[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D7DMPKKFZQBRC9TT8SCMWZ":3,"skill-same:01M7D7DMPKKFZQBRC9TT8SCMWZ":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},"01M7D7DMPKKFZQBRC9TT8SCMWZ","lbo-model",null,"Build leveraged buyout models in Excel — sources & uses, debt schedule, cash sweep, exit multiple, IRR\u002FMOIC sensitivity. Pairs with excel-author. Use for PE screening, sponsor-case valuation, or illustrative LBO in a pitch.","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\u002Flbo-model\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: lbo-model\ndescription: Build leveraged buyout models in Excel — sources & uses, debt schedule, cash sweep, exit multiple, IRR\u002FMOIC sensitivity. Pairs with excel-author. Use for PE screening, sponsor-case valuation, or illustrative LBO in a pitch.\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, lbo, private-equity, excel, openpyxl, modeling]\n    related_skills: [excel-author, pptx-author, dcf-model, 3-statement-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---\n\n## TEMPLATE REQUIREMENT\n\n**This skill uses templates for LBO models. Always check for an attached template file first.**\n\nBefore starting any LBO model:\n1. **If a template file is attached\u002Fprovided**: Use that template's structure exactly - copy it and populate with the user's data\n2. **If no template is attached**: Ask the user: *\"Do you have a specific LBO template you'd like me to use? If not, I can use the standard template which includes Sources & Uses, Operating Model, Debt Schedule, and Returns Analysis.\"*\n3. **If using the standard template**: Copy `examples\u002FLBO_Model.xlsx` as your starting point and populate it with the user's assumptions\n\n**IMPORTANT**: When a file like `LBO_Model.xlsx` is attached, you MUST use it as your template - do not build from scratch. Even if the template seems complex or has more features than needed, copy it and adapt it to the user's requirements. Never decide to \"build from scratch\" when a template is provided.\n\n---\n\n## CRITICAL INSTRUCTIONS — READ FIRST\n\nUse Python\u002Fopenpyxl. Write formula strings (`ws[\"D20\"] = \"=B5*B6\"`), then run the `excel-author` skill's `recalc.py` helper before delivery.\n\n### Core Principles\n* **Every calculation must be an Excel formula** - NEVER compute values in Python and hardcode results into cells. When using openpyxl, write `cell.value = \"=B5*B6\"` (formula string), NOT `cell.value = 1250` (computed result). The model must be dynamic and update when inputs change.\n* **Use the template structure** - Follow the organization in `examples\u002FLBO_Model.xlsx` or the user's provided template. Do not invent your own layout.\n* **Use proper cell references** - All formulas should reference the appropriate cells. Never type numbers that should come from other cells.\n* **Maintain sign convention consistency** - Follow whatever sign convention the template uses (some use negative for outflows, some use positive). Be consistent throughout.\n* **Work section by section, verify with user at each step** - Complete one section fully, show the user what was built, run the section's verification checks, and get confirmation BEFORE moving to the next section. Do NOT build the entire model end-to-end and then present it — later sections depend on earlier ones, so catching a mistake in Sources & Uses after the returns are already built means rework everywhere.\n\n### Formula Color Conventions\n* **Blue (0000FF)**: Hardcoded inputs - typed numbers that don't reference other cells\n* **Black (000000)**: Formulas with calculations - any formula using operators or functions (`=B4*B5`, `=SUM()`, `=-MAX(0,B4)`)\n* **Purple (800080)**: Links to cells on the **same tab** - direct references with no calculation (`=B9`, `=B45`)\n* **Green (008000)**: Links to cells on **different tabs** - cross-sheet references (`=Assumptions!B5`, `='Operating Model'!C10`)\n\n### Fill Color Palette — Professional Blues & Greys (Default unless user\u002Ftemplate specifies otherwise)\n* **Keep it minimal** — only use blues and greys for cell fills. Do NOT introduce greens, yellows, reds, or multiple accents. A professional LBO model uses restraint.