financial-modeling
Skill1 starsChanged 7 months agoMITView on GitHub
Build financial models including DCF, LBO, comparable company analysis, and sensitivity analysis. Use when valuing a company or asset, evaluating an acquisition, building a three-statement model, or stress-testing assumptions. Trigger with "financial model", "DCF", "valuation", "LBO model", "comparable analysis", "comps", or "sensitivity analysis".
8 other projects use a version of this.
Adopted by
Most recently taken up by
- anotb/management-consulting-plugintheir own version, first seen Nov 1, 2026
- KMaruthi2002/universal-llm-skillstheir own version, first seen Oct 25, 2026
- poorvith-mp/skills-financetheir own version, first seen Oct 11, 2026
- ZeroTokenClaw/agents-skillstheir own version, first seen Sep 21, 2026
- magnus919/agent-skillstheir own version, first seen Jul 21, 2026
- claude-office-skills/claude-office-plugintheir own version, first seen Mar 9, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- claude-office-skills/skills★ 433same name
- magnus919/agent-skills★ 177same name
- anotb/management-consulting-plugin★ 62same name
- claude-office-skills/claude-office-plugin★ 9same name
- elvismusli/business-validator★ 1same name
- KMaruthi2002/universal-llm-skills★ 1same name
- poorvith-mp/skills-finance★ 1same name
- ZeroTokenClaw/agents-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository164 other files it gives its agents.
- instrument-data-to-allotropeSkill
- literature-reviewSkill
- nextflow-developmentSkill
- scientific-problem-selectionSkill
- scvi-toolsSkill
- single-cell-rna-qcSkill
- discover-brandSkill
- enforce-voiceSkill
- generate-guidelinesSkill
- csat-reportSkill
- customer-escalationSkill
- customer-researchSkill
- draft-responseSkill
- kb-articleSkill
- sentiment-analysisSkill
- ticket-triageSkill
- analyzeSkill
- build-dashboardSkill
- create-vizSkill
- data-context-extractorSkill
- data-modelingSkill
- data-pipelineSkill
- etl-designSkill
- explore-dataSkill
- sql-queriesSkill
- statistical-analysisSkill
- validate-dataSkill
- write-querySkill
- accessibility-reviewSkill
- component-librarySkill
- design-critiqueSkill
- design-handoffSkill
- design-systemSkill
- frontend-designSkill
- research-synthesisSkill
- user-researchSkill
- ux-copySkill
- wireframingSkill
- Agent DevelopmentSkill
- CLAUDE.md ManagementSkill
- MCP Server BuilderSkill
- Plugin DevelopmentSkill
- Prompt EngineeringSkill
- Skill CreatorSkill
- curriculum-designSkill
- lesson-planningSkill
- quiz-generatorSkill
- study-guideSkill
- tutoringSkill
- api-designSkill
- architectureSkill
- ci-cd-pipelineSkill
- code-reviewSkill
- database-migrationSkill
- debugSkill
- dependency-auditSkill
- deploy-checklistSkill
- documentationSkill
- error-handlingSkill
- git-workflowSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 163
Always clearly state and document every assumption.
- Distinctive: line 164
Use terminal value sanity checks: terminal value should be 50-80% of total enterprise value in most DCFs.
- Distinctive: line 170
Keep formatting consistent: units, decimal places, and sign conventions should be uniform throughout.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Financial Modeling
Build structured financial models: discounted cash flow (DCF), leveraged buyout (LBO), comparable company analysis, three-statement models, and sensitivity/scenario analysis.
Workflow
Step 1: Define Model Scope and Purpose
Clarify the modeling objective:
- Model type: DCF, LBO, comps, three-statement integrated, or merger model.
- Subject: The company, division, or asset being modeled.
- Purpose: Valuation for M&A, investment decision, fundraising, strategic planning, or board presentation.
- Time horizon: Typically 5-10 years for DCF; 3-7 years for LBO.
- Level of detail: High-level (revenue and EBITDA) or granular (unit economics, cohort analysis).
Step 2: Build the Revenue and Operating Model
Construct the top-line and operating assumptions:
Revenue Drivers:
- Revenue by segment or product line.
- Growth rates (organic vs. inorganic).
- Key volume and pricing assumptions.
- Customer metrics (new, retained, churned) if applicable.
Operating Model:
- Cost of revenue and gross margin trajectory.
- Operating expense build (fixed vs. variable components).
- EBITDA and EBIT margins over the projection period.
- Working capital assumptions (DSO, DPO, DSI).
- Capital expenditure as % of revenue.
Step 3: Build the Valuation
Discounted Cash Flow (DCF):
- Project unlevered free cash flow (UFCF) for the explicit period.
- UFCF = EBIT x (1 - tax rate) + D&A - CapEx - change in NWC.
- Calculate terminal value using either:
- Exit multiple method: terminal year EBITDA x exit multiple.
