Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Configure Clari API authentication with API key and set up export access. Use when connecting to the Clari API, generating API tokens, or configuring forecast data exports. Trigger with phrases like "install clari", "setup clari api", "clari auth", "clari api key", "configure clari".
.claude/skills/jeremylongshore-clari-install-auth/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 6% | 0% |
Establish a dedicated integration identity before building any data flow. Treat Revenue API tokens, ingestion partner keys, and Copilot key/password pairs as separate credentials with separate rotation and revocation paths.
Record the exact base URL and authentication contract: Revenue API uses the apikey header, v2 ingestion additionally requires partnerkey, and Copilot uses both X-Api-Key and X-Api-Password.
Use a service or integration user whose hierarchy and forecast access match the intended export scope. Do not reuse a personal administrator credential.
Generate the credential in the Clari settings exposed for the entitled product, capture it once into the approved secret manager, and record owner and rotation metadata without copying the value into tickets or logs.
For Revenue API, call the administrative limits read or another entitled read-only endpoint. For Copilot, list a narrowly scoped resource such as users; do not create or update CRM records during authentication testing.
Confirm the identity can see only the expected organization, forecast hierarchy, workspace, and object set. Treat an empty result separately from successful authorization.
Define overlap, rollback, dependent-job restart, and emergency revocation procedures before production use.
Send credentials only in the provider-documented headers over HTTPS. Redact all token and password values, never persist them in shell history or fixtures, and remember that revoking a Revenue API token or deactivating its owning user can break active integrations.
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.
A forecast warehouse integration receives a dedicated user and token limited by the user’s Clari hierarchy. The operator validates /admin/limits, records only the HTTP status and organization context, and schedules a rotation drill before enabling exports.
| Failure | Response | | --- | --- | | 401 or authentication failure | Verify the correct header contract and secret reference; rotate rather than printing the credential. | | 403 or missing data | Check product entitlement, hierarchy opt-in, forecast access, partner enablement, and workspace scope. | | Credential owner is deactivated | Issue a replacement under an approved integration identity and restart dependents only after read-only validation. |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 14,272 | 8,971 | -37% | 1 | 1 | 0% | 2,530 | 2,832 | +12% | 0 | 0 | — |
case-02 | fail→pass | 12,554 | 7,230 | -42% | 1 | 1 | 0% | 2,193 | 2,165 | -1% | 0 | 0 | — |
case-03 | fail→fail | 16,316 | 11,708 | -28% | 1 | 1 | 0% | 2,888 | 3,228 | +12% | 0 | 0 | — |
case-04 | fail→pass | 7,295 | 3,167 | -57% | 1 | 1 | 0% | 1,156 | 1,321 | +14% | 0 | 0 | — |
case-05 | fail→pass | 11,505 | 4,641 | -60% | 1 | 1 | 0% | 2,113 | 1,865 | -12% | 0 | 0 | — |
case-06 | fail→pass | 8,758 | 5,335 | -39% | 1 | 1 | 0% | 1,824 | 1,936 | +6% | 0 | 0 | — |
case-07 | pass→pass | 11,178 | 9,303 | -17% | 1 | 1 | 0% | 2,018 | 2,468 | +22% | 0 | 0 | — |
case-08 | pass→pass | 7,805 | 4,202 | -46% | 1 | 1 | 0% | 1,457 | 1,634 | +12% | 0 | 0 | — |
case-09 | fail→pass | 10,731 | 5,932 | -45% | 1 | 1 | 0% | 1,451 | 1,812 | +25% | 0 | 0 | — |
case-10 | pass→pass | 17,967 | 6,656 | -63% | 1 | 1 | 0% | 1,484 | 2,048 | +38% | 0 | 0 | — |
case-11 | fail→pass | 10,525 | 4,165 | -60% | 1 | 1 | 0% | 1,853 | 1,632 | -12% | 0 | 0 | — |
case-12 | fail→pass | 12,360 | 9,650 | -22% | 1 | 1 | 0% | 2,312 | 2,402 | +4% | 0 | 0 | — |
case-13 | fail→pass | 12,420 | 11,948 | -4% | 1 | 1 | 0% | 1,966 | 2,818 | +43% | 0 | 0 | — |
case-14 | fail→pass | 10,626 | 7,937 | -25% | 1 | 1 | 0% | 1,721 | 2,292 | +33% | 0 | 0 | — |
case-15 | fail→fail | 13,827 | 8,865 | -36% | 1 | 1 | 0% | 2,443 | 2,518 | +3% | 0 | 0 | — |
case-16 | pass→pass | 7,916 | 3,141 | -60% | 1 | 1 | 0% | 1,247 | 1,374 | +10% | 0 | 0 | — |
case-17 | fail→pass | 16,422 | 4,257 | -74% | 1 | 1 | 0% | 2,600 | 1,623 | -38% | 0 | 0 | — |
case-18 | pass→pass | 8,940 | 5,028 | -44% | 1 | 1 | 0% | 1,684 | 1,972 | +17% | 0 | 0 | — |
case-19 | pass→pass | 7,967 | 3,244 | -59% | 1 | 1 | 0% | 1,482 | 1,568 | +6% | 0 | 0 | — |
case-20 | pass→pass | 13,641 | 10,418 | -24% | 1 | 1 | 0% | 2,670 | 3,012 | +13% | 0 | 0 | — |
case-21 | pass→pass | 7,460 | 8,730 | +17% | 1 | 1 | 0% | 1,426 | 2,746 | +93% | 0 | 0 | — |
case-22 | pass→pass | 8,932 | 6,199 | -31% | 1 | 1 | 0% | 1,700 | 1,971 | +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 +50 percentage points is the difference between those two pass rates over the 22 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.