\n* **Default fill palette:**\n  * **Section headers** (Sources & Uses, Operating Model, etc.): Dark blue `#1F4E79` with white bold text\n  * **Column headers** (Year 1, Year 2, etc.): Light blue `#D9E1F2` with black bold text\n  * **Input cells**: Light grey `#F2F2F2` (or just white) — the blue *font* is the signal, fill is secondary\n  * **Formula\u002Fcalculated cells**: White, no fill\n  * **Key outputs** (IRR, MOIC, Exit Equity): Medium blue `#BDD7EE` with black bold text\n* **That's the whole palette.** 3 blues + 1 grey + white. If the template uses its own colors, follow the template instead.\n* Note: The blue\u002Fblack\u002Fpurple\u002Fgreen **font** colors above are for distinguishing inputs vs formulas vs links. Those are separate from the **fill** palette here — both work together.\n\n### Number Formatting Standards\n* **Currency**: `$#,##0;($#,##0);\"-\"` or `$#,##0.0` depending on template\n* **Percentages**: `0.0%` (one decimal)\n* **Multiples**: `0.0\"x\"` (one decimal)\n* **MOIC\u002FDetailed Ratios**: `0.00\"x\"` (two decimals for precision)\n* **All numeric cells**: Right-aligned\n\n---\n\n### Clarify Requirements First\n\nBefore filling any formulas:\n\n* **Examine the template structure** - Identify all sections, understand the timeline (which columns are which periods), note any existing formulas\n* **Ask the user if anything is unclear** - If the template structure, calculation methods, or requirements are ambiguous, ask before proceeding\n* **Confirm key assumptions** - Any key inputs, calculation preferences, or specific requirements\n* **ONLY AFTER understanding the template**, proceed to fill in formulas\n\n---\n\n## TEMPLATE ANALYSIS PHASE - DO THIS FIRST\n\nBefore filling any formulas, examine the template thoroughly:\n\n1. **Map the structure** - Identify where each section lives and how they relate to each other. Note which sections feed into others.\n\n2. **Understand the timeline** - Which columns represent which periods? Is there a \"Closing\" or \"Pro Forma\" column? Where does the projection period start?\n\n3. **Identify input vs formula cells** - Templates often use color coding, borders, or shading to indicate which cells need inputs vs formulas. Respect these conventions.\n\n4. **Read existing labels carefully** - The row labels tell you exactly what calculation is expected. Don't assume - read what the template is asking for.\n\n5. **Check for existing formulas** - Some templates come partially filled. Don't overwrite working formulas unless specifically asked.\n\n6. **Note template-specific conventions** - Sign conventions, subtotal structures, how sections are organized, whether there are separate tabs for different components, etc.\n\n---\n\n## FILLING FORMULAS - GENERAL APPROACH\n\nFor each cell that needs a formula, follow this hierarchy:\n\n### Step 1: Check the Template\n* Does the cell already have a formula? If yes, verify it's correct and move on.\n* Is there a comment or note indicating the expected calculation?\n* Does the row\u002Fcolumn label make the calculation obvious?\n* Do neighboring cells show a pattern you should follow?\n\n### Step 2: Check the User's Instructions\n* Did the user specify a particular calculation method?\n* Are there stated assumptions that affect this formula?\n* Any special requirements mentioned?