Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →diegosouzapw/cli-models
Query available AI models, list model aliases, and browse the full model catalog from the CLI. Filter by provider, search by capability, and resolve model name variants.
Passed 24 of 25 test cases with the skill, and 8 of 25 without it.
and 18 more in the full report
17 fixed7 passed either way0 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am adding an unverified manual model 'gemini-1.5-flash' under provider 'google' with display name 'Gemini Flash'. I want to preview the addition without persisting it. What flag enables this preview when adding manual models?
| Checked | Without skill | With skill |
|---|---|---|
| The command uses `omniroute models add google gemini-1.5-flash` | Missed | Passed |
| The command includes `--dry-run` | Passed | Passed |
The instructions your model reads when the skill loads.
Query available AI models, list model aliases, and browse the full model catalog from the CLI. Filter by provider, search by capability, and resolve model name variants.
npm install -g omniroute # or: npx omniroute
omniroute --version
models test-add <model>Validate an OpenAI-compatible model on one strict connection, then add it after a synthetic tool round-trip
Flags:
--provider <id>--connection <id>--name <name>--max-input-tokens <count>--max-output-tokens <count>--api-format <format>--context <name>--base-url <url>--allow-inference--yes--dry-run--jsonExample:
omniroute models test-add example-model --provider example-provider --connection example-connection --dry-run
test cases passed, vs 8 / 25 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.