forecast-modeling
Use when designing, tuning, or auditing revenue forecast models.
When & Why to Use This Skill
This Claude skill provides a comprehensive framework for designing, tuning, and auditing revenue forecast models. It enables businesses to establish robust forecasting methodologies, map key drivers such as win rates and churn, and perform sensitivity analysis through scenario planning to ensure financial accuracy and strategic alignment.
Use Cases
- Strategic Planning: Running scenario planning (base, upside, and downside cases) ahead of board meetings or budget cycles to evaluate financial impact and sensitivity.
- Performance Auditing: Auditing deviations between forecasted revenue, sales pipeline, and actual results to identify methodology gaps and improve data integrity.
- Methodology Design: Launching new forecasting cadences by selecting appropriate models—such as bottom-up CRM, top-down macro, or cohort-based—and documenting core assumptions.
- Operational Sensitivity Analysis: Automating 'what-if' questions during executive reviews by adjusting levers like pricing, seasonality, and sales velocity to see real-time impacts.
| name | forecast-modeling |
|---|---|
| description | Use when designing, tuning, or auditing revenue forecast models. |
Forecast Modeling System Skill
When to Use
- Launching new forecasting cadences or revisiting methodology.
- Running scenario planning ahead of board meetings or budget cycles.
- Auditing deviations between forecast, pipeline, and actuals.
Framework
- Method Selection – pick bottom-up CRM, top-down macro, cohort, or blended models and document assumptions.
- Driver Mapping – define win rates, velocity, expansion, churn, pricing, and seasonality inputs.
- Scenario Logic – establish base/upside/downside cases with tunable levers for sensitivity analysis.
- Model Governance – list data sources, refresh cadence, validation checks, and ownership.
- Output Packaging – standardize tables, charts, and narrative prompts for exec review.
Templates
- Driver tree diagram connecting levers to KPIs.
- Scenario sheet (assumption → base/upside/downside values).
- Model QA checklist (data freshness, formula audits, version history).
Tips
- Keep raw inputs + assumptions in version control for auditability.
- Pair with
variance-analysisskill to recalibrate after each cycle. - Automate sensitivity runs to answer "what-if" questions during reviews.