What does this skill do?

The Variance Analysis skill helps an agent decompose financial variances into their drivers, with narrative explanations and waterfall analysis, for budget-vs-actual and period-over-period changes.

It applies decomposition techniques — price/volume, rate/mix, headcount/compensation, and spend-category — and uses materiality thresholds to focus on the variances that matter.

It generates clear, causal variance narratives and text or chart waterfall bridges, and supports budget-vs-actual-vs-forecast comparisons. It assists with the analysis and does not provide financial advice.

  • Decomposes variances into quantified drivers

  • Applies materiality thresholds and investigation priorities

  • Generates specific, causal variance commentary

  • Builds waterfall bridges that reconcile to the total

How it works

1

Set the comparison

The agent takes the line item, period, and comparison basis — budget, forecast, prior period, or prior year.

2

Decompose the variance

It applies the right technique — price/volume, rate/mix, headcount/comp, or spend-category — and quantifies each driver.

3

Apply materiality

It uses threshold frameworks to prioritize the largest, unexpected, or trending variances for explanation.

4

Explain and bridge

It writes specific, causal narratives and builds a waterfall bridge that reconciles from the base to the actual.

Best use cases for this skill

  • Budget vs actual: Explain why actuals differ from budget by driver.

  • Board commentary: Prepare concise, causal variance commentary for leadership.

  • Revenue bridges: Build a waterfall from budget to actual revenue.

  • Forecast review: Compare budget, forecast, and actuals and assess accuracy.

Frequently asked questions

What does the Variance Analysis skill do?

It decomposes financial variances into drivers with narrative explanations and waterfall analysis, for budget vs. actual, period-over-period, and forecast comparisons.

Is it financial advice?

No. It assists with variance-analysis workflows and does not provide financial advice; analyses should be reviewed by qualified financial professionals before use in reporting.

How does it decide what to explain?

It uses materiality thresholds and an investigation priority — largest dollar and percentage variances, unexpected directions, and trending variances.

What makes a good variance narrative?

One that is specific, quantified, causal, forward-looking, actionable, and concise — naming the actual driver, not just 'higher than expected'.

Use from source

Ask your Buda agent to install this community skill.

Copy this prompt into your own Buda agent. It includes the source repository and install command so the agent can complete the setup in natural language.

Prompt to send to your Buda agent
Please install the "Variance Analysis Skill" skill into this Buda agent.

Source repository: https://github.com/anthropics/knowledge-work-plugins
Install command: npx skills add anthropics/knowledge-work-plugins --skill variance-analysis -y -a universal

Please run the install command, verify the skill is available, and tell me any setup notes or follow-up steps from the source repository.
Explore marketplace

Install workflow

  1. 1Copy the prompt
  2. 2Send it to your Buda agent
  3. 3Done