hoavdc/CodexKit / skills/codexkit-finance-variance-story
codexkit-finance-variance-story
VerifiedAnalyze budget-versus-actual or forecast-versus-actual performance and turn finance data into a management-ready narrative using variance logic, drivers, cash impact, and forward actions. Use when finance, FP&A, or business leaders need commentary, management accounts, or performance explanation. Do not use for bookkeeping entries, tax filing preparation, or legal accounting sign-off.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.2 KB |
| agents/openai.yaml | config | 197 B |
SKILL.md
View on GitHub---
name: codexkit-finance-variance-story
description: Analyze budget-versus-actual or forecast-versus-actual performance and turn finance data into a management-ready narrative using variance logic, drivers, cash impact, and forward actions. Use when finance, FP&A, or business leaders need commentary, management accounts, or performance explanation. Do not use for bookkeeping entries, tax filing preparation, or legal accounting sign-off.
version: 1.0.0
category: knowledge
---
# Finance Variance Story
## Purpose
Convert raw financial movements into an explanation that managers can act on.
## When to use
- Actual results differ materially from budget or forecast.
- A monthly business review needs finance commentary.
- Leadership wants the story behind revenue, margin, cash, or cost movement.
## When not to use
- The request is for journal entries or bookkeeping.
- Formal statutory accounting treatment is the main question.
## Inputs
- actuals, budget, forecast, or prior-period data
- key business drivers and assumptions
- notable one-offs, mix effects, or timing issues
- audience: board, exec, functional leader, or finance team
## Procedure
1. Separate size, timing, volume, price, mix, and controllability effects where possible.
2. Identify the 3-5 drivers that actually explain most of the movement.
3. Connect the variance to cash, margin, runway, or operational implications.
4. Distinguish structural change from one-off noise.
5. Recommend actions, owners, and forecast implications.
6. Flag missing data and confidence limits.
## Output
- executive summary of the variance story
- driver table with impact and explanation
- cash and margin implications
- forward-looking actions and watchpoints
- short management commentary in plain language
## Definition of done
- A non-finance leader can understand the business story.
- The explanation distinguishes causes from symptoms.
- Recommended actions follow from the analysis.
## Examples
- "Explain why gross margin missed plan this quarter and what actions we should take."
- "Turn these budget versus actual numbers into management commentary for the board pack."
## Quality Criteria
- [ ] All claims reference specific frameworks, standards, or quantifiable data
- [ ] Content matches the stated audience's expertise level
- [ ] Recommendations are actionable — each includes a concrete next step
- [ ] No unsupported assertions or generic filler language
## Verification (4C)
| Check | Question |
|-------|----------|
| **Correctness** | Do referenced frameworks and standards match their official definitions? |
| **Completeness** | Are all key concepts covered without significant gaps for the stated audience? |
| **Context-fit** | Would this be useful for someone new to this domain, or is it too advanced/too basic? |
| **Consequence** | If a stakeholder acted on this immediately, what could they misinterpret? |
## Edge Cases
- **Conflicting frameworks** — State which framework takes precedence and why. Document the trade-off explicitly.
- **Rapidly changing domain** — Note information currency date. Flag sections likely to need updates.
- **Audience has mixed expertise levels** — Provide a glossary and mark advanced sections as optional.
## Changelog
- v1.0.0 — Initial release
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |