Skip to content
Automation
Skill

/variance-analysis

Use to attribute forecast vs actual deltas and recommend remediation

From plugin
gtm-agents
368200 skills200 agents199 commands
Install
$ npx -y skills add gtmagents/gtm-agents --skill variance-analysis --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/variance-analysis

Context preview

The summary Claude sees to decide when to auto-load this skill.

Use to attribute forecast vs actual deltas and recommend remediation

SKILL.md

variance-analysis.SKILL.md
name: variance-analysis
description: Use to attribute forecast vs actual deltas and recommend remediation
  actions.

Revenue Variance Analysis Skill

When to Use

  • Preparing forecast reviews or board updates that require variance explanations.
  • Investigating misses/exceeds across segments, products, or channels.
  • Prioritizing remediation plays tied to specific variance drivers.

Framework

1. **Driver Taxonomy** – classify deltas into volume, conversion, price/mix, churn, expansion, currency. 2. **Attribution Logic** – define formulas for each driver and maintain consistent baselines. 3. **Root Cause Layer** – connect drivers to operational issues (pipeline quality, capacity, enablement, macro). 4. **Action Mapping** – translate each root cause into specific plays with owners and expected impact. 5. **Feedback Loop** – update forecasting assumptions once variance is understood.

Templates

  • Variance waterfall chart setup instructions.
  • Driver worksheet (metric → delta → driver → root cause → owner → due date).
  • Remediation tracker with status and forecast impact.

Tips

  • Keep a glossary so stakeholders interpret drivers consistently.
  • Combine quantitative attribution with qualitative context from GTM leaders.
  • Feed learnings back to `forecast-modeling` to tighten assumptions next cycle.

---

Ships withgtm-agents

Free AI automation for sales, marketing, and growth teams. No coding required.

Get the whole plugin