Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Export your first Clari forecast and pipeline snapshot. Use when testing Clari API connectivity, pulling forecast data, or learning the export API structure. Trigger with phrases like "clari hello world", "clari first export", "clari test api", "clari forecast export".
.claude/skills/jeremylongshore-clari-hello-world/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 57% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 191% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -32% | 0% |
Prove the complete asynchronous export contract with one small, non-production forecast request. Success means retaining the forecast ID, job ID, terminal state, result format, and a redacted schema sample—not merely receiving an initial HTTP response.
Record the forecast ID, time period, requested data types, scope ID, currency, history choice, and JSON or CSV format.
Read /admin/limits and confirm both concurrent capacity and rolling monthly quota before consuming an export slot.
Submit POST /export/forecast/{forecastId} against the documented Revenue API base and retain the returned job ID.
Read /export/jobs/{jobId} with bounded backoff until DONE, ABORTED, or an operator-defined timeout. Do not treat SCHEDULED or STARTED as completion.
Only after DONE, fetch /export/jobs/{jobId}/results, validate content type and shape, and store the result in the approved temporary boundary.
Record row count, schema fingerprint, status timeline, and cleanup result; delete temporary exported data according to policy.
Use the Revenue API token only in the apikey header over HTTPS. Never include the header, raw response body, or revenue values in logs; authorization follows the token owner’s Clari access and hierarchy.
Use Read and Grep to inspect configuration, provider contracts, fixtures, logs, schemas, and existing tests before proposing a change. Use Write or Edit only for the approved plan, implementation, test, or redacted receipt; do not issue, rotate, revoke, create, update, cancel, delete, export, ingest, or publish provider data without explicit operator approval.
Return the exact surface, environment, resource or job identifiers, contract fingerprint, evidence, unresolved risks, and final decision without exposing credentials or sensitive customer data.
An operator requests a JSON export for one current-quarter Forecast Tab, observes SCHEDULED, STARTED, and DONE, retrieves the result once, and records field names and row count without retaining deal values in the test artifact.
| Failure | Response | | --- | --- | | Forecast ID rejected | Re-copy the ID from the intended Forecast Tab and verify the integration identity is opted into that hierarchy. | | Job remains non-terminal | Stop at the timeout, retain the job ID, inspect service status, and avoid queuing duplicate jobs. | | Results request fails | Confirm the job is DONE, the job ID belongs to the same token, and the export has not expired. |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 10,778 | 2,957 | -73% | 1 | 1 | 0% | 2,066 | 1,577 | -24% | 0 | 0 | — |
case-02 | fail→pass | 13,289 | 10,230 | -23% | 1 | 1 | 0% | 2,867 | 3,096 | +8% | 0 | 0 | — |
case-03 | pass→pass | 16,262 | 12,575 | -23% | 1 | 1 | 0% | 3,265 | 3,570 | +9% | 0 | 0 | — |
case-04 | fail→pass | 5,595 | 3,253 | -42% | 1 | 1 | 0% | 917 | 1,444 | +57% | 0 | 0 | — |
case-05 | fail→pass | 3,126 | 2,181 | -30% | 1 | 1 | 0% | 454 | 1,322 | +191% | 0 | 0 | — |
case-06 | fail→pass | 10,561 | 1,823 | -83% | 1 | 1 | 0% | 1,908 | 1,294 | -32% | 0 | 0 | — |
case-07 | fail→pass | 8,925 | 4,748 | -47% | 1 | 1 | 0% | 1,706 | 1,701 | -0% | 0 | 0 | — |
case-08 | fail→pass | 6,245 | 1,994 | -68% | 1 | 1 | 0% | 991 | 1,328 | +34% | 0 | 0 | — |
case-09 | pass→pass | 6,135 | 2,244 | -63% | 1 | 1 | 0% | 1,027 | 1,346 | +31% | 0 | 0 | — |
case-10 | fail→pass | 5,950 | 1,516 | -75% | 1 | 1 | 0% | 1,015 | 1,238 | +22% | 0 | 0 | — |
case-11 | pass→pass | 3,028 | 1,457 | -52% | 1 | 1 | 0% | 326 | 1,213 | +272% | 0 | 0 | — |
case-22 | pass→pass | 11,546 | 6,918 | -40% | 1 | 1 | 0% | 1,929 | 2,187 | +13% | 0 | 0 | — |
case-12 | fail→fail | 5,561 | 2,305 | -59% | 1 | 1 | 0% | 1,108 | 1,315 | +19% | 0 | 0 | — |
case-13 | pass→pass | 7,606 | 2,444 | -68% | 1 | 1 | 0% | 1,338 | 1,404 | +5% | 0 | 0 | — |
case-14 | pass→pass | 10,438 | 5,086 | -51% | 1 | 1 | 0% | 1,715 | 1,892 | +10% | 0 | 0 | — |
case-15 | fail→pass | 14,235 | 7,826 | -45% | 1 | 1 | 0% | 2,014 | 1,869 | -7% | 0 | 0 | — |
case-16 | pass→pass | 11,028 | 5,818 | -47% | 1 | 1 | 0% | 1,588 | 1,939 | +22% | 0 | 0 | — |
case-17 | pass→pass | 12,439 | 6,945 | -44% | 1 | 1 | 0% | 1,837 | 2,007 | +9% | 0 | 0 | — |
case-18 | pass→pass | 3,464 | 1,540 | -56% | 1 | 1 | 0% | 519 | 1,190 | +129% | 0 | 0 | — |
case-19 | fail→pass | 10,156 | 6,460 | -36% | 1 | 1 | 0% | 1,638 | 2,079 | +27% | 0 | 0 | — |
case-20 | fail→pass | 11,855 | 1,786 | -85% | 1 | 1 | 0% | 2,015 | 1,252 | -38% | 0 | 0 | — |
case-21 | fail→pass | 10,618 | 4,787 | -55% | 1 | 1 | 0% | 1,778 | 1,951 | +10% | 0 | 0 | — |
case-23 | pass→pass | 13,839 | 11,596 | -16% | 1 | 1 | 0% | 2,530 | 2,865 | +13% | 0 | 0 | — |
case-24 | pass→pass | 14,827 | 8,204 | -45% | 1 | 1 | 0% | 2,712 | 2,411 | -11% | 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 +50 percentage points is the difference between those two pass rates over the 24 comparable cases.
The publisher has shipped newer versions since this run, so these numbers describe v1, not the version currently listed.
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.