[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D7CS69KFKB5WMHRK8FK55W":3,"skill-same:01M7D7CS69KFKB5WMHRK8FK55W":67},{"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":45,"commitSha":46,"skillDirectory":47,"forksCount":14,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M7D7CS69KFKB5WMHRK8FK55W","comps-analysis",null,"Build comparable company analysis in Excel — operating metrics, valuation multiples, statistical benchmarking vs peer sets. Pairs with excel-author. Use for public-company valuation, IPO pricing, sector benchmarking, or outlier detection.","GrupoANDevelopment-m\u002Falberto-ai","GrupoANDevelopment-m","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F257455179?v=4","01M7D69X2N2KEVN0SJF6WGM6SH","Antônio  Ndombe","01M7D69X3P5JTT8H8S904N3888",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Foptional\u002Ffinance\u002Fcomps-analysis\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: comps-analysis\ndescription: Build comparable company analysis in Excel — operating metrics, valuation multiples, statistical benchmarking vs peer sets. Pairs with excel-author. Use for public-company valuation, IPO pricing, sector benchmarking, or outlier detection.\nversion: 1.0.0\nauthor: Anthropic (adapted by Nous Research)\nlicense: Apache-2.0\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [finance, valuation, comps, excel, openpyxl, modeling, investment-banking]\n    related_skills: [excel-author, pptx-author, dcf-model, lbo-model]\n---\n\n## Environment\n\nThis skill assumes **headless openpyxl** — you are producing an .xlsx file on disk.\nFollow the `excel-author` skill's conventions for cell coloring, formulas, named ranges, and sensitivity tables.\nRecalculate before delivery: `python \u002Fpath\u002Fto\u002Fexcel-author\u002Fscripts\u002Frecalc.py .\u002Fout\u002Fmodel.xlsx`.\n\n# Comparable Company Analysis\n\n## ⚠️ CRITICAL: Data Source Priority (READ FIRST)\n\n**ALWAYS follow this data source hierarchy:**\n\n1. **FIRST: Check for MCP data sources** - If S&P Kensho MCP, FactSet MCP, or Daloopa MCP are available, use them exclusively for financial and trading information\n2. **DO NOT use web search** if the above MCP data sources are available\n3. **ONLY if MCPs are unavailable:** Then use Bloomberg Terminal, SEC EDGAR filings, or other institutional sources\n4. **NEVER use web search as a primary data source** - it lacks the accuracy, audit trails, and reliability required for institutional-grade analysis\n\n**Why this matters:** MCP sources provide verified, institutional-grade data with proper citations. Web search results can be outdated, inaccurate, or unreliable for financial analysis.\n\n---\n\n## Overview\nThis skill teaches the agent to build institutional-grade comparable company analyses that combine operating metrics, valuation multiples, and statistical benchmarking. The output is a structured Excel\u002Fspreadsheet that enables informed investment decisions through peer comparison.\n\n**Reference Material & Contextualization:**\n\nAn example comparable company analysis is provided in `examples\u002Fcomps_example.xlsx`. When using this or other example files in this skill directory, use them intelligently:\n\n**DO use examples for:**\n- Understanding structural hierarchy (how sections flow)\n- Grasping the level of rigor expected (statistical depth, documentation standards)\n- Learning principles (clear headers, transparent formulas, audit trails)\n\n**DO NOT use examples for:**\n- Exact reproduction of format or metrics\n- Copying layout without considering context\n- Applying the same visual style regardless of audience\n\n**ALWAYS ask yourself first:**\n1. **\"Do you have a preferred format or should I adapt the template style?\"**\n2. **\"Who is the audience?\"** (Investment committee, board presentation, quick reference, detailed memo)\n3. **\"What's the key question?\"** (Valuation, growth analysis, competitive positioning, efficiency)\n4. **\"What's the context?\"** (M&A evaluation, investment decision, sector benchmarking, performance review)\n\n**Adapt based on specifics:**\n- **Industry context**: Big tech mega-caps need different metrics than emerging SaaS startups\n- **Sector-specific needs**: Add relevant metrics early (e.g., cloud ARR, enterprise customers, developer ecosystem for tech)\n- **Company familiarity**: Well-known companies may need less background, more focus on delta analysis\n- **Decision type**: M&A requires different emphasis than ongoing portfolio monitoring\n\n**Core principle:** Use template principles (clear structure, statistical rigor, transparent formulas) but vary execution based on context. The goal is institutional-quality analysis, not institutional-looking templates.\n\nUser-provided examples and explicit preferences always take precedence over defaults.\n\n## Core Philosophy\n**\"Build the right structure first, then let the data tell the story.\"**\n\nStart with headers that force strategic thinking about what matters, input clean data, build transparent formulas, and let statistics emerge automatically. A good comp should be immediately readable by someone who didn't build it.\n\n---\n\n## ⚠️ CRITICAL: Formulas Over Hardcodes + Step-by-Step Verification\n\n**Formulas, not hardcodes:**\n- Every derived value (margin, multiple, statistic) MUST be an Excel formula referencing input cells — never a pre-computed number pasted in\n- When using Python\u002Fopenpyxl to build the sheet: write `cell.value = \"=E7\u002FC7\"` (formula string), NOT `cell.value = 0.687` (computed result)\n- The only hardcoded values should be raw input data (revenue, EBITDA, share price, etc.) — and every one of those gets a cell comment with its source\n- Why: the model must update automatically when an input changes. A hardcoded margin is a silent bug waiting to happen.\n\n**Verify step-by-step with the user:**\n- After setting up the structure → show the user the header layout before filling data\n- After entering raw inputs → show the user the input block and confirm sources\u002Fperiods before building formulas\n- After building operating metrics formulas → show the calculated margins and sanity-check with the user before moving to valuation\n- After building valuation multiples → show the multiples and confirm they look reasonable before adding statistics\n- Do NOT build the entire sheet end-to-end and then present it — catch errors early by confirming each section\n\n---\n\n## Section 1: Document Structure & Setup\n\n### Header Block (Rows 1-3)\n```\nRow 1: [ANALYSIS TITLE] - COMPARABLE COMPANY ANALYSIS\nRow 2: [List of Companies with Tickers] • [Company 1 (TICK1)] • [Company 2 (TICK2)] • [Company 3 (TICK3)]\nRow 3: As of [Period] | All figures in [USD Millions\u002FBillions] except per-share amounts and ratios\n```\n\n**Why this matters:** Establishes context immediately. Anyone opening this file knows what they're looking at, when it was created, and how to interpret the numbers.\n\n### Visual Convention Standards (OPTIONAL - User preferences and uploaded templates always override)\n\n**IMPORTANT: These are suggested defaults only. Always prioritize:**\n1. User's explicit formatting preferences\n2. Formatting from any uploaded template files\n3. Company\u002Fteam style guides\n4. These defaults (only if no other guidance provided)\n\n**Suggested Font & Typography:**\n- **Font family**: Times New Roman (professional, readable, industry standard)\n- **Font size**: 11pt for data cells, 12pt for headers\n- **Bold text**: Section headers, company names, statistic labels\n\n**Default Color & Shading — Professional Blue\u002FGrey Palette (minimal is better):**\n- **Keep it restrained** — only blues and greys. Do NOT introduce greens, oranges, reds, or multiple accent colors. A clean comps sheet uses 3-4 colors total.\n- **Section headers** (e.g., \"OPERATING STATISTICS & FINANCIAL METRICS\"):\n  - Dark blue background (`#1F4E79` or `#17365D` navy)\n  - White bold text\n  - Full row shading across all columns\n- **Column headers** (e.g., \"Company\", \"Revenue\", \"Margin\"):\n  - Light blue background (`#D9E1F2` or similar pale blue)\n  - Black bold text\n  - Centered alignment\n- **Data rows**:\n  - White background for company data\n  - Black text for formulas; blue text for hardcoded inputs\n- **Statistics rows** (Maximum, 75th Percentile, etc.):\n  - Light grey background (`#F2F2F2`)\n  - Black text, left-aligned labels\n- **That's the whole palette**: dark blue + light blue + light grey + white. Nothing else unless the user's template says otherwise.\n\n**Suggested Formatting Conventions:**\n- **Decimal precision**:\n  - Percentages: 1 decimal (12.3%)\n  - Multiples: 1 decimal (13.5x)\n  - Dollar amounts: No decimals, thousands separator (69,632)\n  - Margins shown as percentages: 1 decimal (68.7%)\n- **Borders**: No borders (clean, minimal appearance)\n- **Alignment**: All metrics center-aligned for clean, uniform appearance\n- **Cell dimensions**: All column widths should be uniform\u002Feven, all row heights should be consistent (creates clean, professional grid)\n\n**Note:** If the user provides a template file or specifies different formatting, use that instead.\n\n---\n\n## Section 2: Operating Statistics & Financial Metrics\n\n### Core Columns (Start with these)\n1. **Company** - Names with consistent formatting\n2. **Revenue** - Size metric (can be LTM, quarterly, or annual depending on context)\n3. **Revenue Growth** - Year-over-year percentage change\n4. **Gross Profit** - Revenue minus cost of goods sold\n5. **Gross Margin** - GP\u002FRevenue (fundamental profitability)\n6. **EBITDA** - Earnings before interest, tax, depreciation, amortization\n7. **EBITDA Margin** - EBITDA\u002FRevenue (operating efficiency)\n\n### Optional Additions (Choose based on industry\u002Fpurpose)\n- **Quarterly vs LTM** - Include both if seasonality matters\n- **Free Cash Flow** - For capital-intensive or SaaS businesses\n- **FCF Margin** - FCF\u002FRevenue (cash generation efficiency)\n- **Net Income** - For mature, profitable companies\n- **Operating Income** - For businesses with varying D&A\n- **CapEx metrics** - For asset-heavy industries\n- **Rule of 40** - Specifically for SaaS (Growth % + Margin %)\n- **FCF Conversion** - For quality of earnings analysis (advanced)\n\n### Formula Examples (Using Row 7 as example)\n```excel\n\u002F\u002F Core ratios - these are always calculated\nGross Margin (F7): =E7\u002FC7\nEBITDA Margin (H7): =G7\u002FC7\n\n\u002F\u002F Optional ratios - include if relevant\nFCF Margin: =[FCF]\u002F[Revenue]\nNet Margin: =[Net Income]\u002F[Revenue]\nRule of 40: =[Growth %]+[FCF Margin %]\n```\n\n**Golden Rule:** Every ratio should be [Something] \u002F [Revenue] or [Something] \u002F [Something from this sheet]. Keep it simple.\n\n### Statistics Block (After company data)\n\n**CRITICAL: Add statistics formulas for all comparable metrics (ratios, margins, growth rates, multiples).**\n\n```\n[Leave one blank row for visual separation]\n- Maximum: =MAX(B7:B9)\n- 75th Percentile: =QUARTILE(B7:B9,3)\n- Median: =MEDIAN(B7:B9)\n- 25th Percentile: =QUARTILE(B7:B9,1)\n- Minimum: =MIN(B7:B9)\n```\n\n**Columns that NEED statistics (comparable metrics):**\n- Revenue Growth %, Gross Margin %, EBITDA Margin %, EPS\n- EV\u002FRevenue, EV\u002FEBITDA, P\u002FE, Dividend Yield %, Beta\n\n**Columns that DON'T need statistics (size metrics):**\n- Revenue, EBITDA, Net Income (absolute size varies by company scale)\n- Market Cap, Enterprise Value (not comparable across different-sized companies)\n\n**Note:** Add one blank row between company data and statistics rows for visual separation. Do NOT add a \"SECTOR STATISTICS\" or \"VALUATION STATISTICS\" header row.\n\n**Why quartiles matter:** They show distribution, not just average. A 75th percentile multiple tells you what \"premium\" companies trade at.\n\n---\n\n## Section 3: Valuation Multiples & Investment Metrics\n\n### Core Valuation Columns (Start with these)\n1. **Company** - Same order as operating section\n2. **Market Cap** - Current market valuation\n3. **Enterprise Value** - Market Cap ± Net Debt\u002FCash\n4. **EV\u002FRevenue** - How much market pays per dollar of sales\n5. **EV\u002FEBITDA** - How much market pays per dollar of earnings\n6. **P\u002FE Ratio** - Price relative to net earnings\n\n### Optional Valuation Metrics (Choose based on context)\n- **FCF Yield** - FCF\u002FMarket Cap (for cash-focused analysis)\n- **PEG Ratio** - P\u002FE\u002FGrowth Rate (for growth companies)\n- **Price\u002FBook** - Market value vs. book value (for asset-heavy businesses)\n- **ROE\u002FROA** - Return metrics (for profitability comparison)\n- **Revenue\u002FEBITDA CAGR** - Historical growth rates (for trend analysis)\n- **Asset Turnover** - Revenue\u002FAssets (for operational efficiency)\n- **Debt\u002FEquity** - Leverage (for capital structure analysis)\n\n**Key Principle:** Include 3-5 core multiples that matter for your industry. Don't include every possible metric just because you can.\n\n### Formula Examples\n```excel\n\u002F\u002F Core multiples - always include these\nEV\u002FRevenue: =[Enterprise Value]\u002F[LTM Revenue]\nEV\u002FEBITDA: =[Enterprise Value]\u002F[LTM EBITDA]\nP\u002FE Ratio: =[Market Cap]\u002F[Net Income]\n\n\u002F\u002F Optional multiples - include if data available\nFCF Yield: =[LTM FCF]\u002F[Market Cap]\nPEG Ratio: =[P\u002FE]\u002F[Growth Rate %]\n```\n\n### Cross-Reference Rule\n**CRITICAL:** Valuation multiples MUST reference the operating metrics section. Never input the same raw data twice. If revenue is in C7, then EV\u002FRevenue formula should reference C7.\n\n### Statistics Block\nSame structure as operating section: Max, 75th, Median, 25th, Min for every metric. Add one blank row for visual separation between company data and statistics. Do NOT add a \"VALUATION STATISTICS\" header row.\n\n---\n\n## Section 4: Notes & Methodology Documentation\n\n### Required Components\n\n**Data Sources & Quality:**\n- Where did the data come from? (S&P Kensho MCP, FactSet MCP, Daloopa MCP, Bloomberg, SEC filings)\n- What period does it cover? (Q4 2024, audited figures)\n- How was it verified? (Cross-checked against 10-K\u002F10-Q)\n- Note: Prioritize MCP data sources (S&P Kensho, FactSet, Daloopa) if available for better accuracy and traceability\n\n**Key Definitions:**\n- EBITDA calculation method (Gross Profit + D&A, or Operating Income + D&A)\n- Free Cash Flow formula (Operating CF - CapEx)\n- Special metrics explained (Rule of 40, FCF Conversion)\n- Time period definitions (LTM, CAGR calculation periods)\n\n**Valuation Methodology:**\n- How was Enterprise Value calculated? (Market Cap + Net Debt)\n- What growth rates were used? (Historical CAGR, forward estimates)\n- Any adjustments made? (One-time items excluded, normalized margins)\n\n**Analysis Framework:**\n- What's the investment thesis? (Cloud\u002FSaaS efficiency)\n- What metrics matter most? (Cash generation, capital efficiency)\n- How should readers interpret the statistics? (Quartiles provide context)\n\n---\n\n## Section 5: Choosing the Right Metrics (Decision Framework)\n\n### Start with \"What question am I answering?\"\n\n**\"Which company is undervalued?\"**\n→ Focus on: EV\u002FRevenue, EV\u002FEBITDA, P\u002FE, Market Cap\n→ Skip: Operational details, growth metrics\n\n**\"Which company is most efficient?\"**\n→ Focus on: Gross Margin, EBITDA Margin, FCF Margin, Asset Turnover\n→ Skip: Size metrics, absolute dollar amounts\n\n**\"Which company is growing fastest?\"**\n→ Focus on: Revenue Growth %, EBITDA CAGR, User\u002FCustomer Growth\n→ Skip: Margin metrics, leverage ratios\n\n**\"Which is the best cash generator?\"**\n→ Focus on: FCF, FCF Margin, FCF Conversion, CapEx intensity\n→ Skip: EBITDA, P\u002FE ratios\n\n### Industry-Specific Metric Selection\n\n**Software\u002FSaaS:**\nMust have: Revenue Growth, Gross Margin, Rule of 40\nOptional: ARR, Net Dollar Retention, CAC Payback\nSkip: Asset Turnover, Inventory metrics\n\n**Manufacturing\u002FIndustrials:**\nMust have: EBITDA Margin, Asset Turnover, CapEx\u002FRevenue\nOptional: ROA, Inventory Turns, Backlog\nSkip: Rule of 40, SaaS metrics\n\n**Financial Services:**\nMust have: ROE, ROA, Efficiency Ratio, P\u002FE\nOptional: Net Interest Margin, Loan Loss Reserves\nSkip: Gross Margin, EBITDA (not meaningful for banks)\n\n**Retail\u002FE-commerce:**\nMust have: Revenue Growth, Gross Margin, Inventory Turnover\nOptional: Same-Store Sales, Customer Acquisition Cost\nSkip: Heavy R&D or CapEx metrics\n\n### The \"5-10 Rule\"\n\n**5 operating metrics** - Revenue, Growth, 2-3 margins\u002Fefficiency metrics\n**5 valuation metrics** - Market Cap, EV, 3 multiples\n**= 10 total columns** - Enough to tell the story, not so many you lose the thread\n\nIf you have more than 15 metrics, you're probably including noise. Edit ruthlessly.