Help us improve
Share bugs, ideas, or general feedback.
From finance
Decompose variances into drivers with narrative explanations and waterfall analysis
npx claudepluginhub 8gg-git/claude --plugin financeHow this command is triggered — by the user, by Claude, or both
Slash command
/finance:variance-analysis <line item> <period> vs <comparison>The summary Claude sees in its command listing — used to decide when to auto-load this command
# Variance / Flux Analysis > If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../CONNECTORS.md). **Important**: This command assists with variance analysis workflows but does not provide financial advice. All analyses should be reviewed by qualified financial professionals before use in reporting. Decompose variances into underlying drivers, provide narrative explanations for significant variances, and generate waterfall analysis. ## Usage ### Arguments - `area` — The area to analyze: - `revenue` — Revenue variance by stream, produ...
/rental-varianceDecomposes rental revenue variance into rate, area, and term components from Excel/CSV or lease documents, producing a detailed breakdown report.
/budget-reviewAnalyzes marketing budget performance for a <review-period>, tracking spend vs. actuals, ROI by channel/campaign, variance, and generating Markdown reports with optimization recommendations and forecasts.
/ftk-mom-reportPerforms autonomous analysis of specified environment for last fiscal month with next-month forecast, generating a professional demo report.
/financial-summaryGenerates a narrative financial summary from raw data, including period overview, trends, action items, and key metrics in plain language.
/budget-narrativeGenerates professional budget narratives and financial summaries for property board review, including variance explanations and assessment impact analysis.
/unit-economicsAnalyzes unit economics metrics including ARR cohorts, LTV/CAC ratio, retention, and net retention for a specified company or data file.
Share bugs, ideas, or general feedback.
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Important: This command assists with variance analysis workflows but does not provide financial advice. All analyses should be reviewed by qualified financial professionals before use in reporting.
Decompose variances into underlying drivers, provide narrative explanations for significant variances, and generate waterfall analysis.
/flux <area> <period-comparison>
area — The area to analyze:
revenue — Revenue variance by stream, product, geography, customer segmentopex — Operating expense variance by category, department, cost centercapex — Capital expenditure variance vs budget by project and asset classheadcount — Headcount and compensation variance by department and role levelcogs or cost-of-revenue — Cost of revenue variance by componentgross-margin — Gross margin analysis with mix and rate effectsperiod-comparison — The periods to compare. Formats:
2024-12 vs 2024-11 — Month over month2024-12 vs 2023-12 — Year over year2024-Q4 vs 2024-Q3 — Quarter over quarter2024-12 vs budget — Actual vs budget2024-12 vs forecast — Actual vs forecast2024-Q4 vs 2024-Q3 vs 2023-Q4 — Three-way comparisonIf ~~erp or ~~data warehouse is connected:
If no data source is connected:
Connect ~~erp or ~~data warehouse to pull financial data automatically. To analyze manually, provide:
- Actual data for both comparison periods (at account or line-item detail)
- Budget/forecast data (if comparing to plan)
- Any operational metrics that drive the financial results (headcount, volumes, pricing, etc.)
VARIANCE SUMMARY: [Area] — [Period 1] vs [Period 2]
Period 1 Period 2 Variance ($) Variance (%)
-------- -------- ------------ ------------
Total [Area] $XX,XXX $XX,XXX $X,XXX X.X%
Break down the total variance into constituent drivers. Use the appropriate decomposition method for the area:
Revenue Decomposition:
Operating Expense Decomposition:
CapEx Decomposition:
Headcount Decomposition:
Generate a text-based waterfall showing how each driver contributes to the total variance:
WATERFALL: [Area] — [Period 1] vs [Period 2]
[Period 2 Base] $XX,XXX
|
|--[+] [Driver 1 description] +$X,XXX
|--[+] [Driver 2 description] +$X,XXX
|--[-] [Driver 3 description] -$X,XXX
|--[+] [Driver 4 description] +$X,XXX
|--[-] [Driver 5 description] -$X,XXX
|
[Period 1 Actual] $XX,XXX
Variance Reconciliation:
Driver 1: +$X,XXX (XX% of total variance)
Driver 2: +$X,XXX (XX% of total variance)
Driver 3: -$X,XXX (XX% of total variance)
Driver 4: +$X,XXX (XX% of total variance)
Driver 5: -$X,XXX (XX% of total variance)
Unexplained: $X,XXX (XX% of total variance)
--------
Total: $X,XXX (100%)
For each significant driver, generate a narrative explanation:
[Driver name] — [Favorable/Unfavorable] variance of $X,XXX (X.X%)
[2-3 sentence explanation of what caused this variance, referencing specific operational factors, business events, or decisions. Include quantification where possible.]
Outlook: [Whether this is expected to continue, reverse, or change in future periods]
If the decomposition does not fully explain the total variance, flag the residual:
Unexplained variance: $X,XXX (X.X% of total)
Possible causes to investigate:
- [Suggested area 1]
- [Suggested area 2]
- [Suggested area 3]
Ask the user for additional context on unexplained variances:
Provide: