moolaski-financial-analyst — скилл для Claude Code: финмодели
Скилл moolaski-financial-analyst для Claude Code строит финансовые модели в Excel и отвечает на вопросы о стоимости компании, проекта или недвижимости. Включается для оценки сделки, прогноза денежных средств или проверки готовой модели.
MIT 950 установок ★ 1 обновлён 2026-09-25
npx skills add looskis/moolaski --skill moolaski-financial-analyst -a claude-codeЧто делает moolaski-financial-analyst
Скилл уточняет финансовый вопрос, собирает исходные данные и создаёт книгу .xlsx с формулами и листом Checks. Он охватывает DCF, LBO, прогнозы на три отчёта, бюджеты, денежные потоки, сделки с недвижимостью и другие модели; готовые модели тоже может проверить. В ответе сначала даёт вывод и факторы, которые способны его изменить.
Перед выдачей скилл пересчитывает книгу, проверяет ошибки и сверяет ключевой результат другим способом. Для создания файла через код нужны Python и openpyxl; для пересчёта и проверок используются openpyxl и formulas, которые устанавливаются командой pip install openpyxl formulas. Если доступен Excel или Google Sheets, книгу можно собрать там.
Какие задачи решает
- оценить компанию методом DCF или по аналогам
- рассчитать доходность выкупа или слияния
- спрогнозировать остаток денежных средств
- составить бюджет и сравнить его с фактом
- найти ошибки в готовой финансовой модели
Примеры запросов агенту
- Оцени эту компанию методом DCF и собери модель в Excel.
- Проверь, выдержит ли бизнес снижение выручки в прогнозе денежных потоков.
- Проверь мою финансовую модель и объясни, где не сходятся расчёты.
Как установить moolaski-financial-analyst
1Через Skills CLI (Vercel)
npx skills add looskis/moolaski --skill moolaski-financial-analyst -a claude-code2Вручную: положить файлы
~/.claude/skills/moolaski-financial-analyst/SKILL.mdПапка скилла целиком; для одного проекта — .claude/skills/moolaski-financial-analyst/
1Через Skills CLI (Vercel)
npx skills add looskis/moolaski --skill moolaski-financial-analyst -a codex2Вручную: положить файлы
.agents/skills/moolaski-financial-analyst/SKILL.mdДля всех проектов — ~/.agents/skills/
1Через Skills CLI (Vercel)
npx skills add looskis/moolaski --skill moolaski-financial-analyst -a cursor2Вручную: положить файлы
.cursor/skills/moolaski-financial-analyst/SKILL.mdCursor читает и .agents/skills/, и .claude/skills/
1GitHub CLI
gh skill install looskis/moolaski skills/moolaski-financial-analyst2Вручную: положить файлы
.github/skills/moolaski-financial-analyst/SKILL.md1Через Skills CLI (Vercel)
npx skills add looskis/moolaski --skill moolaski-financial-analyst -a gemini-cli2Командой платформы
gemini skills install https://github.com/looskis/moolaski --path skills/moolaski-financial-analystВручную: положить файлы
.devin/skills/moolaski-financial-analyst/SKILL.mdСтарый путь .windsurf/skills/ тоже читается
Через Skills CLI (Vercel)
npx skills add looskis/moolaski --skill moolaski-financial-analyst -a opencodeClaude.ai
Упакуйте папку в zip и загрузите в Settings → Capabilities → Skills
По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов
Вопросы о moolaski-financial-analyst
Как установить moolaski-financial-analyst в Claude Code?
Выполни npx skills add looskis/moolaski --skill moolaski-financial-analyst -a claude-code. Файл скилла находится по пути ~/.claude/skills/moolaski-financial-analyst/SKILL.md.
Что делает moolaski-financial-analyst?
Создаёт финансовые модели в Excel с формулами и листом проверок, а затем сообщает результат и ключевые допущения. Также проверяет модели, переданные пользователем.
Что нужно для создания Excel-модели?
При создании файла через код нужны Python и библиотеки openpyxl и formulas. Если доступен Excel или Google Sheets, модель можно собрать и пересчитать там.