\n\n### Step 3: Apply Standard Practice\n* If neither template nor user specifies, use standard LBO modeling conventions\n* Document any assumptions you make\n* If genuinely uncertain, ask the user\n\n---\n\n## COMMON PROBLEM AREAS\n\nThe following calculation patterns frequently cause issues across LBO models. Pay special attention when you encounter these:\n\n### Balancing Sections\n* When two sections must equal (e.g., Sources = Uses), one item is typically the \"plug\" (balancing figure)\n* Identify which item is the plug and calculate it as the difference\n\n### Tax Calculations\n* Tax formulas should only reference the relevant income line and tax rate\n* Should NOT reference unrelated sections (e.g., debt schedules)\n* Consider whether losses create tax shields or are simply ignored\n\n### Interest and Circular References\n* Interest calculations can create circularity if they reference balances affected by cash flows\n* Use **Beginning Balance** (not average or ending) to break circular references\n* Pattern: Interest → Cash Flow → Paydown → Ending Balance (if interest uses ending balance, this circles back)\n\n### Debt Paydown \u002F Cash Sweeps\n* When multiple debt tranches exist, there's usually a priority order\n* Cash sweep should respect the priority waterfall\n* Balances cannot go negative - use MAX or MIN functions appropriately\n\n### Returns Calculations (IRR\u002FMOIC)\n* Cash flows must have correct signs: Investment = negative, Proceeds = positive\n* If using XIRR, need corresponding dates\n* If using IRR, cash flows should be in consecutive periods\n* MOIC = Total Proceeds \u002F Total Investment\n\n### Sensitivity Tables\n* **Use ODD dimensions** (5×5 or 7×7) — never 4×4 or 6×6. Odd dimensions guarantee a true center cell.\n* **Center cell = base case.** Build the row and column axis values symmetrically around the model's actual assumptions (e.g., if base entry multiple = 10.0x, axis = `[8.0x, 9.0x, 10.0x, 11.0x, 12.0x]`). The center cell's IRR\u002FMOIC MUST then equal the model's actual IRR\u002FMOIC output — this is the proof the table is wired correctly.\n* **Highlight the center cell** — medium-blue fill (`#BDD7EE`) + bold font so the base case is visually anchored.\n* Excel's DATA TABLE function may not work with openpyxl — instead write explicit formulas that reference row\u002Fcolumn headers\n* Each cell should show a DIFFERENT value — if all same, formulas aren't varying correctly\n* Use mixed references (e.g., `$A5` for row input, `B$4` for column input)\n\n---\n\n## VERIFICATION CHECKLIST - RUN AFTER COMPLETION\n\n### Run Formula Validation\n```bash\npython \u002Fpath\u002Fto\u002Fexcel-author\u002Fscripts\u002Frecalc.py model.xlsx\n```\nMust return success with zero errors.\n\n### Section Balancing\n- [ ] Any sections that must balance (Sources\u002FUses, Assets\u002FLiabilities) balance exactly\n- [ ] Plug items are calculated correctly as the balancing figure\n- [ ] Amounts that should match across sections are consistent\n\n### Income\u002FOperating Projections\n- [ ] Revenue\u002Ftop-line builds correctly from drivers or growth rates\n- [ ] All cost and expense items calculated appropriately\n- [ ] Subtotals and totals sum correctly\n- [ ] Margins and ratios are reasonable\n- [ ] Links to assumptions are correct\n\n### Balance Sheet (if applicable)\n- [ ] Assets = Liabilities + Equity (must balance)\n- [ ] All items link to appropriate schedules or roll-forwards\n- [ ] Beginning balances = prior period ending balances\n- [ ] Check row included and shows zero\n\n### Cash Flow (if applicable)\n- [ ] Starts with correct income figure\n- [ ] Non-cash items added\u002Fsubtracted appropriately\n- [ ] Working capital changes have correct signs\n- [ ] Ending Cash = Beginning Cash + Net Cash Flow\n- [ ] Cash balances are consistent across statements\n\n### Supporting Schedules\n- [ ] Roll-forward schedules balance (Beginning + Changes = Ending)\n- [ ] Schedules link correctly to main statements\n- [ ] Calculated items use appropriate drivers\n- [ ] All periods are calculated consistently\n\n### Debt\u002FFinancing Schedules (if applicable)\n- [ ] Beginning balances tie to sources or prior period\n- [ ] Interest calculated on appropriate balance (typically beginning)\n- [ ] Paydowns respect cash availability and priority\n- [ ] Ending balances cannot be negative\n- [ ] Totals sum tranches correctly\n\n### Returns\u002FOutput Analysis\n- [ ] Exit\u002Fterminal values calculated correctly\n- [ ] All relevant adjustments included\n- [ ] Cash flow signs are correct (negative for investment, positive for proceeds)\n- [ ] IRR\u002FMOIC formulas reference complete ranges\n- [ ] Results are reasonable for the scenario\n\n### Sensitivity Tables (if applicable)\n- [ ] Grid dimensions are ODD (5×5 or 7×7) — there is a true center cell\n- [ ] Row and column axis values are symmetric around the base case (`[base-2Δ, base-Δ, base, base+Δ, base+2Δ]`)\n- [ ] Center cell output equals the model's actual IRR\u002FMOIC — confirms the table is wired correctly\n- [ ] Center cell is highlighted (medium-blue fill `#BDD7EE`, bold font)\n- [ ] Row and column headers contain appropriate input values\n- [ ] Each data cell contains a formula (not hardcoded)\n- [ ] Each data cell shows a DIFFERENT value\n- [ ] Values move in expected directions (higher exit multiple → higher IRR, etc.)\n\n### Formatting\n- [ ] Hardcoded inputs are blue (0000FF)\n- [ ] Calculated formulas are black (000000)\n- [ ] Same-tab links are purple (800080)\n- [ ] Cross-tab links are green (008000)\n- [ ] All numbers are right-aligned\n- [ ] Appropriate number formats applied throughout\n- [ ] No cells show error values (#REF!, #DIV\u002F0!, #VALUE!, #NAME?)\n\n### Logical Sanity Checks\n- [ ] Numbers are reasonable order of magnitude\n- [ ] Trends make sense (growth, decline, stabilization as expected)\n- [ ] No obviously wrong values (negative where should be positive, impossible percentages, etc.)\n- [ ] Key outputs are within reasonable ranges for the type of analysis\n\n---\n\n## COMMON ERRORS TO AVOID\n\n| Error | What Goes Wrong | How to Fix |\n|-------|-----------------|------------|\n| Hardcoding calculated values | Model doesn't update when inputs change | Always use formulas that reference source cells |\n| Wrong cell references after copying | Formulas point to wrong cells | Verify all links, use appropriate $ anchoring |\n| Circular reference errors | Model can't calculate | Use beginning balances for interest-type calcs, break the circle |\n| Sections don't balance | Totals that should match don't | Ensure one item is the plug (calculated as difference) |\n| Negative balances where impossible | Paying\u002Fusing more than available | Use MAX(0, ...) or MIN functions appropriately |\n| IRR\u002Freturn errors | Wrong signs or incomplete ranges | Check cash flow signs and ensure formula covers all periods |\n| Sensitivity table shows same value | Formula not varying with inputs | Check cell references - need mixed references ($A5, B$4) |\n| Roll-forwards don't tie | Beginning ≠ prior ending | Verify links between periods |\n| Inconsistent sign conventions | Additions become subtractions or vice versa | Follow template's convention consistently throughout |\n\n---\n\n## WORKING WITH THE USER — SECTION-BY-SECTION CHECKPOINTS\n\n* **If the template structure is unclear**, ask before proceeding\n* **If the user's requirements conflict with the template**, confirm their preference\n* **After completing each major section**, STOP and verify with the user before continuing:\n  - **After Sources & Uses** → show the balanced table, confirm the plug is correct, get sign-off before building the operating model\n  - **After Operating Model \u002F Projections** → show the projected P&L, confirm growth rates and margins look right, get sign-off before the debt schedule\n  - **After Debt Schedule** → show beginning\u002Fending balances and interest, confirm the waterfall logic, get sign-off before returns\n  - **After Returns (IRR\u002FMOIC)** → show the cash flow series and outputs, confirm signs and ranges, get sign-off before sensitivity tables\n  - **After Sensitivity Tables** → show that each cell varies, confirm the base case lands where expected\n* **If errors are found during verification**, fix them before moving to the next section\n* **Show your work** - explain key formulas or assumptions when helpful\n* **Never present a completed model without having checked in at each section** — it's faster to catch a wrong cell reference at the source than to trace it backwards from a broken IRR\n\n---\n\n**This skill produces investment banking-quality LBO models by filling templates with correct formulas, proper formatting, and validated calculations. The skill adapts to any template structure while ensuring financial accuracy and professional presentation standards.**\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---\n\n## TEMPLATE REQUIREMENT\n\n**This skill uses templates for LBO models. Always check for an attached template file first.**\n\nBefore starting any LBO model:\n1. **If a template file is attached\u002Fprovided**: Use that template's structure exactly - copy it and populate with the user's data\n2. **If no template is attached**: Ask the user: *\"Do you have a specific LBO template you'd like me to use? If not, I can use the standard template which includes Sources & Uses, Operating Model, Debt Schedule, and Returns Analysis.\"*\n3. **If using the standard template**: Copy `examples\u002FLBO_Model.xlsx` as your starting point and populate it with the user's assumptions\n\n**IMPORTANT**: When a file like `LBO_Model.xlsx` is attached, you MUST use it as your template - do not build from scratch. Even if the template seems complex or has more features than needed, copy it and adapt it to the user's requirements. Never decide to \"build from scratch\" when a template is provided.\n\n---\n\n## CRITICAL INSTRUCTIONS — READ FIRST\n\nUse Python\u002Fopenpyxl. Write formula strings (`ws[\"D20\"] = \"=B5*B6\"`), then run the `excel-author` skill's `recalc.py` helper before delivery.\n\n### Core Principles\n* **Every calculation must be an Excel formula** - NEVER compute values in Python and hardcode results into cells. When using openpyxl, write `cell.value = \"=B5*B6\"` (formula string), NOT `cell.value = 1250` (computed result). The model must be dynamic and update when inputs change.\n* **Use the template structure** - Follow the organization in `examples\u002FLBO_Model.xlsx` or the user's provided template. Do not invent your own layout.\n* **Use proper cell references** - All formulas should reference the appropriate cells. Never type numbers that should come from other cells.\n* **Maintain sign convention consistency** - Follow whatever sign convention the template uses (some use negative for outflows, some use positive). Be consistent throughout.\n* **Work section by section, verify with user at each step** - Complete one section fully, show the user what was built, run the section's verification checks, and get confirmation BEFORE moving to the next section. Do NOT build the entire model end-to-end and then present it — later sections depend on earlier ones, so catching a mistake in Sources & Uses after the returns are already built means rework everywhere.\n\n### Formula Color Conventions\n* **Blue (0000FF)**: Hardcoded inputs - typed numbers that don't reference other cells\n* **Black (000000)**: Formulas with calculations - any formula using operators or functions (`=B4*B5`, `=SUM()`, `=-MAX(0,B4)`)\n* **Purple (800080)**: Links to cells on the **same tab** - direct references with no calculation (`=B9`, `=B45`)\n* **Green (008000)**: Links to cells on **different tabs** - cross-sheet references (`=Assumptions!B5`, `='Operating Model'!C10`)\n\n### Fill Color Palette — Professional Blues & Greys (Default unless user\u002Ftemplate specifies otherwise)\n* **Keep it minimal** — only use blues and greys for cell fills. Do NOT introduce greens, yellows, reds, or multiple accents. A professional LBO model uses restraint.\n* **Default fill palette:**\n  * **Section headers** (Sources & Uses, Operating Model, etc.): Dark blue `#1F4E79` with white bold text\n  * **Column headers** (Year 1, Year 2, etc.): Light blue `#D9E1F2` with black bold text\n  * **Input cells**: Light grey `#F2F2F2` (or just white) — the blue *font* is the signal, fill is secondary\n  * **Formula\u002Fcalculated cells**: White, no fill\n  * **Key outputs** (IRR, MOIC, Exit Equity): Medium blue `#BDD7EE` with black bold text\n* **That's the whole palette.** 3 blues + 1 grey + white. If the template uses its own colors, follow the template instead.\n* Note: The blue\u002Fblack\u002Fpurple\u002Fgreen **font** colors above are for distinguishing inputs vs formulas vs links. Those are separate from the **fill** palette here — both work together.\n\n### Number Formatting Standards\n* **Currency**: `$#,##0;($#,##0);\"-\"` or `$#,##0.0` depending on template\n* **Percentages**: `0.0%` (one decimal)\n* **Multiples**: `0.0\"x\"` (one decimal)\n* **MOIC\u002FDetailed Ratios**: `0.00\"x\"` (two decimals for precision)\n* **All numeric cells**: Right-aligned\n\n---\n\n### Clarify Requirements First\n\nBefore filling any formulas:\n\n* **Examine the template structure** - Identify all sections, understand the timeline (which columns are which periods), note any existing formulas\n* **Ask the user if anything is unclear** - If the template structure, calculation methods, or requirements are ambiguous, ask before proceeding\n* **Confirm key assumptions** - Any key inputs, calculation preferences, or specific requirements\n* **ONLY AFTER understanding the template**, proceed to fill in formulas\n\n---\n\n## TEMPLATE ANALYSIS PHASE - DO THIS FIRST\n\nBefore filling any formulas, examine the template thoroughly:\n\n1. **Map the structure** - Identify where each section lives and how they relate to each other. Note which sections feed into others.\n\n2. **Understand the timeline** - Which columns represent which periods? Is there a \"Closing\" or \"Pro Forma\" column? Where does the projection period start?\n\n3. **Identify input vs formula cells** - Templates often use color coding, borders, or shading to indicate which cells need inputs vs formulas. Respect these conventions.\n\n4. **Read existing labels carefully** - The row labels tell you exactly what calculation is expected. Don't assume - read what the template is asking for.\n\n5. **Check for existing formulas** - Some templates come partially filled. Don't overwrite working formulas unless specifically asked.\n\n6. **Note template-specific conventions** - Sign conventions, subtotal structures, how sections are organized, whether there are separate tabs for different components, etc.\n\n---\n\n## FILLING FORMULAS - GENERAL APPROACH\n\nFor each cell that needs a formula, follow this hierarchy:\n\n### Step 1: Check the Template\n* Does the cell already have a formula? If yes, verify it's correct and move on.\n* Is there a comment or note indicating the expected calculation?\n* Does the row\u002Fcolumn label make the calculation obvious?\n* Do neighboring cells show a pattern you should follow?\n\n### Step 2: Check the User's Instructions\n* Did the user specify a particular calculation method?\n* Are there stated assumptions that affect this formula?\n* Any special requirements mentioned?\n\n### Step 3: Apply Standard Practice\n* If neither template nor user specifies, use standard LBO modeling conventions\n* Document any assumptions you make\n* If genuinely uncertain, ask the user\n\n---\n\n## COMMON PROBLEM AREAS\n\nThe following calculation patterns frequently cause issues across LBO models. Pay special attention when you encounter these:\n\n### Balancing Sections\n* When two sections must equal (e.g., Sources = Uses), one item is typically the \"plug\" (balancing figure)\n* Identify which item is the plug and calculate it as the difference\n\n### Tax Calculations\n* Tax formulas should only reference the relevant income line and tax rate\n* Should NOT reference unrelated sections (e.g., debt schedules)\n* Consider whether losses create tax shields or are simply ignored\n\n### Interest and Circular References\n* Interest calculations can create circularity if they reference balances affected by cash flows\n* Use **Beginning Balance** (not average or ending) to break circular references\n* Pattern: Interest → Cash Flow → Paydown → Ending Balance (if interest uses ending balance, this circles back)\n\n### Debt Paydown \u002F Cash Sweeps\n* When multiple debt tranches exist, there's usually a priority order\n* Cash sweep should respect the priority waterfall\n* Balances cannot go negative - use MAX or MIN functions appropriately\n\n### Returns Calculations (IRR\u002FMOIC)\n* Cash flows must have correct signs: Investment = negative, Proceeds = positive\n* If using XIRR, need corresponding dates\n* If using IRR, cash flows should be in consecutive periods\n* MOIC = Total Proceeds \u002F Total Investment\n\n### Sensitivity Tables\n* **Use ODD dimensions** (5×5 or 7×7) — never 4×4 or 6×6. Odd dimensions guarantee a true center cell.