hoavdc/CodexKit / skills/codexkit-budget-variance-explainer
codexkit-budget-variance-explainer
VerifiedTurn raw budget-versus-actual data into plain-language explanations for non-finance managers. Focus on why numbers moved, what it means for the team, and what action to take — without requiring accounting knowledge. Use when managers need to understand their cost center performance. Do not use for technical accounting analysis, tax preparation, or external audit deliverables.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.5 KB |
| agents/openai.yaml | config | 177 B |
SKILL.md
View on GitHub---
name: codexkit-budget-variance-explainer
description: Turn raw budget-versus-actual data into plain-language explanations for non-finance managers. Focus on why numbers moved, what it means for the team, and what action to take — without requiring accounting knowledge. Use when managers need to understand their cost center performance. Do not use for technical accounting analysis, tax preparation, or external audit deliverables.
version: 1.0.0
category: data
---
# Budget Variance Explainer
## Purpose
Make budget data understandable for non-finance managers so they can act on it.
## When to use
- a team lead receives budget vs actual numbers and needs to understand them
- a department manager needs to explain their cost center to leadership
- monthly or quarterly financial reviews for non-finance stakeholders
- translating finance team output into operational language
## When not to use
- technical accounting analysis or journal entries
- external audit preparation or regulatory reporting
- when the variance requires forensic investigation
## Inputs
- budget vs actual data (table, spreadsheet extract, or raw numbers)
- time period (month, quarter, YTD)
- any known context (e.g. "we hired 2 extra people" or "project X was delayed")
- audience (team lead, VP, non-finance manager)
## Procedure
1. Identify the top 3–5 variances by absolute dollar impact.
2. Classify each: favorable or unfavorable.
3. Explain WHY each variance happened in one sentence (driver).
4. Determine if the variance is one-time or recurring.
5. Suggest what action to take for each significant variance.
6. Write a 2-sentence headline summary suitable for an exec email.
7. Produce an action table: driver → impact → owner → action.
## Output
- headline summary (2 sentences)
- variance explanation table (line item, variance, driver, one-time/recurring, action)
- recommended talking points for presenting to leadership
## Definition of done
- every variance > 5% is explained
- explanations use business language, not accounting jargon
- each significant variance has an owner and recommended action
- a non-finance person can understand the summary without follow-up questions
## Examples
- "Explain why our department is $30K over budget this month in plain English."
- "Turn this spreadsheet into talking points for the VP meeting."
- "Our travel spend is 40% over plan — write an explanation and recommended action."
## Quality Criteria
- [ ] Data sources and assumptions are explicitly stated
- [ ] Calculations are reproducible from provided inputs
- [ ] Visualizations or tables have clear labels, units, and time ranges
- [ ] Caveats and confidence levels are documented for estimates
## Verification (4C)
| Check | Question |
|-------|----------|
| **Correctness** | Are formulas, aggregations, and statistical methods applied correctly? |
| **Completeness** | Does the analysis cover all requested metrics and time ranges? |
| **Context-fit** | Are the chosen metrics relevant to the business question being answered? |
| **Consequence** | If this data were used for a decision today, what blind spots remain? |
## Edge Cases
- **Missing or incomplete data** — Document gaps and their potential impact on conclusions. Provide ranges instead of point estimates.
- **Outliers skewing results** — Report with and without outliers. Document the decision to include or exclude.
- **Changing data definitions mid-period** — Split analysis at the change boundary and note the schema difference.
## Changelog
- v1.0.0 — Initial release
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |