Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Query AppFolio properties, units, and tenants via REST API. Trigger: "appfolio hello world".
.claude/skills/jeremylongshore-appfolio-hello-world/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -27% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -7% | 0% |
Get started with the AppFolio Property Manager API by authenticating with your client credentials and making your first API calls. This skill walks through connecting to the REST API, fetching a property listing, retrieving tenant details, and creating a basic work order — the essential operations for any AppFolio integration.
APPFOLIO_CLIENT_ID and APPFOLIO_CLIENT_SECRET environment variables settypescriptconst APPFOLIO_BASE = process.env.APPFOLIO_BASE_URL || "https://yourcompany.appfolio.com/api/v1"; async function appfolioFetch(path: string) { const credentials = Buffer.from( `${process.env.APPFOLIO_CLIENT_ID}:${process.env.APPFOLIO_CLIENT_SECRET}` ).toString("base64"); const res = await fetch(`${APPFOLIO_BASE}${path}`, { headers: { Authorization: `Basic ${credentials}`, Accept: "application/json" }, }); if (!res.ok) throw new Error(`AppFolio ${res.status}: ${await res.text()}`); return res.json(); }
typescriptconst properties = await appfolioFetch("/properties?page_size=10"); console.log(`Found ${properties.length} properties`); properties.forEach((p: any) => console.log(` ${p.id}: ${p.address_line1}, ${p.city}`));
typescriptconst tenants = await appfolioFetch(`/tenants?property_id=${properties[0].id}`); tenants.forEach((t: any) => console.log(` ${t.name} — Unit ${t.unit_number}`));
typescriptconst workOrder = await fetch(`${APPFOLIO_BASE}/work_orders`, { method: "POST", headers: { Authorization: `Basic ${Buffer.from(`${process.env.APPFOLIO_CLIENT_ID}:${process.env.APPFOLIO_CLIENT_SECRET}`).toString("base64")}`, "Content-Type": "application/json", }, body: JSON.stringify({ property_id: properties[0].id, description: "Leaky faucet in kitchen", priority: "normal", }), }); console.log("Work order created:", (await workOrder.json()).id);
A successful run produces authenticated API responses: a list of properties with addresses, tenant details for the first property, and a new work order ID confirming write access.
| Error | Cause | Solution | |-------|-------|----------| | 401 Unauthorized | Invalid client_id or secret | Verify credentials in environment variables | | 403 Forbidden | API scope not granted | Check Stack Partner permissions for the endpoint | | 404 Not Found | Wrong base URL or endpoint | Confirm your company subdomain and API version | | 422 Unprocessable | Missing required fields | Validate property_id and required body params | | 429 Too Many Requests | Rate limit exceeded | Add backoff delay, batch requests |
See appfolio-core-workflow-a for full property and tenant management workflows.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | fail→fail | 12,901 | 11,471 | -11% | 1 | 1 | 0% | 2,690 | 3,312 | +23% | 0 | 0 | — |
case-01 | fail→fail | 28,585 | 11,879 | -58% | 1 | 1 | 0% | 3,180 | 3,675 | +16% | 0 | 0 | — |
case-02 | fail→pass | 13,676 | 6,269 | -54% | 1 | 1 | 0% | 3,214 | 2,358 | -27% | 0 | 0 | — |
case-03 | fail→fail | 12,818 | 8,908 | -31% | 1 | 1 | 0% | 2,875 | 2,914 | +1% | 0 | 0 | — |
case-04 | pass→pass | 9,601 | 5,002 | -48% | 1 | 1 | 0% | 1,740 | 1,900 | +9% | 0 | 0 | — |
case-05 | fail→pass | 7,737 | 1,584 | -80% | 1 | 1 | 0% | 1,628 | 1,150 | -29% | 0 | 0 | — |
case-10 | pass→fail | 8,319 | 2,592 | -69% | 1 | 1 | 0% | 1,454 | 1,250 | -14% | 0 | 0 | — |
case-06 | fail→pass | 6,286 | 1,773 | -72% | 1 | 1 | 0% | 1,020 | 1,106 | +8% | 0 | 0 | — |
case-07 | pass→pass | 10,153 | 3,434 | -66% | 1 | 1 | 0% | 1,828 | 1,447 | -21% | 0 | 0 | — |
case-08 | fail→pass | 5,356 | 2,038 | -62% | 1 | 1 | 0% | 933 | 1,225 | +31% | 0 | 0 | — |
case-09 | fail→pass | 8,715 | 2,113 | -76% | 1 | 1 | 0% | 1,294 | 1,198 | -7% | 0 | 0 | — |
case-21 | fail→fail | 16,794 | 9,977 | -41% | 1 | 1 | 0% | 3,129 | 2,963 | -5% | 0 | 0 | — |
case-11 | fail→pass | 9,732 | 2,301 | -76% | 1 | 1 | 0% | 1,598 | 1,225 | -23% | 0 | 0 | — |
case-12 | pass→pass | 10,840 | 7,203 | -34% | 1 | 1 | 0% | 1,780 | 2,131 | +20% | 0 | 0 | — |
case-13 | pass→pass | 12,495 | 9,257 | -26% | 1 | 1 | 0% | 2,078 | 2,880 | +39% | 0 | 0 | — |
case-14 | pass→pass | 10,287 | 3,236 | -69% | 1 | 1 | 0% | 1,710 | 1,228 | -28% | 0 | 0 | — |
case-15 | pass→pass | 9,165 | 11,648 | +27% | 1 | 1 | 0% | 1,673 | 1,202 | -28% | 0 | 0 | — |
case-16 | pass→pass | 5,094 | 1,406 | -72% | 1 | 1 | 0% | 895 | 1,015 | +13% | 0 | 0 | — |
case-17 | fail→pass | 9,959 | 3,105 | -69% | 1 | 1 | 0% | 1,617 | 1,335 | -17% | 0 | 0 | — |
case-18 | fail→pass | 12,777 | 1,951 | -85% | 1 | 1 | 0% | 2,034 | 1,173 | -42% | 0 | 0 | — |
case-19 | pass→pass | 4,011 | 1,801 | -55% | 1 | 1 | 0% | 686 | 1,141 | +66% | 0 | 0 | — |
case-20 | pass→pass | 14,793 | 12,943 | -13% | 1 | 1 | 0% | 2,441 | 3,374 | +38% | 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. 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.