What does this skill do, and when should you use it?
This skill builds on the OfficeCLI xlsx skill to enable AI agents to build decision-grade financial models that output a single formula-driven .xlsx file. It introduces a mandatory three-zone architecture (Inputs/Calc/Outputs) to separate assumptions from derivations. Three model recipes are provided: 3-statement, DCF, and LBO, along with sensitivity and scenario protocols. It inherits the xlsx skill's visual standards, such as a four-color coding scheme and number formatting. Installation is straightforward via a command-line script.
Recognizes intent to build a financial model (e.g., 3-statement, DCF, LBO). Creates an Excel workbook with Assumptions, Calc, and Outputs zones. Automates styling (colors, number formats). Builds detailed financial models (3-statement, DCF, LBO) using formulas and named ranges. Runs audit checks to ensure balance and consistency. Executes cache-refresh passes to ensure correct rendering in other viewers.
- An investment banking analyst needs to quickly build a 3-statement model for an M&A deal.
- A private equity analyst builds an LBO model to assess investment returns.
- A startup CFO creates a DCF valuation to support fundraising.
- A financial advisor conducts sensitivity analysis to assess impact of key drivers.
- A corporate finance team automates generation of financial forecasts and budgets.
How do you install this skill?
- The skill's install commands (curl/irm) download and execute binaries from external sources, posing supply chain risks without checksum verification; use in controlled environments or verify downloads.
- Since the skill operates on top of officecli-xlsx, it performs extensive file system writes; ensure user awareness and confirmation.
- Many commands rely on external tools (e.g., jq) without version specification, which may cause environment compatibility issues.
- The skill targets financial models and may be triggered in inappropriate contexts (e.g., simple budget sheets); accurate trigger boundary understanding is required by the dispatcher.
- Shell / CLI
curl
Install the OfficeCLI binary: on macOS/Linux curl -fsSL https://d.officecli.ai/install.sh | bash, on Windows PowerShell irm https://d.officecli.ai/install.ps1 | iex. Verify with officecli --version. The skill is bundled with OfficeCLI.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/iOfficeAI/OfficeCLI.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/officecli-financial-model" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Build a DCF model
- Create a 3-statement model.
Ensure OfficeCLI is installed. Place the skill file (this SKILL.md) in your agent's skills directory. Use financial-modeling keywords in your prompt, such as 'Build a DCF model' or 'Create a 3-statement model.' The agent will follow the skill's instructions automatically.
What are this skill's strengths and limitations?
- Provides a standardized structure for financial models, ensuring auditability
- Supports complex financial functions like NPV, IRR, and XIRR
- Automatically caches values for correct display in other tools
- Rigorous audit gates ensure model accuracy
- Open source and no Office installation required
- Requires command-line proficiency
- Only supports Excel, not other spreadsheet software
- Advanced features like Data Tables are not supported and need workarounds
- May have a learning curve for non-technical finance users
- Dependent on ongoing maintenance and updates of OfficeCLI
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| OfficeCLI Financial Modeling Skill this page | 53 · Use with care | ★ 32k | 5d ago | Apache-2.0 |
| DCF Valuation Model Builder ✓ Anthropic · Official | 45 · Not recommended | ★ 39k | 20d ago | Apache-2.0 |
| StockValuation.io Local Valuation Workflow | 58 · Recommended | ★ 33 | 27d ago | Apache-2.0 |
| Three-Statement Model Builder ✓ Anthropic · Official | 55 · Use with care | ★ 39k | 20d ago | Apache-2.0 |
| 3-Statements-Ultra | 55 · Use with care | ★ 85 | 4mo ago | — |
Compared to libraries like python-docx/openpyxl, OfficeCLI offers a more streamlined CLI that is better suited for AI agents.
How did FollowSkills review this skill?
This skill acts as a scene layer on top of officecli-xlsx, and while it does not directly perform file system operations, it inherits install commands (curl/irm) that download external binaries and execute them via pipe, posing supply chain risks without checksum verification. User confirmation mechanisms are not explicitly documented, though scope boundaries are clear (not for simple budgets) and data flow is disclosed. However, dynamic code execution and external tool dependencies warrant deductions, and the publisher is unverified. Overall score: 13.
The skill provides detailed step-by-step commands and build orders, but references numerous placeholders (e.g., row numbers need substitution) and depends on inherited officecli-xlsx rules, making standalone reproduction unreliable. Static review cannot execute verification, and no tests or error handling specific to this skill are provided. Failure feedback (e.g., balance checks) offers basic diagnostics but relies on external tools (jq) and a specific environment. Therefore, score: 8.
The skill has clear scenarios, distinguishes financial models from simple tables, has explicit trigger phrases, and indicates non-fit cases. However, it is specialized for Excel financial modeling, requires a base officecli-xlsx skill, and environment fit (e.g., mainland China network) is not explicitly addressed; Chinese-language support is not explicitly verified. Score: 12.
Documentation is well-structured with progressive disclosure (inherits xlsx rules), includes installation instructions, recipes, and verification steps, but lacks version history, changelog, and explicit maintenance responsibility (only mentions unverified publisher). Numerous placeholders in code blocks may cause operational ambiguity. License is clear (Apache-2.0), but update path is not mentioned. Score: 12.
The skill's value proposition is clear, claiming to produce decision-grade financial models, but static review cannot verify output correctness. It provides detailed recipes and verification steps, but no actual output examples or third-party validation. Therefore, value proposition remains unverified, and considering static limitations, score: 5.
CI workflows exist (build and npm publish), but they only cover basic document creation, not the financial-model recipes. There is no test suite specific to this skill. Thus, key claims lack verifiable evidence, relying only on author documentation and marketing. Score: 3.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →