Open finance skill
Charts for the monthly finance review
How should finance data be visualized so an owner can make a decision quickly?
Create cash-flow, margin, working-capital and budget-comparison charts from verified tables. Working-capital charts show balances such as unpaid customer invoices and supplier bills. Keep labels and source notes clear enough for an owner to decide what to do.
Records you need
- ✓Verified finance table
- ✓Units and periods
- ✓Decision question
What you get
- ✓Data arranged for charts
- ✓Notes explaining the owner’s decision
- ✓Source table
Checks performed
- ✓Missing periods stay visible
- ✓Actual and forecast labels
- ✓Charts match their source tables
From finding to decision
The chart must show the same signs and dates as its source.
A chart can look polished while a loss points upward or forecasts look like actual results. Compare the finished chart with its source table.
- Check units, positive and negative signs, periods and actual-versus-forecast labels in the source table.
- Inspect positive and negative values in the finished chart, including the exported PDF.
- Explain the cause and decision without removing a qualification that changes their meaning.
Evidence ready for review
Every visible value and direction agrees with the source table and stated units.
Who makes the next decision?
The owner sees the decision and remaining uncertainty without reconstructing the workbook.
Collect the supporting records from your software
Level diagnostic method reviewed . Apply it to the selected records and accounting policy; the teaching example does not resolve a live account.
Guided synthetic example
See the check from input to decision
An owner needs to see the cash trough and margin decline without reading a dense workbook.
How review effort might be shared
An illustrative allocation is 15% collecting records, 20% applying checks, 10% flagging results, 25% investigating reasons, 20% finance review and 10% choosing an action. These percentages were not measured across engagements. Actual effort varies with data quality, complexity and the issue found.
Start with the source records
| Series | June actual | July actual | August forecast |
|---|---|---|---|
| Ending cash | $180,000 | $132,000 | $86,000 |
| Gross margin | 42% | 38% | 37% |
| AR over 60 days | $22,000 | $35,000 | $41,000 |
Apply the documented check
Preserve table values, label actual versus forecast, select compatible units, and annotate the decision-relevant movement.
Surface the flagged result
Needs review
The chart pack shows actual cash declining from $180,000 in June to $132,000 in July, with August forecast cash of $86,000 below an assumed $100,000 management cash buffer. Margin declines and older AR grows in this separate synthetic scenario.
Use recorded finance judgment to analyze possible reasons
At Level, we record the review logic, known explanations, and questions our finance professionals use in this situation. AI applies that documented human judgment to organize the most plausible reasons, without pretending it knows which reason is true.
Possible reasons to investigate
The visual connects movements but does not prove that collections or margin caused the cash decline.
Make the final human judgment
In a Level engagement, a Level finance professional validates the source evidence, challenges the AI-assisted analysis, and decides which explanation is supported.
Make the operating decision
Use the chart to focus the meeting, then validate the underlying drivers in the source schedules.
Each skill uses an independent synthetic scenario. Shared month labels do not mean the examples describe one company or a single financial period.
Use this system
Start with the example, then inspect the structure
The JSON download is a sample record file to inspect with an AI assistant or developer. It is not a file to upload into your accounting software.
- Download the invented input and expected output.
- Replace one field at a time with a safe test value.
- Compare the result with the expected structure.
- Have a finance professional review every exception before acting.
Website example JSON and registry: CC BY 4.0 (attribution required). Downloadable toolkit ZIP: MIT. Each version identifies its own frozen examples.
Developer preview: AI-assistant helper (MCP)
This tool call returns fixed, invented sample records only. It does not connect to your books. Read the setup instructions.
run_synthetic_example {"slug":"cfo-chart-pack"}Human review is part of the system
This check organizes evidence and surfaces exceptions. A person with finance domain expertise still needs to interpret the result, validate the source records, and discuss the operating decision.
Open source does not mean open client data. We publish reusable finance tools, checks, templates, and playbooks. Client records, workpapers, credentials, communications, and private configurations remain confidential.
Use it yourself, or bring us the messy part
Get a one-page plan for checking your records
Tell us where the records stop making sense. We will reply with the first check to run, the records it needs, and the decision that still needs human finance judgment.
Install the free skills yourself