Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Diagnose and fix common Fondo issues including integration sync failures, categorization errors, and R&D credit qualification problems. Trigger: "fondo error", "fondo sync issue", "fondo not syncing", "fondo problem".
.claude/skills/jeremylongshore-fondo-common-errors/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -39% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -20% | 0% |
Quick reference for common Fondo platform issues and their resolutions.
| Issue | Cause | Solution | |-------|-------|----------| | Bank transactions not appearing | Plaid connection expired | Dashboard > Integrations > Re-connect bank | | Gusto data stale | OAuth token expired (90-day limit) | Re-authorize in Integrations | | Stripe revenue missing | Webhook not configured | Connect Stripe in Dashboard > Integrations | | Duplicate transactions | Multiple connections to same bank | Remove duplicate in Integrations | | Payroll amounts wrong | Mid-period payroll change | Notify Fondo CPA via Dashboard > Messages |
| Error | Fix | |-------|-----| | Software expense marked as Office | Recategorize in Transactions, Fondo learns | | Contractor marked as Vendor | Ensure 1099 classification matches in payroll | | Inter-company transfer as Revenue | Mark as Transfer in Transactions | | R&D expense not flagged | Tag employee/activity as R&D in Dashboard |
| Issue | Cause | Solution | |-------|-------|----------| | Credit is $0 | No qualifying W-2 employees | Hire W-2 (not 1099) for R&D work | | Credit lower than expected | Activities not properly documented | Schedule call with Fondo CPA team | | Ineligible (>$5M revenue) | Exceeds startup threshold | Credit still available, just not payroll offset | | Missing contractor hours | Time tracking not connected | Upload contractor time logs manually |
For diagnostic data collection, see fondo-debug-bundle.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 15,028 | 10,171 | -32% | 1 | 1 | 0% | 2,488 | 1,404 | -44% | 0 | 0 | — |
case-02 | fail→fail | 23,568 | 15,546 | -34% | 1 | 1 | 0% | 2,967 | 2,319 | -22% | 0 | 0 | — |
case-03 | pass→pass | 17,046 | 3,797 | -78% | 1 | 1 | 0% | 1,927 | 1,087 | -44% | 0 | 0 | — |
case-04 | fail→pass | 12,520 | 5,530 | -56% | 1 | 1 | 0% | 2,000 | 1,370 | -32% | 0 | 0 | — |
case-05 | fail→pass | 11,247 | 3,646 | -68% | 1 | 1 | 0% | 1,698 | 1,003 | -41% | 0 | 0 | — |
case-06 | pass→pass | 17,832 | 4,456 | -75% | 1 | 1 | 0% | 1,880 | 1,184 | -37% | 0 | 0 | — |
case-07 | fail→pass | 11,224 | 4,244 | -62% | 1 | 1 | 0% | 1,828 | 1,117 | -39% | 0 | 0 | — |
case-08 | fail→pass | 14,627 | 9,569 | -35% | 1 | 1 | 0% | 1,455 | 1,163 | -20% | 0 | 0 | — |
case-09 | fail→pass | 19,515 | 7,495 | -62% | 1 | 1 | 0% | 2,271 | 1,347 | -41% | 0 | 0 | — |
case-10 | fail→pass | 18,032 | 9,868 | -45% | 1 | 1 | 0% | 2,772 | 1,295 | -53% | 0 | 0 | — |
case-11 | pass→pass | 15,050 | 10,094 | -33% | 1 | 1 | 0% | 1,777 | 1,273 | -28% | 0 | 0 | — |
case-12 | fail→pass | 10,549 | 11,691 | +11% | 1 | 1 | 0% | 1,730 | 1,612 | -7% | 0 | 0 | — |
case-13 | fail→pass | 14,145 | 8,586 | -39% | 1 | 1 | 0% | 1,534 | 1,072 | -30% | 0 | 0 | — |
case-14 | fail→pass | 11,483 | 2,864 | -75% | 1 | 1 | 0% | 1,816 | 872 | -52% | 0 | 0 | — |
case-15 | fail→pass | 17,945 | 6,672 | -63% | 1 | 1 | 0% | 2,894 | 721 | -75% | 0 | 0 | — |
case-16 | pass→pass | 15,042 | 2,388 | -84% | 1 | 1 | 0% | 1,622 | 812 | -50% | 0 | 0 | — |
case-17 | fail→pass | 17,312 | 10,458 | -40% | 1 | 1 | 0% | 2,710 | 1,435 | -47% | 0 | 0 | — |
case-18 | pass→pass | 11,478 | 9,863 | -14% | 1 | 1 | 0% | 1,619 | 1,349 | -17% | 0 | 0 | — |
case-19 | fail→pass | 14,739 | 2,779 | -81% | 1 | 1 | 0% | 1,592 | 901 | -43% | 0 | 0 | — |
case-20 | pass→pass | 5,261 | 5,304 | +1% | 1 | 1 | 0% | 1,028 | 1,338 | +30% | 0 | 0 | — |
case-21 | pass→pass | 3,973 | 3,650 | -8% | 1 | 1 | 0% | 719 | 1,096 | +52% | 0 | 0 | — |
case-22 | pass→pass | 12,577 | 4,364 | -65% | 1 | 1 | 0% | 1,491 | 1,254 | -16% | 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 +59 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.