- Home
- Skills
- Finance & Accounting
- project finance modeler
Works with the AI Agents you already use
project finance modeler
Infrastructure and energy projects require rigorous debt modeling, yet manual spreadsheets are prone to calculation errors in the cash waterfall and debt service reserve accounts.
$1
project finance modeler
Example session with this skill installed
Model a 24-month solar build. Capex: 10M per 6mo. Revenue: 5M/period. Debt: 70% share, 5% interest, 10-period annuity repayment. 6mo DSRA target. Run a 10% revenue shortfall scenario.
- Read your context and instructions
- Compiled the project finance modeler
I have processed the financing terms for the solar project build. The deterministic engine has computed the base case and the requested revenue shortfall scenario.
Project Finance Model — Solar Project, 2023-10-27
1. Scope, sources and assumptions
- Sources: E1 (User provided budget/terms)
- Currency: USD (unscaled)
- Frequency: Semi-annual (2 periods/year)
- Repayment: Annuity
- Assumptions: Tax, refinancing, and working capital are not modelled.
2. Funding and construction
| Item | Amount |
|---|---|
| Total Construction Uses | 20,750,000.00 |
| Interest During Construction | 750,000.00 |
| Senior Debt at COD | 14,525,000.00 |
| Equity Contributed | 6,225,000.00 |
| Implied Gearing | 70.00% |
3. Cash waterfall and integrity checks
| Period | CFADS | Interest | Principal | Reserve balance | Distribution | Closing cash | Debt balance |
|---|---|---|---|---|---|---|---|
| 1 | 5,000,000 | 363,125 | 1,290,000 | 826,562 | 2,520,313 | 0 | 13,235,000 |
| 2 | 5,000,000 | 330,875 | 1,322,250 | 826,562 | 2,520,313 | 0 | 11,912,750 |
[...truncated for example...]
- Checks: Sources equal uses. Distributions remain within permitted cash limits.
4. Debt service coverage
- Min DSCR: 3.024
- Average DSCR: 3.024
- LLCR at COD: 2.850
- Min LLCR: 2.850
5. Scenarios
| Scenario | Debt at COD | Min DSCR | LLCR at COD | Equity IRR | Distributions | Breaches |
|---|---|---|---|---|---|---|
| Base Case | 14,525,000 | 3.024 | 2.850 | 12.4% | 25,203,130 | 0 |
| Revenue -10% | 14,525,000 | 2.721 | 2.565 | 10.1% | 22,682,817 | 0 |
6. Covenant and liquidity alerts
- All covenants passed.
- Reserve account fully funded by Period 1.
7. Feasibility memorandum and items for human review
- Computed result: Project maintains a healthy DSCR above 2.7x even in stress scenarios.
Analytical estimate — validation required: The 70% gearing is consistent with similar renewable assets but requires lender confirmation.
- Management decision required: Final approval of the debt sizing and equity commitment.
This analysis supports, and does not replace, professional judgment and management's decision.
Next steps
- Validate the capex draw schedule with the EPC contractor.
- Confirm the 5% interest rate assumption with potential lenders.
- Review the DSRA funding timing relative to COD.
Connects securely to your tools. The creator never sees your data.
About this skill
Infrastructure and energy projects require rigorous debt modeling, yet manual spreadsheets are prone to calculation errors in the cash waterfall and debt service reserve accounts. This skill automates the creation of a compact project finance model using a deterministic script to ensure exact decimal precision for senior debt tranches and covenant testing.
What it does
- Construction funding computes interest during construction (IDC) and tracks sources and uses across the construction schedule.
- Debt sculpting models one senior tranche with annuity, equal-principal, or sculpted repayment profiles.
- Cash waterfall executes a fixed-order waterfall including CFADS, debt service, reserve funding, and equity distributions.
- Covenant tracking monitors DSCR, LLCR, and lock-up breaches with automated alerts for reserve shortfalls.
- Stress testing runs exact scenarios for construction delays, cost overruns, and revenue shortfalls.
How it works
- Data ingestion reads project budgets, schedules, and financing terms, assigning evidence markers to every input.
- Schema validation builds a
request.jsonfollowing a strict schema to ensure all required fields for periodicity and gearing are present. - Deterministic calculation executes the
run.pyscript to compute the model without manual rounding or estimation. - Report generation produces a structured memorandum covering funding, coverage ratios, and covenant integrity checks.
Frameworks & tools
The skill utilizes a custom Python-based calculation engine (run.py) for deterministic financial logic, ensuring accuracy that matches professional banking models.
Why this beats prompting it yourself
Generic LLMs frequently fail at multi-period debt sculpting and waterfall logic, often hallucinating interest calculations or ignoring reserve account constraints. This skill uses a hardened script to perform the actual math, ensuring ratios like DSCR and LLCR are mathematically sound and verifiable.
Use cases
- Model construction funding and interest during construction from a budget and schedule.
- Compute DSCR, LLCR and project and equity IRR for one senior debt tranche.
- Test delay, overrun and revenue shortfall scenarios and their covenant alerts.
- Audit the impact of ramp-up periods and revenue escalation on debt service capacity.
Known limitations
Does not support multiple debt tranches, refinancing, tax modeling, working capital, or maintenance reserves. Limited to two periods per year (semi-annual).
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Finance & Accounting.
Supports only one senior debt tranche and two periods per year. No support for tax modeling, refinancing, or working capital. All inputs must be user-provided.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 days ago