Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Execute Fondo production readiness checklist for year-end tax filing, R&D credit claims, and board-ready financial reporting. Trigger: "fondo production", "fondo tax filing ready", "fondo year-end checklist".
.claude/skills/jeremylongshore-fondo-prod-checklist/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 29% | 0% |
Fondo handles startup tax preparation, R&D credit claims, bookkeeping, and compliance filings. A production integration syncs financial data from banking, payroll, and expense platforms into Fondo for automated tax workflows. Failures mean missed filing deadlines, incorrect R&D credit claims, or unreconciled books that block board reporting.
FONDO_API_KEY stored in secrets manager (not config files)https://api.fondo.com/v1)typescriptasync function checkFondoReadiness(): Promise<void> { const checks: { name: string; pass: boolean; detail: string }[] = []; // API connectivity try { const res = await fetch('https://api.fondo.com/v1/status', { headers: { Authorization: `Bearer ${process.env.FONDO_API_KEY}` }, }); checks.push({ name: 'Fondo API', pass: res.ok, detail: res.ok ? 'Connected' : `HTTP ${res.status}` }); } catch (e: any) { checks.push({ name: 'Fondo API', pass: false, detail: e.message }); } // Credentials present checks.push({ name: 'API Key Set', pass: !!process.env.FONDO_API_KEY, detail: process.env.FONDO_API_KEY ? 'Present' : 'MISSING' }); // Bank sync status try { const res = await fetch('https://api.fondo.com/v1/integrations/status', { headers: { Authorization: `Bearer ${process.env.FONDO_API_KEY}` }, }); const data = await res.json(); const active = data?.integrations?.filter((i: any) => i.status === 'active').length || 0; checks.push({ name: 'Active Integrations', pass: active >= 2, detail: `${active} connected` }); } catch (e: any) { checks.push({ name: 'Active Integrations', pass: false, detail: e.message }); } for (const c of checks) console.log(`[${c.pass ? 'PASS' : 'FAIL'}] ${c.name}: ${c.detail}`); } checkFondoReadiness();
| Check | Risk if Skipped | Priority | |-------|----------------|----------| | Filing deadline alerts | Missed IRS deadlines, penalties | P1 | | Bank sync monitoring | Unreconciled transactions at year-end | P1 | | R&D credit validation | Incorrect credit claim, audit risk | P2 | | Payroll data sync | Missing W-2/1099 data for returns | P2 | | Monthly close tracking | Year-end books incomplete for board | P3 |
See fondo-security-basics for financial data protection and compliance controls.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 16,402 | 14,150 | -14% | 1 | 1 | 0% | 3,723 | 3,057 | -18% | 0 | 0 | — |
case-02 | fail→fail | 33,931 | 27,100 | -20% | 1 | 1 | 0% | 4,681 | 5,234 | +12% | 0 | 0 | — |
case-03 | fail→fail | 43,119 | 39,806 | -8% | 1 | 1 | 0% | 8,241 | 7,968 | -3% | 0 | 0 | — |
case-04 | pass→pass | 22,520 | 21,925 | -3% | 1 | 1 | 0% | 2,944 | 3,919 | +33% | 0 | 0 | — |
case-05 | pass→pass | 16,054 | 17,941 | +12% | 1 | 1 | 0% | 3,141 | 3,824 | +22% | 0 | 0 | — |
case-06 | pass→pass | 18,462 | 16,615 | -10% | 1 | 1 | 0% | 2,494 | 3,242 | +30% | 0 | 0 | — |
case-07 | fail→pass | 12,016 | 2,541 | -79% | 1 | 1 | 0% | 1,261 | 1,539 | +22% | 0 | 0 | — |
case-08 | fail→pass | 40,991 | 11,534 | -72% | 1 | 1 | 0% | 2,859 | 2,877 | +1% | 0 | 0 | — |
case-09 | fail→pass | 13,612 | 7,889 | -42% | 1 | 1 | 0% | 1,445 | 1,609 | +11% | 0 | 0 | — |
case-10 | fail→pass | 11,725 | 9,041 | -23% | 1 | 1 | 0% | 1,964 | 2,537 | +29% | 0 | 0 | — |
case-11 | pass→pass | 17,279 | 6,800 | -61% | 1 | 1 | 0% | 2,144 | 2,307 | +8% | 0 | 0 | — |
case-12 | pass→pass | 20,242 | 2,354 | -88% | 1 | 1 | 0% | 2,457 | 1,454 | -41% | 0 | 0 | — |
case-13 | pass→pass | 18,937 | 27,496 | +45% | 1 | 1 | 0% | 3,395 | 5,254 | +55% | 0 | 0 | — |
case-14 | pass→pass | 13,006 | 19,808 | +52% | 1 | 1 | 0% | 2,274 | 3,689 | +62% | 0 | 0 | — |
case-15 | fail→pass | 12,521 | 7,409 | -41% | 1 | 1 | 0% | 2,283 | 1,527 | -33% | 0 | 0 | — |
case-16 | fail→pass | 14,637 | 2,656 | -82% | 1 | 1 | 0% | 1,880 | 1,549 | -18% | 0 | 0 | — |
case-17 | pass→pass | 10,034 | 1,532 | -85% | 1 | 1 | 0% | 1,862 | 1,374 | -26% | 0 | 0 | — |
case-18 | fail→pass | 9,386 | 1,539 | -84% | 1 | 1 | 0% | 796 | 1,343 | +69% | 0 | 0 | — |
case-19 | fail→pass | 3,655 | 6,925 | +89% | 1 | 1 | 0% | 672 | 1,412 | +110% | 0 | 0 | — |
case-20 | pass→pass | 9,101 | 11,559 | +27% | 1 | 1 | 0% | 1,886 | 2,416 | +28% | 0 | 0 | — |
case-21 | pass→pass | 13,845 | 2,128 | -85% | 1 | 1 | 0% | 1,616 | 1,486 | -8% | 0 | 0 | — |
case-22 | pass→pass | 5,793 | 7,003 | +21% | 1 | 1 | 0% | 1,082 | 1,409 | +30% | 0 | 0 | — |
case-23 | fail→pass | 11,235 | 1,908 | -83% | 1 | 1 | 0% | 1,003 | 1,440 | +44% | 0 | 0 | — |
case-24 | fail→pass | 14,790 | 2,290 | -85% | 1 | 1 | 0% | 1,535 | 1,403 | -9% | 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. 24 cases were attempted. The headline lift of +46 percentage points is the difference between those two pass rates over the 24 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.