n\n**Goal**: Estimate order book depth using available bid\u002Fask data from the equity quote and options chain.\n\nYahoo Finance does not provide full Level 2 \u002F order book data. Be upfront about this limitation. What we can do:\n\n1. **Equity quote**: bid, ask, bid size, ask size (top of book only)\n2. **Options chain**: bid\u002Fask and open interest across strikes give a proxy for derivatives depth\n3. **Intraday volume distribution**: how volume is distributed within the day suggests how deep the continuous market is\n\n### D1: Gather available depth data\n\nCollect three data points:\n\n1. **Top of book** — bid, ask, bidSize, askSize from `ticker.info`\n2. **Intraday volume distribution** — 5-min bars over the last 5 days, grouped by time-of-day and normalized to percentage of daily volume\n3. **Options open interest** — total call\u002Fput OI and volume from the nearest expiration as a derivatives depth proxy\n\nSee `references\u002Fliquidity_reference.md` § \"Order Book Depth Proxy\" for the full code template.\n\n### D2: Present results\n\nShow:\n- **Top of book**: current bid\u002Fask with sizes\n- **Intraday volume shape**: where volume concentrates (open\u002Fclose vs. midday)\n- **Options depth**: total open interest and volume as a proxy for derivatives liquidity\n- **Honest limitation**: \"Yahoo Finance provides top-of-book only. For full Level 2 depth, a direct market data feed (e.g., NYSE OpenBook, NASDAQ TotalView) is needed.\"\n\n---\n\n## Sub-Skill E: Market Impact\n\n**Goal**: Estimate how much a given order size would move the price, using the square-root market impact model.\n\nThe standard model in practice is: **Impact (%) = σ × √(Q \u002F V)** where σ is daily volatility, Q is order size in shares, and V is average daily volume. This is a simplified version of the Almgren-Chriss framework used by institutional traders.\n\n### E1: Compute market impact estimate\n\n```python\nimport yfinance as yf\nimport numpy as np\n\ndef market_impact(ticker_symbol, order_shares=None, order_dollars=None, period=\"3mo\"):\n    ticker = yf.Ticker(ticker_symbol)\n    hist = ticker.history(period=period)\n    info = ticker.info\n\n    if hist.empty:\n        return None\n\n    current_price = info.get(\"currentPrice\") or hist[\"Close\"].iloc[-1]\n    avg_volume = hist[\"Volume\"].mean()\n    daily_volatility = hist[\"Close\"].pct_change().dropna().std()\n\n    # Determine order size in shares\n    if order_dollars and not order_shares:\n        order_shares = order_dollars \u002F current_price\n    elif not order_shares:\n        # Default: estimate for various sizes\n        order_shares = avg_volume * 0.01  # 1% of ADV\n\n    participation_rate = order_shares \u002F avg_volume if avg_volume > 0 else 0\n    pct_adv = (order_shares \u002F avg_volume * 100) if avg_volume > 0 else 0\n\n    # Square-root impact model\n    impact_pct = daily_volatility * np.sqrt(participation_rate) * 100\n    impact_bps = impact_pct * 100\n    impact_dollars = impact_pct \u002F 100 * current_price * order_shares\n\n    # Generate impact curve for multiple order sizes\n    sizes = [0.001, 0.005, 0.01, 0.02, 0.05, 0.10, 0.20, 0.50]  # as fraction of ADV\n    curve = []\n    for s in sizes:\n        q = avg_volume * s\n        imp = daily_volatility * np.sqrt(s) * 100\n        curve.append({\n            \"pct_adv\": round(s * 100, 1),\n            \"shares\": int(q),\n            \"dollars\": round(q * current_price, 0),\n            \"impact_bps\": round(imp * 100, 1),\n            \"impact_dollars_per_share\": round(imp \u002F 100 * current_price, 4),\n        })\n\n    return {\n        \"ticker\": ticker_symbol,\n        \"current_price\": round(current_price, 2),\n        \"avg_daily_volume\": int(avg_volume),\n        \"daily_volatility_pct\": round(daily_volatility * 100, 2),\n        \"order_shares\": int(order_shares),\n        \"order_dollars\": round(order_shares * current_price, 0),\n        \"pct_of_adv\": round(pct_adv, 2),\n        \"estimated_impact_bps\": round(impact_bps, 1),\n        \"estimated_impact_pct\": round(impact_pct, 4),\n        \"estimated_impact_total_dollars\": round(impact_dollars, 2),\n        \"impact_curve\": curve,\n    }\n```\n\n### E2: Present results\n\nShow:\n- The estimated impact for the user's specific order size\n- An impact curve table showing how cost scales with order size\n- Context: \"This uses the square-root market impact model, a standard institutional estimate. Actual impact depends on execution strategy (VWAP, TWAP, etc.), time of day, and current market conditions.