\n* **Center cell = base case.** Build the row and column axis values symmetrically around the model's actual assumptions (e.g., if base entry multiple = 10.0x, axis = `[8.0x, 9.0x, 10.0x, 11.0x, 12.0x]`). The center cell's IRR\u002FMOIC MUST then equal the model's actual IRR\u002FMOIC output — this is the proof the table is wired correctly.\n* **Highlight the center cell** — medium-blue fill (`#BDD7EE`) + bold font so the base case is visually anchored.\n* Excel's DATA TABLE function may not work with openpyxl — instead write explicit formulas that reference row\u002Fcolumn headers\n* Each cell should show a DIFFERENT value — if all same, formulas aren't varying correctly\n* Use mixed references (e.g., `$A5` for row input, `B$4` for column input)\n\n---\n\n## VERIFICATION CHECKLIST - RUN AFTER COMPLETION\n\n### Run Formula Validation\n```bash\npython \u002Fpath\u002Fto\u002Fexcel-author\u002Fscripts\u002Frecalc.py model.xlsx\n```\nMust return success with zero errors.\n\n### Section Balancing\n- [ ] Any sections that must balance (Sources\u002FUses, Assets\u002FLiabilities) balance exactly\n- [ ] Plug items are calculated correctly as the balancing figure\n- [ ] Amounts that should match across sections are consistent\n\n### Income\u002FOperating Projections\n- [ ] Revenue\u002Ftop-line builds correctly from drivers or growth rates\n- [ ] All cost and expense items calculated appropriately\n- [ ] Subtotals and totals sum correctly\n- [ ] Margins and ratios are reasonable\n- [ ] Links to assumptions are correct\n\n### Balance Sheet (if applicable)\n- [ ] Assets = Liabilities + Equity (must balance)\n- [ ] All items link to appropriate schedules or roll-forwards\n- [ ] Beginning balances = prior period ending balances\n- [ ] Check row included and shows zero\n\n### Cash Flow (if applicable)\n- [ ] Starts with correct income figure\n- [ ] Non-cash items added\u002Fsubtracted appropriately\n- [ ] Working capital changes have correct signs\n- [ ] Ending Cash = Beginning Cash + Net Cash Flow\n- [ ] Cash balances are consistent across statements\n\n### Supporting Schedules\n- [ ] Roll-forward schedules balance (Beginning + Changes = Ending)\n- [ ] Schedules link correctly to main statements\n- [ ] Calculated items use appropriate drivers\n- [ ] All periods are calculated consistently\n\n### Debt\u002FFinancing Schedules (if applicable)\n- [ ] Beginning balances tie to sources or prior period\n- [ ] Interest calculated on appropriate balance (typically beginning)\n- [ ] Paydowns respect cash availability and priority\n- [ ] Ending balances cannot be negative\n- [ ] Totals sum tranches correctly\n\n### Returns\u002FOutput Analysis\n- [ ] Exit\u002Fterminal values calculated correctly\n- [ ] All relevant adjustments included\n- [ ] Cash flow signs are correct (negative for investment, positive for proceeds)\n- [ ] IRR\u002FMOIC formulas reference complete ranges\n- [ ] Results are reasonable for the scenario\n\n### Sensitivity Tables (if applicable)\n- [ ] Grid dimensions are ODD (5×5 or 7×7) — there is a true center cell\n- [ ] Row and column axis values are symmetric around the base case (`[base-2Δ, base-Δ, base, base+Δ, base+2Δ]`)\n- [ ] Center cell output equals the model's actual IRR\u002FMOIC — confirms the table is wired correctly\n- [ ] Center cell is highlighted (medium-blue fill `#BDD7EE`, bold font)\n- [ ] Row and column headers contain appropriate input values\n- [ ] Each data cell contains a formula (not hardcoded)\n- [ ] Each data cell shows a DIFFERENT value\n- [ ] Values move in expected directions (higher exit multiple → higher IRR, etc.)\n\n### Formatting\n- [ ] Hardcoded inputs are blue (0000FF)\n- [ ] Calculated formulas are black (000000)\n- [ ] Same-tab links are purple (800080)\n- [ ] Cross-tab links are green (008000)\n- [ ] All numbers are right-aligned\n- [ ] Appropriate number formats applied throughout\n- [ ] No cells show error values (#REF!, #DIV\u002F0!, #VALUE!, #NAME?)