Lbo Model logo

Lbo Model

Community
fivetaku
lbo-model

This skill should be used when completing LBO (Leveraged Buyout) model templates in Excel for private equity transactions, deal materials, or investment committee presentations. The skill fills in formulas, validates calculations, and ensures professional formatting standards that adapt to any template structure.

Overview

Publisherfivetaku
Repositoryclaude-office-skills
Skill namelbo-model
Stars
72
Forks
11
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by fivetaku on GitHub. Read the source before you install it.

Installation

Install the Lbo Model AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/fivetaku/claude-office-skills/tree/main/claude-in-excel/lbo-model
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/fivetaku/claude-office-skills.git /tmp/claude-office-skills
mkdir -p .claude/skills
cp -r /tmp/claude-office-skills/claude-in-excel/lbo-model .claude/skills/lbo-model
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lbo Model in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Lbo Model on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Lbo Model is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

LBO Model Builder

Preflight: Dependency Check

Before starting, verify required libraries and tools are installed and install any that are missing.

bash
python3 -c "import openpyxl" 2>/dev/null || python3 -m pip install openpyxl
command -v soffice >/dev/null 2>&1 || command -v libreoffice >/dev/null 2>&1 || ls /Applications/LibreOffice.app/Contents/MacOS/soffice >/dev/null 2>&1 || echo "WARNING: LibreOffice not found. Install: brew install --cask libreoffice (macOS) or apt install libreoffice (Linux). Required for scripts/recalc.py."

Important: Do not skip this step — scripts/recalc.py is required to verify IRR/MOIC, cash sweep mechanics, and sensitivity base-case.

Scripts

  • scripts/recalc.py — Force formula recalculation via headless LibreOffice. Run after building: python scripts/recalc.py <model.xlsx>

Reference Template

A starter LBO template is bundled at lbo-model.xlsx in this skill directory. If the user does not attach their own template, reuse the bundled file structure (do not copy cell values, only the layout/section conventions).

TEMPLATE REQUIREMENT

  • If template attached → use that template's structure exactly
  • If no template → ask user, or use standard examples/LBO_Model.xlsx
  • NEVER build from scratch when template is provided

CRITICAL INSTRUCTIONS - READ FIRST

Environment: Office JS vs Python

  • Office JS: range.formulas = [["=B5*B6"]], no recalc needed
  • Python/openpyxl: ws["D20"] = "=B5*B6", run recalc.py before delivery
  • Merged cell pitfall: value to top-left first, then merge + format

Core Principles

  • Every calculation must be an Excel formula — NEVER compute in Python and hardcode
  • Use the template structure — follow existing organization
  • Work section by section, verify with user at each step

Formula Color Conventions (4-color system)

  • Blue (0000FF): Hardcoded inputs
  • Black (000000): Formulas with calculations
  • Purple (800080): Links to cells on SAME tab (direct references, no calculation)
  • Green (008000): Links to cells on DIFFERENT tabs

Fill Color Palette — Professional Blues & Greys

  • Section headers: Dark blue #1F4E79 (white bold text)
  • Column headers: Light blue #D9E1F2 (black bold text)
  • Input cells: Light grey #F2F2F2
  • Formula cells: White
  • Key outputs (IRR, MOIC): Medium blue #BDD7EE (black bold)

Number Formatting Standards

  • Currency: $#,##0;($#,##0);"-"
  • Percentages: 0.0%
  • Multiples: 0.0"x"
  • MOIC/Detailed Ratios: 0.00"x"

TEMPLATE ANALYSIS PHASE

  1. Map the structure — identify sections and relationships
  2. Understand the timeline — columns = periods, pro forma column
  3. Identify input vs formula cells — respect template conventions
  4. Read existing labels — they specify expected calculations
  5. Check for existing formulas — don't overwrite working formulas
  6. Note template-specific conventions — sign conventions, subtotal structures

FILLING FORMULAS - GENERAL APPROACH

Step 1: Check the Template (existing formula? comment? label? pattern?)

Step 2: Check the User's Instructions

Step 3: Apply Standard Practice

COMMON PROBLEM AREAS

  • Balancing Sections: Sources = Uses, one item is "plug"
  • Tax Calculations: reference income line + tax rate only
  • Interest and Circular References: use Beginning Balance to break circularity
  • Debt Paydown / Cash Sweeps: priority waterfall, MAX/MIN to prevent negative
  • Returns Calculations (IRR/MOIC): correct signs, consecutive periods
  • Sensitivity Tables: ODD dimensions, center cell = base case, #BDD7EE highlight

VERIFICATION CHECKLIST

  • Section balancing (Sources = Uses)
  • Income projections (subtotals, margins, links)
  • Balance Sheet (Assets = L+E, beginning = prior ending)
  • Cash Flow (correct signs, ending cash ties)
  • Supporting Schedules (roll-forwards balance)
  • Debt Schedule (beginning balance, interest, paydown priority)
  • Returns (IRR/MOIC correct signs and ranges)
  • Sensitivity Tables (ODD grid, center = base, all cells have formulas)
  • Formatting (blue/black/purple/green, number formats, no errors)
  • Logical Sanity Checks (magnitude, trends, reasonableness)

COMMON ERRORS TO AVOID

| Hardcoding | Wrong cell refs | Circular refs | Sections unbalanced | | Negative balances | IRR/return errors | Sensitivity same value | Roll-forwards don't tie | | Inconsistent signs |

WORKING WITH THE USER — SECTION-BY-SECTION CHECKPOINTS

  1. After Sources & Uses → confirm plug, get sign-off
  2. After Operating Model → confirm growth rates, margins
  3. After Debt Schedule → confirm waterfall logic
  4. After Returns (IRR/MOIC) → confirm cash flow signs
  5. After Sensitivity Tables → confirm base case lands correctly

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Lbo Model AI skill do?

This skill should be used when completing LBO (Leveraged Buyout) model templates in Excel for private equity transactions, deal materials, or investment committee presentations. The skill fills in formulas, validates calculations, and ensures professional formatting standards that adapt to any template structure.

Why use Lbo Model on TypingMind?

Because you install it once and use it with any model. Lbo Model is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Lbo Model in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/fivetaku/claude-office-skills/tree/main/claude-in-excel/lbo-model. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Lbo Model?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Lbo Model?

As many as you like. As long as a model supports skills, you can use Lbo Model with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Lbo Model AI skill free?

It is published on GitHub by fivetaku. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