\"\n- If impact > 50 bps, flag that the order is large relative to liquidity and suggest the user consider algorithmic execution or splitting the order across days\n\n---\n\n## Sub-Skill F: Turnover Ratio\n\n**Goal**: Measure how actively a stock trades relative to its shares outstanding and free float.\n\n### F1: Compute turnover metrics\n\n```python\nimport yfinance as yf\nimport pandas as pd\nimport numpy as np\n\ndef turnover_analysis(ticker_symbol, period=\"3mo\"):\n    ticker = yf.Ticker(ticker_symbol)\n    hist = ticker.history(period=period)\n    info = ticker.info\n\n    if hist.empty:\n        return None\n\n    avg_volume = hist[\"Volume\"].mean()\n    shares_outstanding = info.get(\"sharesOutstanding\")\n    float_shares = info.get(\"floatShares\")\n\n    result = {\n        \"avg_daily_volume\": int(avg_volume),\n        \"shares_outstanding\": shares_outstanding,\n        \"float_shares\": float_shares,\n    }\n\n    if shares_outstanding:\n        daily_turnover = avg_volume \u002F shares_outstanding\n        result[\"daily_turnover_ratio\"] = round(daily_turnover, 6)\n        result[\"annualized_turnover\"] = round(daily_turnover * 252, 2)\n        result[\"days_to_trade_float\"] = round(\n            (float_shares or shares_outstanding) \u002F avg_volume, 1\n        ) if avg_volume > 0 else None\n\n    if float_shares:\n        float_turnover = avg_volume \u002F float_shares\n        result[\"float_turnover_daily\"] = round(float_turnover, 6)\n        result[\"float_turnover_annualized\"] = round(float_turnover * 252, 2)\n\n    # Turnover trend\n    vol = hist[\"Volume\"]\n    base = float_shares or shares_outstanding\n    if base:\n        hist_copy = hist.copy()\n        hist_copy[\"turnover\"] = hist_copy[\"Volume\"] \u002F base\n        recent_turnover = hist_copy[\"turnover\"].tail(20).mean()\n        older_turnover = hist_copy[\"turnover\"].head(20).mean()\n        if older_turnover > 0:\n            result[\"turnover_trend_pct\"] = round(\n                (recent_turnover - older_turnover) \u002F older_turnover * 100, 1\n            )\n\n    return result\n```\n\n### F2: Present results\n\nShow:\n- Daily and annualized turnover ratios (vs. outstanding and float)\n- \"Days to trade the float\" — how many days at average volume to turn over the entire free float\n- Turnover trend — is the stock becoming more or less actively traded?\n- Context:\n\n| Turnover (Annualized) | Interpretation |\n|---|---|\n| > 500% | Extremely active — likely speculative or momentum-driven |\n| 100–500% | Actively traded |\n| 30–100% | Moderate activity |\n| \u003C 30% | Thinly traded — likely institutional buy-and-hold or neglected |\n\n---\n\n## Step 3: Respond to the User\n\nAfter running the appropriate sub-skill:\n\n### Always include\n\n- The **lookback period** used for historical metrics\n- The **data timestamp** — spreads and quotes are snapshots, not real-time\n- Any tickers that returned **empty data** (invalid symbol, delisted, etc.)\n\n### Always caveat\n\n- Yahoo Finance quote data has a **15-minute delay** for most exchanges — spreads shown may not reflect the current live market\n- Full order book (Level 2) data is **not available** through Yahoo Finance\n- Market impact estimates are **models, not guarantees** — actual execution costs depend on strategy, timing, and market conditions\n- Liquidity can **change rapidly** — a stock that's liquid today may not be tomorrow (especially around events, halts, or during extended hours)\n\n### Practical guidance (mention when relevant)\n\n- **Position sizing**: If estimated impact exceeds 25 bps, the position may be too large for the stock's liquidity\n- **Small\u002Fmicro-cap warning**: Stocks with \u003C $1M daily dollar volume require careful execution\n- **Spread costs compound**: A 0.10% spread on a round-trip (buy + sell) costs 0.20% — this adds up for active strategies\n- **Illiquidity premium**: Less liquid stocks historically earn higher returns as compensation — but the transaction costs can eat this premium\n\n**Important**: Never recommend specific trades. Present liquidity data and let the user make their own decisions.\n\n---\n\n## Reference Files\n\n- `references\u002Fliquidity_reference.md` — Detailed formulas, extended code templates, metric interpretation guides, and academic references for all liquidity measures\n\nRead the reference file when you need exact formulas, edge case handling, or deeper background on liquidity metrics.\n",{"name":5,"source":24,"license":15,"description":25,"imported_at":26,"source_path":27,"source_repository":28},"https:\u002F\u002Fgithub.com\u002Fhimself65\u002Ffinance-skills","Analyze stock liquidity using bid-ask spreads, volume profiles, order book depth, market impact estimates, and turnover ratios via Yahoo Finance data. Use this skill whenever the user asks about liquidity, trading costs, bid-ask spread, market depth, volume analysis, slippage, market impact, turnover ratio, or how easy\u002Fhard it is to trade a stock without moving the price. Triggers: \"how liquid is AAPL\", \"bid-ask spread\", \"volume analysis\", \"order book depth\", \"market impact of a large order\", \"turnover ratio\", \"slippage estimate\", \"can I trade 100k shares without moving the price\", \"liquidity comparison\", \"spread analysis\", \"ADTV\", \"Amihud illiquidity\", \"dollar volume\", \"execution cost estimate\", \"liquidity score\", penny stocks, small caps, or thinly traded securities.\n","2026-09-20","plugins\u002Fmarket-analysis\u002Fskills\u002Fstock-liquidity\u002FSKILL.md","himself65\u002Ffinance-skills","main","2d1750717747097b602acf30bd09a7cbd4b4c6ea","awesome_skills\u002Fbanking\u002Fstock-liquidity","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous","2026-11-09 11:45:36",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill stock-liquidity",{"tool":41,"command":42},"bunx","bunx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill stock-liquidity",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill stock-liquidity","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbanking\u002Fstock-liquidity\u002FSKILL.md",true,[49],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"README.md","REFERENCE","参考文档",1476,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbanking\u002Fstock-liquidity\u002FREADME.md",[56,64,71,78,85,92],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":63},"01M7FFFZPC2025JQQHPHDX154J","dei-assessment","Assess diversity, equity, and inclusion with metrics. TRIGGERS - Use when user needs help with dei-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-assessment\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":63},"01M7FFFWN8H4WA7A6Y398QKB6J","dei-action-plan","Create DEI action plans with goals and initiatives. TRIGGERS - Use when user needs help with dei-action-plan related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-action-plan\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":63},"01M7FFFSHTM0QZRVZ2NRJTJ0PY","culture-fit-assessment","Design culture add assessment processes. TRIGGERS - Use when user needs help with culture-fit-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fculture-fit-assessment\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":63},"01M7FFFMA12RKEQA38KHJSXXPS","cowork-to-code-bridge","Use an already-installed, independently verified cowork-to-code bridge to run narrowly approved actions on the user's own macOS, Linux, or WSL2 machine through a local file queue.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcowork-to-code-bridge\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":63},"01M7FFFH1F6M8YRGW5V487GH1K","counter-offer-response","Draft counter-offer responses for retention. TRIGGERS - Use when user needs help with counter-offer-response related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcounter-offer-response\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":63},"01M7FFFDGEHV8Y7J9N40HZXW52","continuous-feedback-system","Design continuous feedback systems. TRIGGERS - Use when user needs help with continuous-feedback-system related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcontinuous-feedback-system\u002FSKILL.md",[],[]]