- Perpetuity growth method: final year FCF x (1 + g) / (WACC - g).
- Discount all cash flows to present value using WACC.
- Sum PV of explicit period + PV of terminal value = enterprise value.
- Subtract net debt, add cash = equity value. Divide by shares = per-share value.
Comparable Company Analysis:
- Select 6-10 comparable public companies.
- Calculate trading multiples: EV/Revenue, EV/EBITDA, EV/EBIT, P/E.
- Apply relevant multiples to the subject company's metrics.
- Present a valuation range using mean, median, and selected multiple.
LBO Model:
- Sources and uses of funds (equity, debt tranches, cash on balance sheet).
- Project operating performance and debt paydown schedule.
- Model the exit at a target year and exit multiple.
- Calculate returns: IRR and MOIC (multiple on invested capital).
- Sensitivity on entry multiple, exit multiple, and revenue growth.
Step 4: Sensitivity and Scenario Analysis
Build sensitivity tables on the key value drivers:
Two-variable sensitivity table (e.g., WACC vs. terminal growth rate for DCF):
- Show the implied valuation at each intersection.
- Highlight the base case.
Scenario analysis:
- Bull case: optimistic assumptions on growth, margins, multiples.
- Base case: management plan or consensus estimates.
- Bear case: stress-tested assumptions with downside risks.
Step 5: Present the Output
Format the model output for the intended audience.
Output Format
## Financial Model: [Company/Asset] | [Model Type]
### Key Assumptions
| Assumption | Year 1 | Year 2 | Year 3 | Year 4 | Year 5 |
|---------------------------|--------|--------|--------|--------|--------|
| Revenue ($M) | 50.0 | 62.5 | 78.1 | 93.8 | 109.4 |
| Revenue growth | 25% | 25% | 25% | 20% | 17% |
| Gross margin | 65% | 66% | 67% | 68% | 68% |
| EBITDA margin | 15% | 18% | 22% | 25% | 27% |
| CapEx (% of revenue) | 5% | 5% | 4% | 4% | 3% |
### DCF Valuation
| Component | Amount ($M) |
|-----------------------------------|-------------|
| PV of explicit period FCFs | $45.2 |
| PV of terminal value | $120.8 |
| Enterprise value | $166.0 |
| Less: net debt | ($15.0) |
| Equity value | $151.0 |
| Shares outstanding (M) | 10.0 |
| **Implied price per share** | **$15.10** |
### Sensitivity: Enterprise Value ($M)
| WACC \ Terminal Growth | 2.0% | 2.5% | 3.0% | 3.5% |
|------------------------|--------|--------|--------|--------|
| 9.0% | $185 | $195 | $208 | $224 |
| 10.0% | $162 | $170 | $179 | $190 |
| 11.0% | $143 | $149 | $156 | **$166**|
| 12.0% | $128 | $133 | $139 | $146 |
### Comparable Companies
| Company | EV/Rev | EV/EBITDA | Revenue Growth | EBITDA Margin |
|-------------|--------|-----------|----------------|---------------|
| Comp A | 5.2x | 18.5x | 22% | 28% |
| Comp B | 4.8x | 16.2x | 18% | 30% |
| Median | 5.0x | 17.4x | 20% | 29% |
| **Implied** | $250M | $174M | | |
### Valuation Summary
| Methodology | Low | Mid | High |
|--------------------|----------|----------|----------|
| DCF | $140M | $166M | $195M |
| Comps (EV/EBITDA) | $155M | $174M | $195M |
| Comps (EV/Revenue) | $200M | $250M | $300M |
| **Blended range** | **$155M**| **$190M**| **$230M**|Examples
User: "Build a DCF for a SaaS company growing 25% with 65% gross margins" Action: Build the 5-year projection, calculate UFCF, apply a WACC, compute terminal value, and produce the sensitivity table.
User: "What's a reasonable valuation range using public comps?" Action: Select comparable companies, calculate trading multiples, apply to the subject company, and present the range.
User: "Model an LBO at 5x EBITDA entry with 60/40 debt-equity split" Action: Build sources and uses, project cash flows and debt paydown, model exit scenarios, and calculate IRR/MOIC.
Best Practices
- Always clearly state and document every assumption. Models are only as good as their inputs.
- Use terminal value sanity checks: terminal value should be 50-80% of total enterprise value in most DCFs. If it exceeds 85%, the explicit period projections may be too conservative.
- Cross-check DCF results against comparable multiples. Wide divergence suggests an assumption issue.
- For WACC, use the subject's capital structure or target structure, not the modeler's preference.
- Build in error checks: balance sheet must balance, cash flow must tie, growth rates must be internally consistent.
- Present a range, never a single point estimate. Precision implies false confidence.
- Label all outputs as illustrative when using assumed data rather than actual financials.
- Keep formatting consistent: units, decimal places, and sign conventions should be uniform throughout.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