\n\n---\n\n## Section 6: Best Practices & Quality Checks\n\n### Before You Start\n1. **Define the peer group** - Companies must be truly comparable (similar business model, scale, geography)\n2. **Choose the right period** - LTM smooths seasonality; quarterly shows trends\n3. **Standardize units upfront** - Millions vs. billions decision affects everything\n4. **Map data sources** - Know where each number comes from\n\n### As You Build\n1. **Input all raw data first** - Complete the blue text before writing formulas\n2. **Add cell comments to ALL hard-coded inputs** - Right-click cell → Insert Comment → Document source OR assumption\n\n   **For sourced data, cite exactly where it came from:**\n   - Example: \"Bloomberg Terminal - MSFT Equity DES, accessed 2024-10-02\"\n   - Example: \"Q4 2024 10-K filing, page 42, line item 'Total Revenue'\"\n   - Example: \"FactSet consensus estimate as of 2024-10-02\"\n   - **Include hyperlinks when possible**: Right-click cell → Link → paste URL to SEC filing, data source, or report\n\n   **For assumptions, explain the reasoning:**\n   - Example: \"Assumed 15% EBITDA margin based on peer median, company does not disclose\"\n   - Example: \"Estimated Enterprise Value as Market Cap + $50M net debt (from Q3 balance sheet, Q4 not yet available)\"\n   - Example: \"Forward P\u002FE based on street consensus EPS of $3.45 (average of 12 analyst estimates)\"\n\n   **Why this matters**: Enables audit trails, data verification, assumption transparency, and future updates\n3. **Build formulas row by row** - Test each calculation before moving on\n4. **Use absolute references for headers** - $C$6 locks the header row\n5. **Format consistently** - Percentages as percentages, not decimals\n6. **Add conditional formatting** - Highlight outliers automatically\n\n### Sanity Checks\n- **Margin test**: Gross margin > EBITDA margin > Net margin (always true by definition)\n- **Multiple reasonableness**: \n  - EV\u002FRevenue: typically 0.5-20x (varies widely by industry)\n  - EV\u002FEBITDA: typically 8-25x (fairly consistent across industries)\n  - P\u002FE: typically 10-50x (depends on growth rate)\n- **Growth-multiple correlation**: Higher growth usually means higher multiples\n- **Size-efficiency trade-off**: Larger companies often have better margins (scale benefits)\n\n### Common Mistakes to Avoid\n❌ Mixing market cap and enterprise value in formulas\n❌ Using different time periods for numerator and denominator (LTM vs quarterly)\n❌ Hardcoding numbers into formulas instead of cell references\n❌ **Hard-coded inputs without cell comments citing the source OR explaining the assumption**\n❌ Missing hyperlinks to SEC filings or data sources when available\n❌ Including too many metrics without clear purpose\n❌ Including non-comparable companies (different business models)\n❌ Using outdated data without disclosure\n❌ Calculating averages of percentages incorrectly (should be median)\n\n---\n\n## Section 6: Advanced Features\n\n### Dynamic Headers\nFor columns showing calculations, use clear unit labels:\n```\nRevenue Growth (YoY) % | EBITDA Margin | FCF Margin | Rule of 40\n```\n\n### Quartile Analysis Benefits\nInstead of just mean\u002Fmedian, quartiles show:\n- **75th percentile** = \"Premium\" companies trade here\n- **Median** = Typical market valuation\n- **25th percentile** = \"Discount\" territory\n\nThis helps answer: \"Is our target company trading rich or cheap vs. peers?\"\n\n### Industry-Specific Modifications\n\n**Software\u002FSaaS:**\n- Add: ARR, Net Dollar Retention, CAC Payback Period\n- Emphasize: Rule of 40, FCF margins, gross margins >70%\n\n**Healthcare:**\n- Add: R&D\u002FRevenue, Pipeline value, Regulatory status\n- Emphasize: EBITDA margins, growth rates, reimbursement risk\n\n**Industrials:**\n- Add: Backlog, Order book trends, Geographic mix\n- Emphasize: ROIC, asset turnover, cyclical adjustments\n\n**Consumer:**\n- Add: Same-store sales, Customer acquisition cost, Brand value\n- Emphasize: Revenue growth, gross margins, inventory turns\n\n---\n\n## Section 7: Workflow & Practical Tips\n\n### Step-by-Step Process\n1. **Set up structure** (30 minutes)\n   - Create all headers\n   - Format cells (blue for inputs, black for formulas)\n   - Lock in units and date references\n\n2. **Gather data** (60-90 minutes)\n   - Pull from primary sources (S&P Kensho MCP, FactSet MCP, Daloopa MCP if available; otherwise Bloomberg, SEC)\n   - Input all raw numbers in blue\n   - Document sources in notes section\n\n3. **Build formulas** (30 minutes)\n   - Start with simple ratios (margins)\n   - Progress to multiples (EV\u002FRevenue)\n   - Add cross-checks (do margins make sense?)\n\n4. **Add statistics** (15 minutes)\n   - Copy formula structure for all columns\n   - Verify ranges are correct (B7:B9, not B7:B10)\n   - Check quartile logic\n\n5. **Quality control** (30 minutes)\n   - Run sanity checks\n   - Verify formula references\n   - Check for #DIV\u002F0! or #REF! errors\n   - Compare against known benchmarks\n\n6. **Documentation** (15 minutes)\n   - Complete notes section\n   - Add data sources\n   - Define methodologies\n   - Date-stamp the analysis\n\n### Pro Tips\n- **Save templates**: Build once, reuse forever\n- **Color-code outliers**: Conditional formatting for values >2 standard deviations\n- **Link to source files**: Hyperlink to Bloomberg screenshots or SEC filings\n- **Version control**: Save as \"Comps_v1_2024-12-15\" with clear dating\n- **Collaborative reviews**: Have someone else check your formulas\n\n### Excel Formatting Checklist (Optional - adapt to user preferences)\n- [ ] Font set to user's preferred style (default: Times New Roman, 11pt data, 12pt headers)\n- [ ] Section headers formatted per user's template (default: dark blue #17365D with white bold text)\n- [ ] Column headers formatted per user's template (default: light blue\u002Fgray #D9E2F3 with black bold text)\n- [ ] Statistics rows formatted per user's template (default: light gray #F2F2F2)\n- [ ] No borders applied (clean, minimal appearance)\n- [ ] **Column widths set to uniform\u002Feven width** (creates clean, professional appearance)\n- [ ] **Row heights set to consistent height** (typically 20-25pt for data rows)\n- [ ] Numbers formatted with proper decimal precision and thousands separators\n- [ ] **All metrics center-aligned** for clean, uniform appearance\n- [ ] **One blank row for separation between company data and statistics rows**\n- [ ] **No separate \"SECTOR STATISTICS\" or \"VALUATION STATISTICS\" header rows**\n- [ ] **Every hard-coded input cell has a comment with either: (1) exact data source, OR (2) assumption explanation**\n- [ ] **Hyperlinks added to cells where applicable** (SEC filings, data provider pages, reports)\n\n---\n\n## Section 8: Example Template Layout\n\n**Simple Version (Start here):**\n```\n┌─────────────────────────────────────────────────────────────┐\n│ TECHNOLOGY - COMPARABLE COMPANY ANALYSIS                    │\n│ Microsoft • Alphabet • Amazon                               │\n│ As of Q4 2024 | All figures in USD Millions                │\n├─────────────────────────────────────────────────────────────┤\n│ OPERATING METRICS                                           │\n├──────────┬─────────┬─────────┬──────────┬──────────────────┤\n│ Company  │ Revenue │ Growth  │ Gross    │ EBITDA  │ EBITDA │\n│          │ (LTM)   │ (YoY)   │ Margin   │ (LTM)   │ Margin │\n├──────────┼─────────┼─────────┼──────────┼─────────┼────────┤\n│ MSFT     │ 261,400 │ 12.3%   │ 68.7%    │ 205,100 │ 78.4%  │\n│ GOOGL    │ 349,800 │ 11.8%   │ 57.9%    │ 239,300 │ 68.4%  │\n│ AMZN     │ 638,100 │ 10.5%   │ 47.3%    │ 152,600 │ 23.9%  │\n│          │         │         │          │         │        │ [blank row]\n│ Median   │ =MEDIAN │ =MEDIAN │ =MEDIAN  │ =MEDIAN │=MEDIAN │\n│ 75th %   │ =QUART  │ =QUART  │ =QUART   │ =QUART  │=QUART  │\n│ 25th %   │ =QUART  │ =QUART  │ =QUART   │ =QUART  │=QUART  │\n├─────────────────────────────────────────────────────────────┤\n│ VALUATION MULTIPLES                                         │\n├──────────┬──────────┬──────────┬──────────┬────────────────┤\n│ Company  │ Mkt Cap  │ EV       │ EV\u002FRev   │ EV\u002FEBITDA │ P\u002FE│\n├──────────┼──────────┼──────────┼──────────┼───────────┼────┤\n│ MSFT     │3,550,000 │3,530,000 │ 13.5x    │ 17.2x     │36.0│\n│ GOOGL    │2,030,000 │1,960,000 │  5.6x    │  8.2x     │24.5│\n│ AMZN     │2,226,000 │2,320,000 │  3.6x    │ 15.2x     │58.3│\n│          │          │          │          │           │    │ [blank row]\n│ Median   │ =MEDIAN  │ =MEDIAN  │ =MEDIAN  │ =MEDIAN   │=MED│\n│ 75th %   │ =QUART   │ =QUART   │ =QUART   │ =QUART    │=QRT│\n│ 25th %   │ =QUART   │ =QUART   │ =QUART   │ =QUART    │=QRT│\n└──────────┴──────────┴──────────┴──────────┴───────────┴────┘\n```\n\n**Add complexity only when needed:**\n- Include quarterly AND LTM if seasonality matters\n- Add FCF metrics if cash generation is key story\n- Include industry-specific metrics (Rule of 40 for SaaS, etc.)\n- Add more statistics rows if you have >5 companies\n\n---\n\n## Section 9: Industry-Specific Additions (Optional)\n\nOnly add these if they're critical to your analysis. Most comps work fine with just core metrics.\n\n**Software\u002FSaaS:**\nAdd if relevant: ARR, Net Dollar Retention, Rule of 40\n\n**Financial Services:**\nAdd if relevant: ROE, Net Interest Margin, Efficiency Ratio\n\n**E-commerce:**\nAdd if relevant: GMV, Take Rate, Active Buyers\n\n**Healthcare:**\nAdd if relevant: R&D\u002FRevenue, Pipeline Value, Patent Timeline\n\n**Manufacturing:**\nAdd if relevant: Asset Turnover, Inventory Turns, Backlog\n\n---\n\n## Section 10: Red Flags & Warning Signs\n\n### Data Quality Issues\n🚩 Inconsistent time periods (mixing quarterly and annual)  \n🚩 Missing data without explanation  \n🚩 Significant differences between data sources (>10% variance)\n\n### Valuation Red Flags\n🚩 Negative EBITDA companies being valued on EBITDA multiples (use revenue multiples instead)  \n🚩 P\u002FE ratios >100x without hypergrowth story  \n🚩 Margins that don't make sense for the industry\n\n### Comparability Issues\n🚩 Different fiscal year ends (causes timing problems)  \n🚩ixing pure-play and conglomerates  \n🚩 Materially different business models labeled as \"comps\"\n\n**When in doubt, exclude the company.** Better to have 3 perfect comps than 6 questionable ones.\n\n---\n\n## Section 11: Formulas Reference Guide\n\n### Essential Excel Formulas\n```excel\n\u002F\u002F Statistical Functions\n=AVERAGE(range)          \u002F\u002F Simple mean\n=MEDIAN(range)           \u002F\u002F Middle value\n=QUARTILE(range, 1)      \u002F\u002F 25th percentile\n=QUARTILE(range, 3)      \u002F\u002F 75th percentile\n=MAX(range)              \u002F\u002F Maximum value\n=MIN(range)              \u002F\u002F Minimum value\n=STDEV.P(range)          \u002F\u002F Standard deviation\n\n\u002F\u002F Financial Calculations\n=B7\u002FC7                   \u002F\u002F Simple ratio (Margin)\n=SUM(B7:B9)\u002F3            \u002F\u002F Average of multiple companies\n=IF(B7>0, C7\u002FB7, \"N\u002FA\")  \u002F\u002F Conditional calculation\n=IFERROR(C7\u002FD7, 0)       \u002F\u002F Handle divide by zero\n\n\u002F\u002F Cross-Sheet References\n='Sheet1'!B7             \u002F\u002F Reference another sheet\n=VLOOKUP(A7, Table1, 2)  \u002F\u002F Lookup from data table\n=INDEX(MATCH())          \u002F\u002F Advanced lookup\n\n\u002F\u002F Formatting\n=TEXT(B7, \"0.0%\")        \u002F\u002F Format as percentage\n=TEXT(C7, \"#,##0\")       \u002F\u002F Thousands separator\n```\n\n### Common Ratio Formulas\n```excel\nGross Margin = Gross Profit \u002F Revenue\nEBITDA Margin = EBITDA \u002F Revenue\nFCF Margin = Free Cash Flow \u002F Revenue\nFCF Conversion = FCF \u002F Operating Cash Flow\nROE = Net Income \u002F Shareholders' Equity\nROA = Net Income \u002F Total Assets\nAsset Turnover = Revenue \u002F Total Assets\nDebt\u002FEquity = Total Debt \u002F Shareholders' Equity\n```\n\n---\n\n## Key Principles Summary\n\n1. **Structure drives insight** - Right headers force right thinking\n2. **Less is more** - 5-10 metrics that matter beat 20 that don't\n3. **Choose metrics for your question** - Valuation analysis ≠ efficiency analysis\n4. **Statistics show patterns** - Median\u002Fquartiles reveal more than average\n5. **Transparency beats complexity** - Simple formulas everyone understands\n6. **Comparability is king** - Better to exclude than force a bad comp\n7. **Document your choices** - Explain which metrics and why in notes section\n\n---\n\n## Output Checklist\n\nBefore delivering a comp analysis, verify:\n- [ ] All companies are truly comparable\n- [ ] Data is from consistent time periods\n- [ ] Units are clearly labeled (millions\u002Fbillions)\n- [ ] Formulas reference cells, not hardcoded values\n- [ ] **All hard-coded input cells have comments with either: (1) exact data source with citation, OR (2) clear assumption with explanation**\n- [ ] **Hyperlinks added where relevant** (SEC EDGAR filings, Bloomberg pages, research reports)\n- [ ] Statistics include at least 5 metrics (Max, 75th, Med, 25th, Min)\n- [ ] Notes section documents sources and methodology\n- [ ] Visual formatting follows conventions (blue = input, black = formula)\n- [ ] Sanity checks pass (margins logical, multiples reasonable)\n- [ ] Date stamp is current (\"As of [Date]\")\n- [ ] Formula auditing shows no errors (#DIV\u002F0!, #REF!, #N\u002FA)\n\n---\n\n## Continuous Improvement\n\nAfter completing a comp analysis, ask:\n1. Did the statistics reveal unexpected insights?\n2. Were there any data gaps that limited analysis?\n3. Did stakeholders ask for metrics you didn't include?\n4. How long did it take vs. how long should it take?\n5. What would make this more useful next time?\n\nThe best comp analyses evolve with each iteration. Save templates, learn from feedback, and refine the structure based on what decision-makers actually use.\n\n\n## Data sources — MCP first, web fallback\n\nMany passages below say \"use the S&P Kensho MCP \u002F Daloopa MCP \u002F FactSet MCP\". Those are commercial financial-data MCPs from the original Cowork plugin context. In Hermes:\n\n- **If you have any structured financial-data MCP configured** (Hermes supports MCP — see `native-mcp` skill), prefer it for point-in-time comps, precedent transactions, and filings.\n- **Otherwise**, fall back to:\n  - `web_search` \u002F `web_extract` against SEC EDGAR (`https:\u002F\u002Fwww.sec.gov\u002Fcgi-bin\u002Fbrowse-edgar`) for US filings\n  - Company IR pages for press releases, earnings decks\n  - `browser_navigate` for interactive data portals\n  - User-provided data (explicitly ask when the context doesn't have it)\n- **Never fabricate**. If a multiple, precedent, or filing number can't be sourced, flag the cell as `[UNSOURCED]` and surface it to the user.\n\n## Attribution\n\nThis skill is adapted from Anthropic's Claude for Financial Services plugin suite (Apache-2.0). The Office-JS \u002F Cowork live-Excel paths have been removed; this version targets headless openpyxl via the `excel-author` skill's conventions. Original: https:\u002F\u002Fgithub.com\u002Fanthropics\u002Ffinancial-services\n","## Environment\n\nThis skill assumes **headless openpyxl** — you are producing an .xlsx file on disk.\nFollow the `excel-author` skill's conventions for cell coloring, formulas, named ranges, and sensitivity tables.\nRecalculate before delivery: `python \u002Fpath\u002Fto\u002Fexcel-author\u002Fscripts\u002Frecalc.py .\u002Fout\u002Fmodel.xlsx`.\n\n# Comparable Company Analysis\n\n## ⚠️ CRITICAL: Data Source Priority (READ FIRST)\n\n**ALWAYS follow this data source hierarchy:**\n\n1. **FIRST: Check for MCP data sources** - If S&P Kensho MCP, FactSet MCP, or Daloopa MCP are available, use them exclusively for financial and trading information\n2. **DO NOT use web search** if the above MCP data sources are available\n3. **ONLY if MCPs are unavailable:** Then use Bloomberg Terminal, SEC EDGAR filings, or other institutional sources\n4. **NEVER use web search as a primary data source** - it lacks the accuracy, audit trails, and reliability required for institutional-grade analysis\n\n**Why this matters:** MCP sources provide verified, institutional-grade data with proper citations. Web search results can be outdated, inaccurate, or unreliable for financial analysis.\n\n---\n\n## Overview\nThis skill teaches the agent to build institutional-grade comparable company analyses that combine operating metrics, valuation multiples, and statistical benchmarking. The output is a structured Excel\u002Fspreadsheet that enables informed investment decisions through peer comparison.