finance-model

Build an integrated multi-year financial model — P&L, best, base and worst cases, valuation by multiples and DCF, and a sensitivity matrix — on top of the plan, forecast and budget. Use when the user

SKILL.md

GitHub

Model

Build the financial model for "$ARGUMENTS". Create an integrated model with scenario analysis, valuation, and sensitivity testing to support decision-making and fundraising.

Arguments. $ARGUMENTS may contain the project name and optional flags. Take the first token as <project> and treat --skip-checks as a flag; never include flags in file paths. All paths below use <project>. If --skip-checks is present, skip the prerequisite check and, before writing any artifact, append one line to .singularskills/log.jsonl: {"ts":"<ISO timestamp>","skill":"finance-model","workflow":"finance","phase":5,"project":"<project>","event":"skipped","artifact":"05-model.md","note":"<reason or \"none given\">"}.

Compute with code. Perform every calculation (totals, balances, ratios, variances, projections) with a script — Bash, Python or a spreadsheet formula written to a file — and include the computation alongside the result. Never do arithmetic mentally.

Prerequisites

Part of a workflow. This skill is phase 5 (Model) of the FP&A workflow (finance); cross-domain workflows run it too. First check .singularskills/log.jsonl for an open run for this project: a run-started line with "project":"<project>" and no later run-finished line for the same workflow and project. If one exists, the conductor is running you: continue here. Otherwise, if the user asked to start, run, continue or resume a process or workflow rather than this one step, do not continue here: invoke the workflow skill with the workflow the user asked for, or finance when they named none, followed by <project>; it runs this phase in order, asks before it writes and records the run. Otherwise continue here: a later phase runs on its own, behind its gate.

Run this skill's gate before writing: sh <this skill's folder>/scripts/gate.sh <project> <project root>, where <project root> is the folder that contains .singularskills/ (use . when you are already there). If it exits non-zero, stop and tell the user what it printed, unless --skip-checks was given (see Arguments). On a refusal, before you stop, append this line to .singularskills/log.jsonl (create the folder and file if missing): {"ts":"<ISO timestamp>","skill":"finance-model","workflow":"finance","phase":5,"project":"<project>","event":"refused","artifact":"05-model.md","note":"<what the gate printed>"}. Once the gate has passed, or under --skip-checks once you have appended the skipped line, append this line before you start work: {"ts":"<ISO timestamp>","skill":"finance-model","workflow":"finance","phase":5,"project":"<project>","event":"started","artifact":"05-model.md","note":""}.

Read .singularskills/finance/<project>/04-budget.md. If this file does not exist, tell the user:

Phase 4 (Budget) has not been completed for "<project>". Run /finance-budget <project> first, or use --skip-checks to bypass.

Process

  1. Read context:

    • Read .singularskills/finance/<project>/01-assess.md through 04-budget.md for complete financial picture
    • Reference references/financial-model-template.md for scenario table structure
  2. Build integrated P&L model:

    • Revenue model with driver-based projections
    • COGS and gross profit
    • Operating expenses by category
    • EBITDA and net income
    • Project 3-5 years with monthly detail for year 1
  3. Build scenario models:

    • Base case: aligned with the forecast and budget
    • Best case: upside assumptions (faster growth, better margins)
    • Worst case: downside assumptions (slower growth, higher costs, churn)
    • For each scenario: revenue, expenses, cash flow, runway, break-even
    • Reference references/financial-model-template.md for scenario table format
  4. Valuation analysis (if applicable):

    • Revenue multiples (based on comparable companies)
    • DCF analysis with WACC assumptions
    • Last-round valuation and implied metrics
    • Cap table impact of future fundraising scenarios
  5. Sensitivity analysis:

    • Identify the 5-8 variables with the most impact
    • Show how changes in each variable affect key outputs
    • Create tornado chart data (which inputs swing outcomes most)
  6. Write the artifact to .singularskills/finance/<project>/05-model.md with sections:

    • Integrated P&L — multi-year income statement
    • Scenario Analysis — best/base/worst case summaries
    • Valuation — multiples, DCF, and comparable analysis
    • Sensitivity Matrix — variable impact on key metrics
    • Model Assumptions Log — every input and its source/rationale

Output

The model written to .singularskills/finance/<project>/05-model.md. Present a summary highlighting:

  • Base case P&L trajectory
  • Scenario range (worst to best)
  • Valuation range
  • Most sensitive variables

Record the run. After you have written the artifact, append this line to .singularskills/log.jsonl (the started line of Prerequisites, with "event":"finished"): {"ts":"<ISO timestamp>","skill":"finance-model","workflow":"finance","phase":5,"project":"<project>","event":"finished","artifact":"05-model.md","note":""}.

Open the artifact with this frontmatter (agent is the agent you run in, or unknown; gate is passed when the gate ran clean and skipped under --skip-checks):

---
skill: finance-model
workflow: finance
phase: 5
project: <project>
started: <ISO timestamp>
finished: <ISO timestamp>
agent: <the agent you run in, or "unknown">
gate: <passed|skipped>
---

End the artifact with ## Decisions and ## Open questions, in this shape:

## Decisions
- <what was chosen> — <why> — <what was rejected>

## Open questions
- <what the next phase or a reviewer must settle>

End the artifact with this paragraph, verbatim:

Not financial or tax advice. This artifact is generated analysis for review by a qualified accountant or financial professional before any filing, reporting or decision relies on it.