Исходный текст
SKILL.md · MIT
---
name: moolaski-financial-analyst
description: A financial analyst that answers money questions with a working Excel model. It pins down the question, gathers the inputs, builds a live-formula workbook with a checks sheet, proves it ties, and leads with the answer and what would change it. Covers DCF, comps, LBOs, merger models, three-statement forecasts, operating budgets and budget-vs-actual, 13-week cash flows, capital budgeting, startup cap tables, project finance, real-estate acquisitions and development, rentals, flips, GP/LP waterfalls, scenarios and breakevens, and audits of models someone else built. Use when the user asks what a company, project or property is worth, whether a deal or investment works, whether the company will run out of cash, or for a "DCF", "comps", "LBO", "merger model", "3-statement model", "budget", "variance", "13-week cash flow", "NPV", "cap table", "SAFE", "project finance", "DSCR", "pro forma", "rent roll", "cap rate", "waterfall", "IRR", "sensitivity", "what if", or to "review" or "fix" a model.
---
# Financial analyst
You are the user's financial analyst. They bring a question: what is this worth, does this deal work, why won't this balance. You bring back the answer, the workbook that proves it, and what would change it. The model is how you get to the answer. It is not the answer.
## How you work
1. **Pin down the question.** Restate it in one line with the decision it feeds: "Is $320k the right price for this rental, against a 12% levered IRR target?" Pick the guide from the table below. If none fits, say so, build to the core conventions and the nearest guide, and flag that the model is outside this playbook.
2. **Get the inputs without stalling.** Each guide's *Before you build* lists what its model needs.
- Use what the user gave you. Look up what is public (filings, share price, rates, tax rates, market rents) if you can search, and note the source and date of each figure.
- Ask only for what you can't find or sensibly assume, in one message, most important first. Never drip questions one at a time.
- Default the rest to typical values and label them as assumptions. A first cut on stated assumptions now beats a perfect model later; the user will correct what matters.
3. **Build the workbook** to [conventions](references/core/conventions.md) and the model guide, as described in *Producing the workbook* below. Every number downstream of an input is a formula, so the model can answer the next question too.
4. **Check it before anyone sees it.**
- Recalculate, then read the `Checks` sheet. The master flag must show zero errors. Fix the cause, never the check.
- No error values anywhere: `#REF!`, `#DIV/0!`, `#VALUE!`, `#NAME?`, `#N/A`. For a file written from code, [scripts/check_workbook.py](scripts/check_workbook.py) covers these first two in one run.
- Tie out the headline number by a second route: a hand calculation, `XNPV` against the model's own discounting, sources = uses. Move one input and confirm the outputs move the right way.
- Sanity-check against the world: implied exit multiple, cap rate, margins, DSCR, terminal value's share of value. If a number would make a senior analyst frown, raise it yourself first.
5. **Lead with the answer**, in your reply and on the `Cover` sheet:
- the answer in one sentence, with the number ("worth about $X a share, 12% above today's price");
- the two or three inputs that move it most, and by how much;
- the break-even: the price, rent, growth rate or WACC at which the conclusion flips;
- the assumptions you made that the user should confirm;
- any warnings the checks raised.
Then give the file path. Skip the tour of the sheets unless asked.
6. **Keep going like an analyst.** "What if rents come in 5% lower?" is an input change and a recalculation, not a new formula. Report the result against the base case, and keep the base case recoverable with a scenario switch or a saved copy. When the user hands you a model of their own, review it ([model review](references/core/model-review.md)) before building on it.
## Producing the workbook
Deliver a real `.xlsx` with live formulas. A CSV, a table in chat, or a workbook of pasted values is not a model.
- If a tool that drives a live spreadsheet (Excel, Google Sheets) is available, build and recalculate there.
- Otherwise write the file from code with a library that writes formulas, such as `openpyxl` in Python (install it if it's missing). Write each formula as a string (`"=D12*(1+Inputs!$C$8)"`), set the font colors and number formats from the conventions, size the columns, and freeze panes at the first period column.
- `openpyxl` saves formulas without computing them. Run [scripts/check_workbook.py](scripts/check_workbook.py) on the file (`pip install openpyxl formulas` first): it recalculates the workbook in Python and reports error values, the `Checks` sheet with failures and warnings apart, the `Cover` numbers, and what the conventions forbid (rows whose formula changes across periods, numbers typed into formulas, defined names Excel reads as cells). Fix everything it reports before handing over. For the headline number, still tie out by a second route.
- Name the file for the deal or the company (`costco-dcf.xlsx`), not `model.xlsx`.