\n\n**Reference Material & Contextualization:**\n\nAn example comparable company analysis is provided in `examples\u002Fcomps_example.xlsx`. When using this or other example files in this skill directory, use them intelligently:\n\n**DO use examples for:**\n- Understanding structural hierarchy (how sections flow)\n- Grasping the level of rigor expected (statistical depth, documentation standards)\n- Learning principles (clear headers, transparent formulas, audit trails)\n\n**DO NOT use examples for:**\n- Exact reproduction of format or metrics\n- Copying layout without considering context\n- Applying the same visual style regardless of audience\n\n**ALWAYS ask yourself first:**\n1. **\"Do you have a preferred format or should I adapt the template style?\"**\n2. **\"Who is the audience?\"** (Investment committee, board presentation, quick reference, detailed memo)\n3. **\"What's the key question?\"** (Valuation, growth analysis, competitive positioning, efficiency)\n4. **\"What's the context?\"** (M&A evaluation, investment decision, sector benchmarking, performance review)\n\n**Adapt based on specifics:**\n- **Industry context**: Big tech mega-caps need different metrics than emerging SaaS startups\n- **Sector-specific needs**: Add relevant metrics early (e.g., cloud ARR, enterprise customers, developer ecosystem for tech)\n- **Company familiarity**: Well-known companies may need less background, more focus on delta analysis\n- **Decision type**: M&A requires different emphasis than ongoing portfolio monitoring\n\n**Core principle:** Use template principles (clear structure, statistical rigor, transparent formulas) but vary execution based on context. The goal is institutional-quality analysis, not institutional-looking templates.\n\nUser-provided examples and explicit preferences always take precedence over defaults.\n\n## Core Philosophy\n**\"Build the right structure first, then let the data tell the story.\"**\n\nStart with headers that force strategic thinking about what matters, input clean data, build transparent formulas, and let statistics emerge automatically. A good comp should be immediately readable by someone who didn't build it.\n\n---\n\n## ⚠️ CRITICAL: Formulas Over Hardcodes + Step-by-Step Verification\n\n**Formulas, not hardcodes:**\n- Every derived value (margin, multiple, statistic) MUST be an Excel formula referencing input cells — never a pre-computed number pasted in\n- When using Python\u002Fopenpyxl to build the sheet: write `cell.value = \"=E7\u002FC7\"` (formula string), NOT `cell.value = 0.687` (computed result)\n- The only hardcoded values should be raw input data (revenue, EBITDA, share price, etc.) — and every one of those gets a cell comment with its source\n- Why: the model must update automatically when an input changes. A hardcoded margin is a silent bug waiting to happen.\n\n**Verify step-by-step with the user:**\n- After setting up the structure → show the user the header layout before filling data\n- After entering raw inputs → show the user the input block and confirm sources\u002Fperiods before building formulas\n- After building operating metrics formulas → show the calculated margins and sanity-check with the user before moving to valuation\n- After building valuation multiples → show the multiples and confirm they look reasonable before adding statistics\n- Do NOT build the entire sheet end-to-end and then present it — catch errors early by confirming each section\n\n---\n\n## Section 1: Document Structure & Setup\n\n### Header Block (Rows 1-3)\n```\nRow 1: [ANALYSIS TITLE] - COMPARABLE COMPANY ANALYSIS\nRow 2: [List of Companies with Tickers] • [Company 1 (TICK1)] • [Company 2 (TICK2)] • [Company 3 (TICK3)]\nRow 3: As of [Period] | All figures in [USD Millions\u002FBillions] except per-share amounts and ratios\n```\n\n**Why this matters:** Establishes context immediately. Anyone opening this file knows what they're looking at, when it was created, and how to interpret the numbers.\n\n### Visual Convention Standards (OPTIONAL - User preferences and uploaded templates always override)\n\n**IMPORTANT: These are suggested defaults only. Always prioritize:**\n1. User's explicit formatting preferences\n2. Formatting from any uploaded template files\n3. Company\u002Fteam style guides\n4. These defaults (only if no other guidance provided)\n\n**Suggested Font & Typography:**\n- **Font family**: Times New Roman (professional, readable, industry standard)\n- **Font size**: 11pt for data cells, 12pt for headers\n- **Bold text**: Section headers, company names, statistic labels\n\n**Default Color & Shading — Professional Blue\u002FGrey Palette (minimal is better):**\n- **Keep it restrained** — only blues and greys. Do NOT introduce greens, oranges, reds, or multiple accent colors. A clean comps sheet uses 3-4 colors total.\n- **Section headers** (e.g., \"OPERATING STATISTICS & FINANCIAL METRICS\"):\n  - Dark blue background (`#1F4E79` or `#17365D` navy)\n  - White bold text\n  - Full row shading across all columns\n- **Column headers** (e.g., \"Company\", \"Revenue\", \"Margin\"):\n  - Light blue background (`#D9E1F2` or similar pale blue)\n  - Black bold text\n  - Centered alignment\n- **Data rows**:\n  - White background for company data\n  - Black text for formulas; blue text for hardcoded inputs\n- **Statistics rows** (Maximum, 75th Percentile, etc.):\n  - Light grey background (`#F2F2F2`)\n  - Black text, left-aligned labels\n- **That's the whole palette**: dark blue + light blue + light grey + white. Nothing else unless the user's template says otherwise.\n\n**Suggested Formatting Conventions:**\n- **Decimal precision**:\n  - Percentages: 1 decimal (12.3%)\n  - Multiples: 1 decimal (13.5x)\n  - Dollar amounts: No decimals, thousands separator (69,632)\n  - Margins shown as percentages: 1 decimal (68.7%)\n- **Borders**: No borders (clean, minimal appearance)\n- **Alignment**: All metrics center-aligned for clean, uniform appearance\n- **Cell dimensions**: All column widths should be uniform\u002Feven, all row heights should be consistent (creates clean, professional grid)\n\n**Note:** If the user provides a template file or specifies different formatting, use that instead.\n\n---\n\n## Section 2: Operating Statistics & Financial Metrics\n\n### Core Columns (Start with these)\n1. **Company** - Names with consistent formatting\n2. **Revenue** - Size metric (can be LTM, quarterly, or annual depending on context)\n3. **Revenue Growth** - Year-over-year percentage change\n4. **Gross Profit** - Revenue minus cost of goods sold\n5. **Gross Margin** - GP\u002FRevenue (fundamental profitability)\n6. **EBITDA** - Earnings before interest, tax, depreciation, amortization\n7. **EBITDA Margin** - EBITDA\u002FRevenue (operating efficiency)\n\n### Optional Additions (Choose based on industry\u002Fpurpose)\n- **Quarterly vs LTM** - Include both if seasonality matters\n- **Free Cash Flow** - For capital-intensive or SaaS businesses\n- **FCF Margin** - FCF\u002FRevenue (cash generation efficiency)\n- **Net Income** - For mature, profitable companies\n- **Operating Income** - For businesses with varying D&A\n- **CapEx metrics** - For asset-heavy industries\n- **Rule of 40** - Specifically for SaaS (Growth % + Margin %)\n- **FCF Conversion** - For quality of earnings analysis (advanced)\n\n### Formula Examples (Using Row 7 as example)\n```excel\n\u002F\u002F Core ratios - these are always calculated\nGross Margin (F7): =E7\u002FC7\nEBITDA Margin (H7): =G7\u002FC7\n\n\u002F\u002F Optional ratios - include if relevant\nFCF Margin: =[FCF]\u002F[Revenue]\nNet Margin: =[Net Income]\u002F[Revenue]\nRule of 40: =[Growth %]+[FCF Margin %]\n```\n\n**Golden Rule:** Every ratio should be [Something] \u002F [Revenue] or [Something] \u002F [Something from this sheet]. Keep it simple.\n\n### Statistics Block (After company data)\n\n**CRITICAL: Add statistics formulas for all comparable metrics (ratios, margins, growth rates, multiples).**\n\n```\n[Leave one blank row for visual separation]\n- Maximum: =MAX(B7:B9)\n- 75th Percentile: =QUARTILE(B7:B9,3)\n- Median: =MEDIAN(B7:B9)\n- 25th Percentile: =QUARTILE(B7:B9,1)\n- Minimum: =MIN(B7:B9)\n```\n\n**Columns that NEED statistics (comparable metrics):**\n- Revenue Growth %, Gross Margin %, EBITDA Margin %, EPS\n- EV\u002FRevenue, EV\u002FEBITDA, P\u002FE, Dividend Yield %, Beta\n\n**Columns that DON'T need statistics (size metrics):**\n- Revenue, EBITDA, Net Income (absolute size varies by company scale)\n- Market Cap, Enterprise Value (not comparable across different-sized companies)\n\n**Note:** Add one blank row between company data and statistics rows for visual separation. Do NOT add a \"SECTOR STATISTICS\" or \"VALUATION STATISTICS\" header row.