ReddRadar
Agent skill
financial-model-validator
Validates financial model assumptions, checks formula integrity, stress tests scenarios
Install this agent skill to your Project
npx add-skill https://github.com/a5c-ai/babysitter/tree/main/library/specializations/domains/business/venture-capital/skills/financial-model-validator
Metadata
Additional technical details for this skill
- domain
- business
- skill id
- vc-skill-010
- specialization
- venture-capital
SKILL.md
Financial Model Validator
Overview
The Financial Model Validator skill provides systematic validation of financial models submitted during due diligence. It checks assumption reasonableness, validates formula integrity, and stress tests scenarios to assess model reliability and identify risks.
Capabilities
Assumption Validation
- Check revenue assumptions against market data
- Validate cost structure assumptions
- Assess headcount and hiring plan reasonability
- Compare unit economics to industry benchmarks
Formula Integrity Checking
- Detect circular references and errors
- Validate calculation accuracy
- Check balance sheet balancing
- Verify cash flow statement tie-outs
Stress Testing
- Run downside scenario analyses
- Test assumption sensitivity
- Model cash runway under stress
- Identify breaking point assumptions
Benchmark Comparison
- Compare projections to comparable companies
- Assess growth rate reasonability by stage
- Benchmark margins and efficiency metrics
- Validate working capital assumptions
Usage
Validate Financial Model
Input: Financial model file, validation parameters
Process: Parse model, run validation checks
Output: Validation report, issues identified
Check Assumptions
Input: Model assumptions, market data, benchmarks
Process: Compare against reasonable ranges
Output: Assumption assessment, flags and concerns
Stress Test Scenarios
Input: Base case model, stress parameters
Process: Apply stress scenarios, calculate impacts
Output: Stress test results, runway analysis
Benchmark Model
Input: Financial projections, comparable set
Process: Compare against benchmarks
Output: Benchmark comparison, outlier identification
Validation Checklist
| Category | Key Checks |
|---|---|
| Revenue | Growth rates, pricing trends, customer assumptions |
| Costs | Gross margin trends, opex scaling, headcount costs |
| Working Capital | AR/AP days, inventory, payment terms |
| Cash Flow | Capex, debt service, runway calculation |
| Structure | Formula accuracy, circular refs, balance |
Integration Points
- Financial Due Diligence: Core validation for financial DD
- DCF Modeler: Validate models used in DCF analysis
- Scenario Modeler: Feed validated base case into scenarios
- Financial Analyst (Agent): Support analyst validation work
Common Issues Detected
- Unrealistic revenue growth hockey sticks
- Margin expansion without clear drivers
- Understated headcount requirements
- Missing or understated working capital needs
- Circular references in model logic
- Hard-coded values hiding assumptions
Best Practices
- Always validate against source data where possible
- Check model against historical actuals
- Run multiple stress scenarios
- Document all validation findings
- Request model walkthrough with management
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
a5c-ai/babysitter
gsd-tools
Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).
a5c-ai/babysitter
model-profile-resolution
Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role.
a5c-ai/babysitter
verification-suite
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.
a5c-ai/babysitter
state-management
STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.
a5c-ai/babysitter
git-integration
Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.
a5c-ai/babysitter
frontmatter-parsing
YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.
Didn't find tool you were looking for?