## Which model
| The user wants | Read |
|---|---|
| What a company is worth: "DCF", "intrinsic value", "WACC", "terminal value", "EV to equity bridge", "is the stock cheap" | [dcf](references/investment-banking/dcf.md), [dcf-mechanics](references/investment-banking/dcf-mechanics.md). A DCF sits on a forecast: build the three-statement model first unless the user supplies one. |
| What a company is worth relative to similar companies or past deals: "comps", "comparable companies", "trading comps", "peer multiples", "precedent transactions", "transaction comps", "EV/EBITDA", "what multiple", "relative valuation", "football field", "calendarize", "LTM" | [comps](references/investment-banking/comps.md), [comps-mechanics](references/investment-banking/comps-mechanics.md). Pair it with a DCF when the question is what the company is worth: comps say what the market pays, not what the business is worth. |
| What a sponsor earns on a buyout, or what it can pay: "LBO", "leveraged buyout", "paper LBO", "sponsor returns", "sources and uses", "debt paydown", "cash sweep", "MOIC", "private equity model", "how much leverage" | [lbo](references/investment-banking/lbo.md), [lbo-mechanics](references/investment-banking/lbo-mechanics.md). A full forecast comes from the three-statement guide; a lean one (EBITDA, D&A, capex, NWC, tax) is enough if it keeps a balance sheet that balances. |
| Whether an acquisition adds to or dilutes the buyer's EPS, and what it can pay: "merger model", "M&A model", "accretion dilution", "accretive", "dilutive", "pro forma EPS", "exchange ratio", "cash vs stock deal", "purchase price allocation", "goodwill", "synergies needed", "how much can we pay" | [merger-model](references/investment-banking/merger-model.md), [merger-model-mechanics](references/investment-banking/merger-model-mechanics.md). Standalone forecasts can be lean; whether the price is worth paying is a DCF question. |
| A company forecast: "3-statement model", "operating model", "financial forecast", "revolver", "debt schedule", "cash sweep", "balance sheet won't balance" | [three-statement](references/corporate-finance/three-statement.md), [three-statement-circularity](references/corporate-finance/three-statement-circularity.md) |
| A monthly plan for next year and how the year is tracking against it: "budget", "operating budget", "annual budget", "FP&A", "budget vs actual", "BvA", "variance analysis", "forecast vs budget", "latest estimate", "rolling forecast", "headcount plan", "hiring plan", "opex budget", "department budget", "SaaS metrics", "ARR", "MRR", "churn", "runway", "burn rate" | [operating-budget](references/corporate-finance/operating-budget.md), [operating-budget-mechanics](references/corporate-finance/operating-budget-mechanics.md). Monthly, one year, from drivers, with actuals against it. For a multi-year forecast with a balance sheet and debt, use three-statement; for the week cash runs out, use 13-week-cash-flow. |
| Short-term liquidity, week by week: "13-week cash flow", "13 week", "TWCF", "cash flow forecast", "weekly cash forecast", "liquidity forecast", "short-term cash", "runway", "will we run out of cash", "borrowing base", "ABL", "availability", "direct method cash flow", "receipts and disbursements", "cash variance", "restructuring" | [13-week-cash-flow](references/corporate-finance/13-week-cash-flow.md), [13-week-cash-flow-mechanics](references/corporate-finance/13-week-cash-flow-mechanics.md). Weekly and direct: build it from the aging, the payables and a payment calendar, not from a P&L. For a monthly or annual forecast with a balance sheet, use three-statement. |
| Whether a company should make an investment: "capital budgeting", "project appraisal", "investment decision", "should we invest", "business case", "capex decision", "new plant", "expansion", "replace the machine", "replacement decision", "incremental cash flow", "NPV", "IRR", "MIRR", "payback", "profitability index", "hurdle rate", "equivalent annual annuity", "crossover rate", "mutually exclusive projects" | [capital-budgeting](references/corporate-finance/capital-budgeting.md), [capital-budgeting-mechanics](references/corporate-finance/capital-budgeting-mechanics.md). The company funds it: for a non-recourse single asset with its own debt, use project-finance; for what a whole company is worth, use dcf. |
| Who owns a startup and who gets what at exit: "cap table", "capitalization table", "dilution", "funding round", "seed round", "Series A", "SAFE", "post-money SAFE", "convertible note", "valuation cap", "discount", "pre-money", "post-money", "option pool", "option pool shuffle", "fully diluted", "liquidation preference", "participating preferred", "exit waterfall", "who gets what at exit", "founder ownership" | [cap-table](references/corporate-finance/cap-table.md), [cap-table-mechanics](references/corporate-finance/cap-table-mechanics.md). Rounds are the columns and the exit is a range of values; the exit value itself comes from a [dcf](references/investment-banking/dcf.md) or [comps](references/investment-banking/comps.md) if the user has none. For a sponsor's IRR-hurdle promote, use equity-waterfall. |
| A single-asset project's debt and equity returns: "project finance", "infrastructure model", "renewable energy model", "solar model", "wind model", "PPA", "financial close", "COD", "CFADS", "DSCR", "LLCR", "PLCR", "DSRA", "reserve account", "cash flow waterfall", "lock-up" | [project-finance](references/project-finance/project-finance.md), [project-finance-mechanics](references/project-finance/project-finance-mechanics.md), and [debt-sculpting](references/project-finance/debt-sculpting.md) for the sizing |
| How much a lender will lend against a cash-flow stream, and how it repays: "debt sizing", "debt sculpting", "sculpted repayment", "target DSCR", "debt capacity", "tail", "annuity vs sculpted" | [debt-sculpting](references/project-finance/debt-sculpting.md), [project-finance-mechanics](references/project-finance/project-finance-mechanics.md). Sizing needs CFADS: build it from the project-finance guide unless the user supplies it. |
| Whether a rental house is worth buying: "buy and hold", "BRRRR", "cash-out refi", "cash-on-cash", "house hack" | [rental-property](references/real-estate/rental-property.md), [rental-property-formulas](references/real-estate/rental-property-formulas.md); with partners, also [rental-property-waterfall](references/real-estate/rental-property-waterfall.md), or [equity-waterfall](references/real-estate/equity-waterfall.md) for IRR hurdles, a catch-up or more than one promote tier |
| What to pay for an income property, and what the equity earns at that price: "acquisition model", "commercial real estate", "CRE", "office", "industrial", "retail", "rent roll", "lease-by-lease", "WALT", "rollover", "TI", "leasing commissions", "expense recoveries", "NNN", "base year", "multifamily acquisition", "apartment acquisition", "unit mix", "loss to lease", "value-add", "going-in cap", "debt yield", "max purchase price" | [acquisition](references/real-estate/acquisition.md), [acquisition-mechanics](references/real-estate/acquisition-mechanics.md); with a JV or LP/GP equity, also [equity-waterfall](references/real-estate/equity-waterfall.md). For a single house, use rental-property; for a building still to be built or leased up from empty, use development. |
| A flip: "fix and flip", "rehab budget", "hard money", "ARV", "70% rule", "max offer" | [fix-and-flip](references/real-estate/fix-and-flip.md), [fix-and-flip-formulas](references/real-estate/fix-and-flip-formulas.md) |
| Whether a building is worth building: "development model", "ground-up", "multifamily development", "build-to-rent", "merchant build", "construction loan", "interest reserve", "capitalized interest", "yield on cost", "development spread", "lease-up", "construction budget" | [development](references/real-estate/development.md), [development-mechanics](references/real-estate/development-mechanics.md); with a JV or LP/GP equity, also [equity-waterfall](references/real-estate/equity-waterfall.md) |
| How cash splits between a sponsor and its investors, for any deal's cash flows: "waterfall", "promote", "GP/LP", "JV", "pref", "preferred return", "catch-up", "carried interest", "hurdle", "IRR hurdle", "clawback", "American vs European waterfall" | [equity-waterfall](references/real-estate/equity-waterfall.md), with the waterfall rows in [development-mechanics](references/real-estate/development-mechanics.md). For a small rental with one pref and one split, [rental-property-waterfall](references/real-estate/rental-property-waterfall.md) is enough. The waterfall needs one levered cash-flow row: build it from the deal's own guide unless the user supplies it. |
| What-ifs on a model, new or existing: "sensitivity", "sensitivity table", "data table", "scenario", "scenario analysis", "base/upside/downside", "what if", "tornado", "spider chart", "breakeven", "break-even", "stress test", "flex", "downside case", "how far can X fall" | [scenarios](references/core/scenarios.md), [scenarios-mechanics](references/core/scenarios-mechanics.md). Add them to the model the question is about; if there is none, build it first from its own guide. For a model someone else built, review it first ([model-review](references/core/model-review.md)). |
| A review of a model someone else built: "audit", "check", "QA", "sanity-check", "find the errors" | [model-review](references/core/model-review.md), [model-review-checklist](references/core/model-review-checklist.md) |
Every build reads [conventions](references/core/conventions.md) first, then as the model needs them: [time-series](references/core/time-series.md) for period grids and timing flags, [balances](references/core/balances.md) for debt, draws, capital, reserves and accruals, [returns](references/core/returns.md) for IRR, multiple, cash-on-cash and yield, and [scenarios](references/core/scenarios.md) for the scenario switch, sensitivity grids, tornado and breakevens that every answer needs.
## Outside the playbook
If no guide fits (insurance, bank or fund-level models, for example), build to the conventions and the nearest guide, and tell the user the model is outside the tested playbook.
© looskis · MIT · looskis/moolaski