Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Synchronise OmniRoute configuration, provider connections, and settings to/from cloud storage. Manage cloud worker authentication and remote backup targets.
.claude/skills/diegosouzapw-omni-sync-cloud/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -17% | 0% |
<!-- generated by src/lib/agentSkills/generator.ts; manual edits will be overwritten -->
Synchronise OmniRoute configuration, provider connections, and settings to/from cloud storage. Manage cloud worker authentication and remote backup targets.
All requests require a valid Bearer token or session cookie. Obtain a token via POST /api/auth/login or configure REQUIRE_API_KEY=false for local development.
Authenticate with cloud worker
Authenticates with the OmniRoute cloud worker for remote access.
bashcurl -X POST https://localhost:20128/api/cloud/auth \ -H "Authorization: Bearer $OMNIROUTE_TOKEN" \ -H "Content-Type: application/json" \ -d '{}'
Update cloud worker credentials
bashcurl -X PUT https://localhost:20128/api/cloud/credentials/update \ -H "Authorization: Bearer $OMNIROUTE_TOKEN" \ -H "Content-Type: application/json" \ -d '{}'
Resolve model via cloud
Resolves a model request through the cloud worker.
bashcurl -X POST https://localhost:20128/api/cloud/model/resolve \ -H "Authorization: Bearer $OMNIROUTE_TOKEN" \ -H "Content-Type: application/json" \ -d '{}'
Get cloud model aliases
bashcurl https://localhost:20128/api/cloud/models/alias \ -H "Authorization: Bearer $OMNIROUTE_TOKEN"
Update cloud model alias
bashcurl -X PUT https://localhost:20128/api/cloud/models/alias \ -H "Authorization: Bearer $OMNIROUTE_TOKEN" \ -H "Content-Type: application/json" \ -d '{}'
Sync with cloud
bashcurl -X POST https://localhost:20128/api/sync/cloud \ -H "Authorization: Bearer $OMNIROUTE_TOKEN" \ -H "Content-Type: application/json" \ -d '{}'
Initialize cloud sync
bashcurl -X POST https://localhost:20128/api/sync/initialize \ -H "Authorization: Bearer $OMNIROUTE_TOKEN" \ -H "Content-Type: application/json" \ -d '{}'
GET sync › bundle
bashcurl https://localhost:20128/api/sync/bundle \ -H "Authorization: Bearer $OMNIROUTE_TOKEN"
GET sync › tokens
bashcurl https://localhost:20128/api/sync/tokens \ -H "Authorization: Bearer $OMNIROUTE_TOKEN"
POST sync › tokens
bashcurl -X POST https://localhost:20128/api/sync/tokens \ -H "Authorization: Bearer $OMNIROUTE_TOKEN" \ -H "Content-Type: application/json" \ -d '{}'
DELETE sync › tokens › <id>
bashcurl -X DELETE https://localhost:20128/api/sync/tokens/{id} \ -H "Authorization: Bearer $OMNIROUTE_TOKEN"
See the full OpenAPI specification at GET /api/openapi/spec or docs/openapi.yaml for detailed request/response schemas.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 13,786 | 9,697 | -30% | 1 | 1 | 0% | 1,273 | 1,754 | +38% | 0 | 0 | — |
case-02 | fail→pass | 13,604 | 3,816 | -72% | 1 | 1 | 0% | 1,665 | 1,663 | -0% | 0 | 0 | — |
case-12 | fail→pass | 14,523 | 7,364 | -49% | 1 | 1 | 0% | 1,770 | 1,269 | -28% | 0 | 0 | — |
case-03 | fail→pass | 10,706 | 7,703 | -28% | 1 | 1 | 0% | 990 | 1,466 | +48% | 0 | 0 | — |
case-04 | fail→pass | 13,663 | 7,841 | -43% | 1 | 1 | 0% | 1,519 | 1,265 | -17% | 0 | 0 | — |
case-05 | fail→pass | 16,378 | 8,469 | -48% | 1 | 1 | 0% | 1,712 | 1,611 | -6% | 0 | 0 | — |
case-06 | fail→pass | 16,319 | 7,587 | -54% | 1 | 1 | 0% | 1,772 | 1,360 | -23% | 0 | 0 | — |
case-07 | fail→pass | 14,472 | 10,790 | -25% | 1 | 1 | 0% | 1,494 | 1,403 | -6% | 0 | 0 | — |
case-08 | fail→pass | 17,196 | 7,482 | -56% | 1 | 1 | 0% | 1,722 | 1,366 | -21% | 0 | 0 | — |
case-09 | pass→pass | 11,953 | 7,824 | -35% | 1 | 1 | 0% | 1,120 | 1,285 | +15% | 0 | 0 | — |
case-10 | fail→pass | 13,841 | 1,597 | -88% | 1 | 1 | 0% | 1,576 | 1,189 | -25% | 0 | 0 | — |
case-11 | fail→pass | 14,029 | 8,273 | -41% | 1 | 1 | 0% | 1,380 | 1,309 | -5% | 0 | 0 | — |
case-13 | fail→pass | 13,773 | 7,415 | -46% | 1 | 1 | 0% | 1,441 | 1,399 | -3% | 0 | 0 | — |
case-14 | fail→pass | 9,666 | 7,815 | -19% | 1 | 1 | 0% | 1,361 | 1,386 | +2% | 0 | 0 | — |
case-15 | fail→pass | 13,837 | 6,686 | -52% | 1 | 1 | 0% | 1,400 | 1,209 | -14% | 0 | 0 | — |
case-16 | fail→pass | 11,506 | 2,584 | -78% | 1 | 1 | 0% | 1,020 | 1,219 | +20% | 0 | 0 | — |
case-17 | fail→pass | 18,974 | 10,566 | -44% | 1 | 1 | 0% | 2,274 | 1,671 | -27% | 0 | 0 | — |
case-18 | pass→pass | 14,121 | 7,624 | -46% | 1 | 1 | 0% | 1,484 | 1,385 | -7% | 0 | 0 | — |
case-19 | fail→pass | 13,556 | 6,580 | -51% | 1 | 1 | 0% | 1,471 | 1,161 | -21% | 0 | 0 | — |
case-20 | pass→pass | 10,796 | 19,851 | +84% | 1 | 1 | 0% | 1,023 | 1,605 | +57% | 0 | 0 | — |
case-21 | pass→pass | 15,641 | 10,432 | -33% | 1 | 1 | 0% | 2,129 | 1,938 | -9% | 0 | 0 | — |
case-22 | pass→fail | 20,066 | 10,815 | -46% | 1 | 1 | 0% | 2,269 | 1,976 | -13% | 0 | 0 | — |
case-23 | fail→pass | 12,640 | 8,401 | -34% | 1 | 1 | 0% | 1,249 | 1,567 | +25% | 0 | 0 | — |
case-24 | fail→pass | 14,327 | 13,164 | -8% | 1 | 1 | 0% | 1,617 | 1,919 | +19% | 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 +75 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/24/2026 | +50% |
| gemini-3.6-flash | verified | 8/7/2026 | +55% |
Other measured skills in the registry, with their headline benchmark lift.