Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Reconcile accounts by comparing GL balances to subledgers, bank statements, or third-party data. Use when performing bank reconciliations, GL-to-subledger recs, intercompany reconciliations, or identifying and categorizing reconciling items.
.claude/skills/evolution-foundation-fin-reconciliation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 68% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 104% | 0% |
Important: This skill assists with reconciliation workflows but does not provide financial advice. All reconciliations should be reviewed by qualified financial professionals before sign-off.
Methodology and best practices for account reconciliation, including GL-to-subledger, bank reconciliations, and intercompany. Covers reconciling item categorization, aging analysis, and escalation.
Compare the general ledger control account balance to the detailed subledger balance.
Common accounts:
Process:
Common causes of differences:
Compare the GL cash balance to the bank statement balance.
Process:
Standard format:
Balance per bank statement: $XX,XXX
Add: Deposits in transit $X,XXX
Less: Outstanding checks ($X,XXX)
Add/Less: Bank errors $X,XXX
Adjusted bank balance: $XX,XXX
Balance per general ledger: $XX,XXX
Add: Interest/credits not recorded $X,XXX
Less: Bank fees not recorded ($X,XXX)
Add/Less: GL errors $X,XXX
Adjusted GL balance: $XX,XXX
Difference: $0.00Reconcile balances between related entities to ensure they net to zero on consolidation.
Process:
Common causes of differences:
Items that exist because of normal processing timing and will clear without action:
Expected resolution: These items should clear within the normal processing cycle (typically 1-5 business days). No adjusting entry needed.
Items that require a journal entry to correct:
Action: Prepare adjusting journal entry to correct the GL or subledger.
Items that cannot be immediately explained:
Action: Investigate root cause, document findings, escalate if unresolved.
Track the age of reconciling items to identify stale items requiring escalation:
| Age Bucket | Status | Action | |-----------|--------|--------| | 0-30 days | Current | Monitor — within normal processing cycle | | 31-60 days | Aging | Investigate — follow up on why item has not cleared | | 61-90 days | Overdue | Escalate — notify supervisor, document investigation | | 90+ days | Stale | Escalate to management — potential write-off or adjustment needed |
| Item # | Description | Amount | Date Originated | Age (Days) | Category | Status | Owner | |--------|-------------|--------|-----------------|------------|----------|--------|-------| | 1 | Detail] | $X,XXX | Date] | XX | Type] | Status] | Name] |
Track reconciling item totals over time to identify growing balances:
Define escalation triggers based on your organization's risk tolerance:
| Trigger | Threshold (Example) | Escalation | |---------|---------------------|------------| | Individual item amount | > $10,000 | Supervisor review | | Individual item amount | > $50,000 | Controller review | | Total reconciling items | > $100,000 | Controller review | | Item age | > 60 days | Supervisor follow-up | | Item age | > 90 days | Controller / management review | | Unreconciled difference | Any amount | Cannot close — must resolve or document | | Growing trend | 3+ consecutive periods | Process improvement investigation |
Note: Set thresholds based on your organization's materiality level and risk appetite. The examples above are illustrative.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→pass | 9,244 | 4,255 | -54% | 1 | 1 | 0% | 1,449 | 2,438 | +68% | 0 | 0 | — |
case-05 | fail→pass | 7,903 | 3,502 | -56% | 1 | 1 | 0% | 1,321 | 2,231 | +69% | 0 | 0 | — |
case-01 | fail→fail | 13,252 | 14,057 | +6% | 1 | 1 | 0% | 2,500 | 4,336 | +73% | 0 | 0 | — |
case-02 | pass→pass | 6,815 | 5,132 | -25% | 1 | 1 | 0% | 1,403 | 2,687 | +92% | 0 | 0 | — |
case-03 | fail→pass | 11,616 | 9,182 | -21% | 1 | 1 | 0% | 1,848 | 3,210 | +74% | 0 | 0 | — |
case-06 | fail→pass | 10,655 | 5,115 | -52% | 1 | 1 | 0% | 1,759 | 2,480 | +41% | 0 | 0 | — |
case-07 | pass→pass | 11,207 | 7,214 | -36% | 1 | 1 | 0% | 1,896 | 2,901 | +53% | 0 | 0 | — |
case-08 | pass→pass | 11,512 | 7,847 | -32% | 1 | 1 | 0% | 1,887 | 3,002 | +59% | 0 | 0 | — |
case-09 | pass→pass | 14,443 | 11,400 | -21% | 1 | 1 | 0% | 2,187 | 3,266 | +49% | 0 | 0 | — |
case-10 | pass→pass | 11,913 | 8,957 | -25% | 1 | 1 | 0% | 1,658 | 3,074 | +85% | 0 | 0 | — |
case-11 | pass→pass | 8,065 | 7,036 | -13% | 1 | 1 | 0% | 1,301 | 2,754 | +112% | 0 | 0 | — |
case-12 | fail→pass | 9,596 | 9,748 | +2% | 1 | 1 | 0% | 1,614 | 3,295 | +104% | 0 | 0 | — |
case-13 | fail→pass | 5,588 | 3,784 | -32% | 1 | 1 | 0% | 938 | 2,231 | +138% | 0 | 0 | — |
case-14 | fail→pass | 6,104 | 6,374 | +4% | 1 | 1 | 0% | 956 | 2,636 | +176% | 0 | 0 | — |
case-15 | pass→pass | 6,365 | 6,340 | -0% | 1 | 1 | 0% | 1,039 | 2,731 | +163% | 0 | 0 | — |
case-16 | pass→pass | 13,202 | 10,372 | -21% | 1 | 1 | 0% | 1,942 | 3,217 | +66% | 0 | 0 | — |
case-17 | pass→pass | 10,722 | 6,253 | -42% | 1 | 1 | 0% | 1,707 | 2,636 | +54% | 0 | 0 | — |
case-18 | pass→pass | 5,207 | 5,542 | +6% | 1 | 1 | 0% | 864 | 2,720 | +215% | 0 | 0 | — |
case-19 | pass→pass | 7,478 | 5,671 | -24% | 1 | 1 | 0% | 1,214 | 2,547 | +110% | 0 | 0 | — |
case-20 | pass→pass | 8,235 | 7,967 | -3% | 1 | 1 | 0% | 1,618 | 3,228 | +100% | 0 | 0 | — |
case-21 | pass→pass | 18,407 | 17,772 | -3% | 1 | 1 | 0% | 3,086 | 4,805 | +56% | 0 | 0 | — |
case-22 | pass→pass | 9,418 | 9,922 | +5% | 1 | 1 | 0% | 1,632 | 3,332 | +104% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +32 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.