\n\n**Why quartiles matter:** They show distribution, not just average. A 75th percentile multiple tells you what \"premium\" companies trade at.\n\n---\n\n## Section 3: Valuation Multiples & Investment Metrics\n\n### Core Valuation Columns (Start with these)\n1. **Company** - Same order as operating section\n2. **Market Cap** - Current market valuation\n3. **Enterprise Value** - Market Cap ± Net Debt\u002FCash\n4. **EV\u002FRevenue** - How much market pays per dollar of sales\n5. **EV\u002FEBITDA** - How much market pays per dollar of earnings\n6. **P\u002FE Ratio** - Price relative to net earnings\n\n### Optional Valuation Metrics (Choose based on context)\n- **FCF Yield** - FCF\u002FMarket Cap (for cash-focused analysis)\n- **PEG Ratio** - P\u002FE\u002FGrowth Rate (for growth companies)\n- **Price\u002FBook** - Market value vs. book value (for asset-heavy businesses)\n- **ROE\u002FROA** - Return metrics (for profitability comparison)\n- **Revenue\u002FEBITDA CAGR** - Historical growth rates (for trend analysis)\n- **Asset Turnover** - Revenue\u002FAssets (for operational efficiency)\n- **Debt\u002FEquity** - Leverage (for capital structure analysis)\n\n**Key Principle:** Include 3-5 core multiples that matter for your industry. Don't include every possible metric just because you can.\n\n### Formula Examples\n```excel\n\u002F\u002F Core multiples - always include these\nEV\u002FRevenue: =[Enterprise Value]\u002F[LTM Revenue]\nEV\u002FEBITDA: =[Enterprise Value]\u002F[LTM EBITDA]\nP\u002FE Ratio: =[Market Cap]\u002F[Net Income]\n\n\u002F\u002F Optional multiples - include if data available\nFCF Yield: =[LTM FCF]\u002F[Market Cap]\nPEG Ratio: =[P\u002FE]\u002F[Growth Rate %]\n```\n\n### Cross-Reference Rule\n**CRITICAL:** Valuation multiples MUST reference the operating metrics section. Never input the same raw data twice. If revenue is in C7, then EV\u002FRevenue formula should reference C7.\n\n### Statistics Block\nSame structure as operating section: Max, 75th, Median, 25th, Min for every metric. Add one blank row for visual separation between company data and statistics. Do NOT add a \"VALUATION STATISTICS\" header row.\n\n---\n\n## Section 4: Notes & Methodology Documentation\n\n### Required Components\n\n**Data Sources & Quality:**\n- Where did the data come from? (S&P Kensho MCP, FactSet MCP, Daloopa MCP, Bloomberg, SEC filings)\n- What period does it cover? (Q4 2024, audited figures)\n- How was it verified? (Cross-checked against 10-K\u002F10-Q)\n- Note: Prioritize MCP data sources (S&P Kensho, FactSet, Daloopa) if available for better accuracy and traceability\n\n**Key Definitions:**\n- EBITDA calculation method (Gross Profit + D&A, or Operating Income + D&A)\n- Free Cash Flow formula (Operating CF - CapEx)\n- Special metrics explained (Rule of 40, FCF Conversion)\n- Time period definitions (LTM, CAGR calculation periods)\n\n**Valuation Methodology:**\n- How was Enterprise Value calculated? (Market Cap + Net Debt)\n- What growth rates were used? (Historical CAGR, forward estimates)\n- Any adjustments made? (One-time items excluded, normalized margins)\n\n**Analysis Framework:**\n- What's the investment thesis? (Cloud\u002FSaaS efficiency)\n- What metrics matter most? (Cash generation, capital efficiency)\n- How should readers interpret the statistics? (Quartiles provide context)\n\n---\n\n## Section 5: Choosing the Right Metrics (Decision Framework)\n\n### Start with \"What question am I answering?\"\n\n**\"Which company is undervalued?\"**\n→ Focus on: EV\u002FRevenue, EV\u002FEBITDA, P\u002FE, Market Cap\n→ Skip: Operational details, growth metrics\n\n**\"Which company is most efficient?\"**\n→ Focus on: Gross Margin, EBITDA Margin, FCF Margin, Asset Turnover\n→ Skip: Size metrics, absolute dollar amounts\n\n**\"Which company is growing fastest?\"**\n→ Focus on: Revenue Growth %, EBITDA CAGR, User\u002FCustomer Growth\n→ Skip: Margin metrics, leverage ratios\n\n**\"Which is the best cash generator?\"**\n→ Focus on: FCF, FCF Margin, FCF Conversion, CapEx intensity\n→ Skip: EBITDA, P\u002FE ratios\n\n### Industry-Specific Metric Selection\n\n**Software\u002FSaaS:**\nMust have: Revenue Growth, Gross Margin, Rule of 40\nOptional: ARR, Net Dollar Retention, CAC Payback\nSkip: Asset Turnover, Inventory metrics\n\n**Manufacturing\u002FIndustrials:**\nMust have: EBITDA Margin, Asset Turnover, CapEx\u002FRevenue\nOptional: ROA, Inventory Turns, Backlog\nSkip: Rule of 40, SaaS metrics\n\n**Financial Services:**\nMust have: ROE, ROA, Efficiency Ratio, P\u002FE\nOptional: Net Interest Margin, Loan Loss Reserves\nSkip: Gross Margin, EBITDA (not meaningful for banks)\n\n**Retail\u002FE-commerce:**\nMust have: Revenue Growth, Gross Margin, Inventory Turnover\nOptional: Same-Store Sales, Customer Acquisition Cost\nSkip: Heavy R&D or CapEx metrics\n\n### The \"5-10 Rule\"\n\n**5 operating metrics** - Revenue, Growth, 2-3 margins\u002Fefficiency metrics\n**5 valuation metrics** - Market Cap, EV, 3 multiples\n**= 10 total columns** - Enough to tell the story, not so many you lose the thread\n\nIf you have more than 15 metrics, you're probably including noise. Edit ruthlessly.\n\n---\n\n## Section 6: Best Practices & Quality Checks\n\n### Before You Start\n1. **Define the peer group** - Companies must be truly comparable (similar business model, scale, geography)\n2. **Choose the right period** - LTM smooths seasonality; quarterly shows trends\n3. **Standardize units upfront** - Millions vs. billions decision affects everything\n4. **Map data sources** - Know where each number comes from\n\n### As You Build\n1. **Input all raw data first** - Complete the blue text before writing formulas\n2. **Add cell comments to ALL hard-coded inputs** - Right-click cell → Insert Comment → Document source OR assumption\n\n   **For sourced data, cite exactly where it came from:**\n   - Example: \"Bloomberg Terminal - MSFT Equity DES, accessed 2024-10-02\"\n   - Example: \"Q4 2024 10-K filing, page 42, line item 'Total Revenue'\"\n   - Example: \"FactSet consensus estimate as of 2024-10-02\"\n   - **Include hyperlinks when possible**: Right-click cell → Link → paste URL to SEC filing, data source, or report\n\n   **For assumptions, explain the reasoning:**\n   - Example: \"Assumed 15% EBITDA margin based on peer median, company does not disclose\"\n   - Example: \"Estimated Enterprise Value as Market Cap + $50M net debt (from Q3 balance sheet, Q4 not yet available)\"\n   - Example: \"Forward P\u002FE based on street consensus EPS of $3.45 (average of 12 analyst estimates)\"\n\n   **Why this matters**: Enables audit trails, data verification, assumption transparency, and future updates\n3. **Build formulas row by row** - Test each calculation before moving on\n4. **Use absolute references for headers** - $C$6 locks the header row\n5. **Format consistently** - Percentages as percentages, not decimals\n6. **Add conditional formatting** - Highlight outliers automatically\n\n### Sanity Checks\n- **Margin test**: Gross margin > EBITDA margin > Net margin (always true by definition)\n- **Multiple reasonableness**: \n  - EV\u002FRevenue: typically 0.5-20x (varies widely by industry)\n  - EV\u002FEBITDA: typically 8-25x (fairly consistent across industries)\n  - P\u002FE: typically 10-50x (depends on growth rate)\n- **Growth-multiple correlation**: Higher growth usually means higher multiples\n- **Size-efficiency trade-off**: Larger companies often have better margins (scale benefits)\n\n### Common Mistakes to Avoid\n❌ Mixing market cap and enterprise value in formulas\n❌ Using different time periods for numerator and denominator (LTM vs quarterly)\n❌ Hardcoding numbers into formulas instead of cell references\n❌ **Hard-coded inputs without cell comments citing the source OR explaining the assumption**\n❌ Missing hyperlinks to SEC filings or data sources when available\n❌ Including too many metrics without clear purpose\n❌ Including non-comparable companies (different business models)\n❌ Using outdated data without disclosure\n❌ Calculating averages of percentages incorrectly (should be median)\n\n---\n\n## Section 6: Advanced Features\n\n### Dynamic Headers\nFor columns showing calculations, use clear unit labels:\n```\nRevenue Growth (YoY) % | EBITDA Margin | FCF Margin | Rule of 40\n```\n\n### Quartile Analysis Benefits\nInstead of just mean\u002Fmedian, quartiles show:\n- **75th percentile** = \"Premium\" companies trade here\n- **Median** = Typical market valuation\n- **25th percentile** = \"Discount\" territory\n\nThis helps answer: \"Is our target company trading rich or cheap vs. peers?\"\n\n### Industry-Specific Modifications\n\n**Software\u002FSaaS:**\n- Add: ARR, Net Dollar Retention, CAC Payback Period\n- Emphasize: Rule of 40, FCF margins, gross margins >70%\n\n**Healthcare:**\n- Add: R&D\u002FRevenue, Pipeline value, Regulatory status\n- Emphasize: EBITDA margins, growth rates, reimbursement risk\n\n**Industrials:**\n- Add: Backlog, Order book trends, Geographic mix\n- Emphasize: ROIC, asset turnover, cyclical adjustments\n\n**Consumer:**\n- Add: Same-store sales, Customer acquisition cost, Brand value\n- Emphasize: Revenue growth, gross margins, inventory turns\n\n---\n\n## Section 7: Workflow & Practical Tips\n\n### Step-by-Step Process\n1. **Set up structure** (30 minutes)\n   - Create all headers\n   - Format cells (blue for inputs, black for formulas)\n   - Lock in units and date references\n\n2. **Gather data** (60-90 minutes)\n   - Pull from primary sources (S&P Kensho MCP, FactSet MCP, Daloopa MCP if available; otherwise Bloomberg, SEC)\n   - Input all raw numbers in blue\n   - Document sources in notes section\n\n3. **Build formulas** (30 minutes)\n   - Start with simple ratios (margins)\n   - Progress to multiples (EV\u002FRevenue)\n   - Add cross-checks (do margins make sense?)\n\n4. **Add statistics** (15 minutes)\n   - Copy formula structure for all columns\n   - Verify ranges are correct (B7:B9, not B7:B10)\n   - Check quartile logic\n\n5. **Quality control** (30 minutes)\n   - Run sanity checks\n   - Verify formula references\n   - Check for #DIV\u002F0! or #REF! errors\n   - Compare against known benchmarks\n\n6. **Documentation** (15 minutes)\n   - Complete notes section\n   - Add data sources\n   - Define methodologies\n   - Date-stamp the analysis\n\n### Pro Tips\n- **Save templates**: Build once, reuse forever\n- **Color-code outliers**: Conditional formatting for values >2 standard deviations\n- **Link to source files**: Hyperlink to Bloomberg screenshots or SEC filings\n- **Version control**: Save as \"Comps_v1_2024-12-15\" with clear dating\n- **Collaborative reviews**: Have someone else check your formulas\n\n### Excel Formatting Checklist (Optional - adapt to user preferences)\n- [ ] Font set to user's preferred style (default: Times New Roman, 11pt data, 12pt headers)\n- [ ] Section headers formatted per user's template (default: dark blue #17365D with white bold text)\n- [ ] Column headers formatted per user's template (default: light blue\u002Fgray #D9E2F3 with black bold text)\n- [ ] Statistics rows formatted per user's template (default: light gray #F2F2F2)\n- [ ] No borders applied (clean, minimal appearance)\n- [ ] **Column widths set to uniform\u002Feven width** (creates clean, professional appearance)\n- [ ] **Row heights set to consistent height** (typically 20-25pt for data rows)\n- [ ] Numbers formatted with proper decimal precision and thousands separators\n- [ ] **All metrics center-aligned** for clean, uniform appearance\n- [ ] **One blank row for separation between company data and statistics rows**\n- [ ] **No separate \"SECTOR STATISTICS\" or \"VALUATION STATISTICS\" header rows**\n- [ ] **Every hard-coded input cell has a comment with either: (1) exact data source, OR (2) assumption explanation**\n- [ ] **Hyperlinks added to cells where applicable** (SEC filings, data provider pages, reports)\n\n---\n\n## Section 8: Example Template Layout\n\n**Simple Version (Start here):**\n```\n┌─────────────────────────────────────────────────────────────┐\n│ TECHNOLOGY - COMPARABLE COMPANY ANALYSIS                    │\n│ Microsoft • Alphabet • Amazon                               │\n│ As of Q4 2024 | All figures in USD Millions                │\n├─────────────────────────────────────────────────────────────┤\n│ OPERATING METRICS                                           │\n├──────────┬─────────┬─────────┬──────────┬──────────────────┤\n│ Company  │ Revenue │ Growth  │ Gross    │ EBITDA  │ EBITDA │\n│          │ (LTM)   │ (YoY)   │ Margin   │ (LTM)   │ Margin │\n├──────────┼─────────┼─────────┼──────────┼─────────┼────────┤\n│ MSFT     │ 261,400 │ 12.3%   │ 68.7%    │ 205,100 │ 78.4%  │\n│ GOOGL    │ 349,800 │ 11.8%   │ 57.9%    │ 239,300 │ 68.4%  │\n│ AMZN     │ 638,100 │ 10.5%   │ 47.3%    │ 152,600 │ 23.9%  │\n│          │         │         │          │         │        │ [blank row]\n│ Median   │ =MEDIAN │ =MEDIAN │ =MEDIAN  │ =MEDIAN │=MEDIAN │\n│ 75th %   │ =QUART  │ =QUART  │ =QUART   │ =QUART  │=QUART  │\n│ 25th %   │ =QUART  │ =QUART  │ =QUART   │ =QUART  │=QUART  │\n├─────────────────────────────────────────────────────────────┤\n│ VALUATION MULTIPLES                                         │\n├──────────┬──────────┬──────────┬──────────┬────────────────┤\n│ Company  │ Mkt Cap  │ EV       │ EV\u002FRev   │ EV\u002FEBITDA │ P\u002FE│\n├──────────┼──────────┼──────────┼──────────┼───────────┼────┤\n│ MSFT     │3,550,000 │3,530,000 │ 13.5x    │ 17.2x     │36.0│\n│ GOOGL    │2,030,000 │1,960,000 │  5.6x    │  8.2x     │24.5│\n│ AMZN     │2,226,000 │2,320,000 │  3.6x    │ 15.2x     │58.3│\n│          │          │          │          │           │    │ [blank row]\n│ Median   │ =MEDIAN  │ =MEDIAN  │ =MEDIAN  │ =MEDIAN   │=MED│\n│ 75th %   │ =QUART   │ =QUART   │ =QUART   │ =QUART    │=QRT│\n│ 25th %   │ =QUART   │ =QUART   │ =QUART   │ =QUART    │=QRT│\n└──────────┴──────────┴──────────┴──────────┴───────────┴────┘\n```\n\n**Add complexity only when needed:**\n- Include quarterly AND LTM if seasonality matters\n- Add FCF metrics if cash generation is key story\n- Include industry-specific metrics (Rule of 40 for SaaS, etc.)\n- Add more statistics rows if you have >5 companies\n\n---\n\n## Section 9: Industry-Specific Additions (Optional)\n\nOnly add these if they're critical to your analysis. Most comps work fine with just core metrics.\n\n**Software\u002FSaaS:**\nAdd if relevant: ARR, Net Dollar Retention, Rule of 40\n\n**Financial Services:**\nAdd if relevant: ROE, Net Interest Margin, Efficiency Ratio\n\n**E-commerce:**\nAdd if relevant: GMV, Take Rate, Active Buyers\n\n**Healthcare:**\nAdd if relevant: R&D\u002FRevenue, Pipeline Value, Patent Timeline\n\n**Manufacturing:**\nAdd if relevant: Asset Turnover, Inventory Turns, Backlog\n\n---\n\n## Section 10: Red Flags & Warning Signs\n\n### Data Quality Issues\n🚩 Inconsistent time periods (mixing quarterly and annual)  \n🚩 Missing data without explanation  \n🚩 Significant differences between data sources (>10% variance)\n\n### Valuation Red Flags\n🚩 Negative EBITDA companies being valued on EBITDA multiples (use revenue multiples instead)  \n🚩 P\u002FE ratios >100x without hypergrowth story  \n🚩 Margins that don't make sense for the industry\n\n### Comparability Issues\n🚩 Different fiscal year ends (causes timing problems)  \n🚩ixing pure-play and conglomerates  \n🚩 Materially different business models labeled as \"comps\"\n\n**When in doubt, exclude the company.** Better to have 3 perfect comps than 6 questionable ones.\n\n---\n\n## Section 11: Formulas Reference Guide\n\n### Essential Excel Formulas\n```excel\n\u002F\u002F Statistical Functions\n=AVERAGE(range)          \u002F\u002F Simple mean\n=MEDIAN(range)           \u002F\u002F Middle value\n=QUARTILE(range, 1)      \u002F\u002F 25th percentile\n=QUARTILE(range, 3)      \u002F\u002F 75th percentile\n=MAX(range)              \u002F\u002F Maximum value\n=MIN(range)              \u002F\u002F Minimum value\n=STDEV.P(range)          \u002F\u002F Standard deviation\n\n\u002F\u002F Financial Calculations\n=B7\u002FC7                   \u002F\u002F Simple ratio (Margin)\n=SUM(B7:B9)\u002F3            \u002F\u002F Average of multiple companies\n=IF(B7>0, C7\u002FB7, \"N\u002FA\")  \u002F\u002F Conditional calculation\n=IFERROR(C7\u002FD7, 0)       \u002F\u002F Handle divide by zero\n\n\u002F\u002F Cross-Sheet References\n='Sheet1'!B7             \u002F\u002F Reference another sheet\n=VLOOKUP(A7, Table1, 2)  \u002F\u002F Lookup from data table\n=INDEX(MATCH())          \u002F\u002F Advanced lookup\n\n\u002F\u002F Formatting\n=TEXT(B7, \"0.0%\")        \u002F\u002F Format as percentage\n=TEXT(C7, \"#,##0\")       \u002F\u002F Thousands separator\n```\n\n### Common Ratio Formulas\n```excel\nGross Margin = Gross Profit \u002F Revenue\nEBITDA Margin = EBITDA \u002F Revenue\nFCF Margin = Free Cash Flow \u002F Revenue\nFCF Conversion = FCF \u002F Operating Cash Flow\nROE = Net Income \u002F Shareholders' Equity\nROA = Net Income \u002F Total Assets\nAsset Turnover = Revenue \u002F Total Assets\nDebt\u002FEquity = Total Debt \u002F Shareholders' Equity\n```\n\n---\n\n## Key Principles Summary\n\n1. **Structure drives insight** - Right headers force right thinking\n2. **Less is more** - 5-10 metrics that matter beat 20 that don't\n3. **Choose metrics for your question** - Valuation analysis ≠ efficiency analysis\n4. **Statistics show patterns** - Median\u002Fquartiles reveal more than average\n5. **Transparency beats complexity** - Simple formulas everyone understands\n6. **Comparability is king** - Better to exclude than force a bad comp\n7. **Document your choices** - Explain which metrics and why in notes section\n\n---\n\n## Output Checklist\n\nBefore delivering a comp analysis, verify:\n- [ ] All companies are truly comparable\n- [ ] Data is from consistent time periods\n- [ ] Units are clearly labeled (millions\u002Fbillions)\n- [ ] Formulas reference cells, not hardcoded values\n- [ ] **All hard-coded input cells have comments with either: (1) exact data source with citation, OR (2) clear assumption with explanation**\n- [ ] **Hyperlinks added where relevant** (SEC EDGAR filings, Bloomberg pages, research reports)\n- [ ] Statistics include at least 5 metrics (Max, 75th, Med, 25th, Min)\n- [ ] Notes section documents sources and methodology\n- [ ] Visual formatting follows conventions (blue = input, black = formula)\n- [ ] Sanity checks pass (margins logical, multiples reasonable)\n- [ ] Date stamp is current (\"As of [Date]\")\n- [ ] Formula auditing shows no errors (#DIV\u002F0!, #REF!, #N\u002FA)\n\n---\n\n## Continuous Improvement\n\nAfter completing a comp analysis, ask:\n1. Did the statistics reveal unexpected insights?\n2. Were there any data gaps that limited analysis?\n3. Did stakeholders ask for metrics you didn't include?\n4. How long did it take vs. how long should it take?\n5. What would make this more useful next time?\n\nThe best comp analyses evolve with each iteration. Save templates, learn from feedback, and refine the structure based on what decision-makers actually use.\n\n\n## Data sources — MCP first, web fallback\n\nMany passages below say \"use the S&P Kensho MCP \u002F Daloopa MCP \u002F FactSet MCP\". Those are commercial financial-data MCPs from the original Cowork plugin context. In Hermes:\n\n- **If you have any structured financial-data MCP configured** (Hermes supports MCP — see `native-mcp` skill), prefer it for point-in-time comps, precedent transactions, and filings.\n- **Otherwise**, fall back to:\n  - `web_search` \u002F `web_extract` against SEC EDGAR (`https:\u002F\u002Fwww.sec.gov\u002Fcgi-bin\u002Fbrowse-edgar`) for US filings\n  - Company IR pages for press releases, earnings decks\n  - `browser_navigate` for interactive data portals\n  - User-provided data (explicitly ask when the context doesn't have it)\n- **Never fabricate**. If a multiple, precedent, or filing number can't be sourced, flag the cell as `[UNSOURCED]` and surface it to the user.\n\n## Attribution\n\nThis skill is adapted from Anthropic's Claude for Financial Services plugin suite (Apache-2.0). The Office-JS \u002F Cowork live-Excel paths have been removed; this version targets headless openpyxl via the `excel-author` skill's conventions. Original: https:\u002F\u002Fgithub.com\u002Fanthropics\u002Ffinancial-services\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"platforms":41,"description":7},"Anthropic (adapted by Nous Research)","1.0.0",{"hermes":27},{"tags":28,"related_skills":36},[29,30,31,32,33,34,35],"finance","valuation","comps","excel","openpyxl","modeling","investment-banking",[37,38,39,40],"excel-author","pptx-author","dcf-model","lbo-model",[42,43,44],"linux","macos","windows","main","eac438ea9216a7cb8a570cab803eb01eeafc6793","skills\u002Foptional\u002Ffinance\u002Fcomps-analysis","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m","https:\u002F\u002Fid-preview--d5bef06d-6c9e-4563-a3d4-a855b9d61610.lovable.app\u002F","Eu sou Antonio B. B. Ndombe \r\nEu sou um Pesquisador e desenvolvedor de sistema autonomia cognitivos, fundador de sistemas ODCs ( organismos digital conscientes)","2026-11-04 06:53:39",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add GrupoANDevelopment-m\u002Falberto-ai --skill comps-analysis",{"tool":59,"command":60},"bunx","bunx skills add GrupoANDevelopment-m\u002Falberto-ai --skill comps-analysis",{"tool":62,"command":63},"pnpm","pnpm dlx skills add GrupoANDevelopment-m\u002Falberto-ai --skill comps-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Foptional\u002Ffinance\u002Fcomps-analysis\u002FSKILL.md",true,[],[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7DASC6FSCJP49JZBSK0NY1Z","nemoclaw-user-reference","Describes the NemoClaw integration layer and blueprint architecture and how they orchestrate compatible agent sandboxes. Use when looking up architecture, agent integration, plugin structure, or blueprint design. Trigger keywords - nemoclaw architecture, nemoclaw agent architecture, nemoclaw plugin blueprint structure, nemoclaw vs openshell, which cli, nemoclaw cli, openshell cli, sandbox commands, nemoclaw cli commands, nemoclaw command reference, nemoclaw network policy, sandbox egress control operator approval, nemoclaw troubleshooting, nemoclaw debug sandbox issues.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-reference\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7DAS5S79VK33XFGVAM2TFWF","nemoclaw-user-overview","Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when to prefer NemoClaw versus integrating OpenShell and OpenClaw directly. Use when users ask about the relationship between OpenClaw, OpenShell, and NemoClaw, or when to use NemoClaw versus OpenShell. Trigger keywords - nemoclaw ecosystem, openclaw openshell, nemoclaw vs openshell, sandboxed openclaw, how nemoclaw works, nemoclaw sandbox lifecycle blueprint, nemoclaw overview, openclaw always-on assistants, nvidia openshell, nvidia nemotron, nemoclaw release notes, nemoclaw changelog.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-overview\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7DAS0PQEMET5MNGZ1ABSZVS","nemoclaw-user-monitor-sandbox","Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox logs. Trigger keywords - monitor nemoclaw sandbox, debug nemoclaw agent issues.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-monitor-sandbox\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7DARQYGF7E9A69VH6S3CGN9","nemoclaw-user-manage-sandboxes","Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential reset, rebuilds, network presets, upgrades, and uninstall. Trigger keywords - manage nemoclaw sandboxes, nemoclaw status, nemoclaw list, nemoclaw dashboard port, nemoclaw rebuild, nemoclaw upgrade sandboxes, nemoclaw uninstall, sandbox mutability, sandbox runtime configuration, sandbox rebuild, nemoclaw backup, nemoclaw restore, workspace backup, openshell sandbox download upload, nemoclaw messaging channels, nemoclaw telegram, nemoclaw discord, nemoclaw slack, nemoclaw wechat, nemoclaw whatsapp, openshell channel messaging, nemoclaw workspace files, soul.md, user.md, identity.md, agents.md, sandbox persistence.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M7DARH8BRTG51TRCAB7YWDJ4","nemoclaw-user-manage-policy","Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint access. Trigger keywords - customize nemoclaw network policy, sandbox egress policy configuration, nemoclaw integration policy examples, post-install policy setup, openshell approval workflow, policy preset, nemoclaw approve network requests, sandbox egress approval tui.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-manage-policy\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M7DARAT62M2VR37590VCZ5NS","nemoclaw-user-get-started","Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart, hermes agent nemoclaw, run hermes openshell sandbox, nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-get-started\u002FSKILL.md",[],[]]