\n\n### Logical Sanity Checks\n- [ ] Numbers are reasonable order of magnitude\n- [ ] Trends make sense (growth, decline, stabilization as expected)\n- [ ] No obviously wrong values (negative where should be positive, impossible percentages, etc.)\n- [ ] Key outputs are within reasonable ranges for the type of analysis\n\n---\n\n## COMMON ERRORS TO AVOID\n\n| Error | What Goes Wrong | How to Fix |\n|-------|-----------------|------------|\n| Hardcoding calculated values | Model doesn't update when inputs change | Always use formulas that reference source cells |\n| Wrong cell references after copying | Formulas point to wrong cells | Verify all links, use appropriate $ anchoring |\n| Circular reference errors | Model can't calculate | Use beginning balances for interest-type calcs, break the circle |\n| Sections don't balance | Totals that should match don't | Ensure one item is the plug (calculated as difference) |\n| Negative balances where impossible | Paying\u002Fusing more than available | Use MAX(0, ...) or MIN functions appropriately |\n| IRR\u002Freturn errors | Wrong signs or incomplete ranges | Check cash flow signs and ensure formula covers all periods |\n| Sensitivity table shows same value | Formula not varying with inputs | Check cell references - need mixed references ($A5, B$4) |\n| Roll-forwards don't tie | Beginning ≠ prior ending | Verify links between periods |\n| Inconsistent sign conventions | Additions become subtractions or vice versa | Follow template's convention consistently throughout |\n\n---\n\n## WORKING WITH THE USER — SECTION-BY-SECTION CHECKPOINTS\n\n* **If the template structure is unclear**, ask before proceeding\n* **If the user's requirements conflict with the template**, confirm their preference\n* **After completing each major section**, STOP and verify with the user before continuing:\n  - **After Sources & Uses** → show the balanced table, confirm the plug is correct, get sign-off before building the operating model\n  - **After Operating Model \u002F Projections** → show the projected P&L, confirm growth rates and margins look right, get sign-off before the debt schedule\n  - **After Debt Schedule** → show beginning\u002Fending balances and interest, confirm the waterfall logic, get sign-off before returns\n  - **After Returns (IRR\u002FMOIC)** → show the cash flow series and outputs, confirm signs and ranges, get sign-off before sensitivity tables\n  - **After Sensitivity Tables** → show that each cell varies, confirm the base case lands where expected\n* **If errors are found during verification**, fix them before moving to the next section\n* **Show your work** - explain key formulas or assumptions when helpful\n* **Never present a completed model without having checked in at each section** — it's faster to catch a wrong cell reference at the source than to trace it backwards from a broken IRR\n\n---\n\n**This skill produces investment banking-quality LBO models by filling templates with correct formulas, proper formatting, and validated calculations. The skill adapts to any template structure while ensuring financial accuracy and professional presentation standards.**\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","lbo","private-equity","excel","openpyxl","modeling",[37,38,39,40],"excel-author","pptx-author","dcf-model","3-statement-model",[42,43,44],"linux","macos","windows","main","eac438ea9216a7cb8a570cab803eb01eeafc6793","skills\u002Foptional\u002Ffinance\u002Flbo-model","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 lbo-model",{"tool":59,"command":60},"bunx","bunx skills add GrupoANDevelopment-m\u002Falberto-ai --skill lbo-model",{"tool":62,"command":63},"pnpm","pnpm dlx skills add GrupoANDevelopment-m\u002Falberto-ai --skill lbo-model","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Foptional\u002Ffinance\u002Flbo-model\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",[],[]]