Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Query available AI models across all configured providers. List models, resolve model aliases, and browse the full model catalog including provider-specific variants.
.claude/skills/diegosouzapw-omni-models/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -15% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 144% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 73% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -25% | 0% |
<!-- generated by src/lib/agentSkills/generator.ts; manual edits will be overwritten -->
Query available AI models across all configured providers. List models, resolve model aliases, and browse the full model catalog including provider-specific variants.
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.
List available models
Returns all models available across configured providers.
bashcurl https://localhost:20128/api/v1/models \ -H "Authorization: Bearer $OMNIROUTE_TOKEN"
List models (management)
bashcurl https://localhost:20128/api/models \ -H "Authorization: Bearer $OMNIROUTE_TOKEN"
Create or update a model alias
bashcurl -X POST https://localhost:20128/api/models/alias \ -H "Authorization: Bearer $OMNIROUTE_TOKEN" \ -H "Content-Type: application/json" \ -d '{}'
Get full model catalog
bashcurl https://localhost:20128/api/models/catalog \ -H "Authorization: Bearer $OMNIROUTE_TOKEN"
GET models › openrouter catalog
bashcurl https://localhost:20128/api/models/openrouter-catalog \ -H "Authorization: Bearer $OMNIROUTE_TOKEN"
POST models › test
bashcurl -X POST https://localhost:20128/api/models/test \ -H "Authorization: Bearer $OMNIROUTE_TOKEN" \ -H "Content-Type: application/json" \ -d '{}'
POST models › test all
bashcurl -X POST https://localhost:20128/api/models/test-all \ -H "Authorization: Bearer $OMNIROUTE_TOKEN" \ -H "Content-Type: application/json" \ -d '{}'
GET models › <model>
bashcurl https://localhost:20128/api/v1/models/{model} \ -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 | 17,182 | 13,635 | -21% | 1 | 1 | 0% | 2,473 | 2,096 | -15% | 0 | 0 | — |
case-02 | fail→pass | 10,047 | 12,839 | +28% | 1 | 1 | 0% | 759 | 1,852 | +144% | 0 | 0 | — |
case-03 | fail→pass | 34,088 | 12,976 | -62% | 1 | 1 | 0% | 2,397 | 2,102 | -12% | 0 | 0 | — |
case-04 | pass→pass | 9,720 | 10,716 | +10% | 1 | 1 | 0% | 841 | 1,642 | +95% | 0 | 0 | — |
case-05 | fail→pass | 22,864 | 3,697 | -84% | 1 | 1 | 0% | 777 | 1,348 | +73% | 0 | 0 | — |
case-06 | fail→pass | 13,539 | 7,809 | -42% | 1 | 1 | 0% | 1,551 | 1,158 | -25% | 0 | 0 | — |
case-07 | fail→pass | 11,575 | 8,065 | -30% | 1 | 1 | 0% | 1,202 | 1,044 | -13% | 0 | 0 | — |
case-08 | fail→pass | 9,585 | 8,164 | -15% | 1 | 1 | 0% | 759 | 1,166 | +54% | 0 | 0 | — |
case-09 | fail→pass | 5,566 | 8,364 | +50% | 1 | 1 | 0% | 1,028 | 1,232 | +20% | 0 | 0 | — |
case-10 | fail→pass | 11,910 | 8,033 | -33% | 1 | 1 | 0% | 1,367 | 1,237 | -10% | 0 | 0 | — |
case-11 | fail→pass | 11,966 | 8,347 | -30% | 1 | 1 | 0% | 1,194 | 1,137 | -5% | 0 | 0 | — |
case-12 | pass→pass | 24,475 | 7,538 | -69% | 1 | 1 | 0% | 1,473 | 1,008 | -32% | 0 | 0 | — |
case-13 | fail→pass | 11,300 | 7,280 | -36% | 1 | 1 | 0% | 1,190 | 1,069 | -10% | 0 | 0 | — |
case-14 | pass→pass | 9,784 | 7,410 | -24% | 1 | 1 | 0% | 932 | 1,088 | +17% | 0 | 0 | — |
case-15 | fail→pass | 17,342 | 6,770 | -61% | 1 | 1 | 0% | 2,120 | 958 | -55% | 0 | 0 | — |
case-16 | pass→pass | 16,590 | 8,008 | -52% | 1 | 1 | 0% | 359 | 975 | +172% | 0 | 0 | — |
case-17 | pass→pass | 14,579 | 7,290 | -50% | 1 | 1 | 0% | 1,456 | 953 | -35% | 0 | 0 | — |
case-18 | pass→pass | 7,176 | 9,424 | +31% | 1 | 1 | 0% | 1,122 | 1,233 | +10% | 0 | 0 | — |
case-19 | fail→pass | 25,084 | 7,152 | -71% | 1 | 1 | 0% | 1,259 | 978 | -22% | 0 | 0 | — |
case-20 | pass→pass | 8,751 | 6,960 | -20% | 1 | 1 | 0% | 435 | 974 | +124% | 0 | 0 | — |
case-21 | pass→pass | 8,404 | 7,041 | -16% | 1 | 1 | 0% | 608 | 976 | +61% | 0 | 0 | — |
case-22 | pass→pass | 9,881 | 8,210 | -17% | 1 | 1 | 0% | 789 | 942 | +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. 22 cases were attempted. The headline lift of +59 percentage points is the difference between those two pass rates over the 22 comparable cases.
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 | +64% |
| gemini-3.6-flash | verified | 8/7/2026 | +55% |
Other measured skills in the registry, with their headline benchmark lift.