home / skills / gtmagents / gtm-agents / forecast-modeling

forecast-modeling skill

safe

/plugins/revenue-forecasting-pipeline/skills/forecast-modeling

This skill helps design, tune, and audit revenue forecast models using scenario analysis, driver mapping, and governance for executive-ready outputs.

npx playbooks add skill gtmagents/gtm-agents --skill forecast-modeling

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

1.3 KB

---
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
1. **Method Selection** – pick bottom-up CRM, top-down macro, cohort, or blended models and document assumptions.
2. **Driver Mapping** – define win rates, velocity, expansion, churn, pricing, and seasonality inputs.
3. **Scenario Logic** – establish base/upside/downside cases with tunable levers for sensitivity analysis.
4. **Model Governance** – list data sources, refresh cadence, validation checks, and ownership.
5. **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-analysis` skill to recalibrate after each cycle.
- Automate sensitivity runs to answer "what-if" questions during reviews.

---

Overview

This skill helps design, tune, and audit revenue forecast models for sales, marketing, customer success, and revenue operations. It provides a practical framework, templates, and checks to move forecasts from ad-hoc spreadsheets to governed, repeatable models. Use it to standardize assumptions, run scenarios, and present defensible outputs to executives.

How this skill works

The skill guides you through method selection (bottom-up, top-down, cohort, or blended), maps model drivers (win rates, velocity, expansion, churn, pricing, seasonality), and codifies scenario logic for base/upside/downside cases. It includes governance steps: data source inventory, refresh cadence, validation checks, and ownership. Templates and QA checklists help package outputs as standardized tables, charts, and narratives for review.

When to use it

Launching a new forecasting cadence or revising methodology
Preparing scenario analysis for board meetings or budget cycles
Auditing deviations between forecast, pipeline, and actuals
Tuning levers during quarter planning or reforecasting
Establishing model governance and version control

Best practices

Select and document one primary forecasting method and when blended approaches apply
Map driver trees so each KPI links to a measurable input or data source
Keep raw inputs and assumptions in version control for auditability
Automate sensitivity runs to support rapid what-if analysis
Define validation checks and a refresh cadence before relying on outputs

Example use cases

Build a bottom-up CRM forecast with win-rate and velocity drivers to justify next quarter targets
Create base/upside/downside scenarios for a board pack and quantify revenue variance ranges
Audit an existing model: validate data freshness, test formulas, and reconcile to actuals
Run automated sensitivity sweeps on pricing or churn to inform pricing experiments
Package standardized charts and narrative prompts for executive review and decision-making

FAQ

What forecasting method should I start with?

Choose bottom-up CRM if pipeline data is reliable; use top-down macro when market indicators drive outcomes; blend when neither alone captures your business dynamics.

How do I keep forecasts auditable?

Store raw inputs and documented assumptions in version control, maintain a change log, and run the model QA checklist each cycle.