Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
verify - Skill - OpenSmartRoute
Skillv1.0.0
verify
Use when you want to validate changes before committing, or when you need to check all React contribution requirements.
Imported from react/react (.claude/skills/verify/SKILL.md) via skills.sh. Install upstream with npx skills add react/react --skill verify. Copyright stays with the author.
Verification
Run all verification steps.
Arguments:
$ARGUMENTS: Test pattern for the test step
Instructions
Run these first in sequence:
Run yarn prettier - format code (stop if fails)
Run yarn linc - lint changed files (stop if fails)
Then run these with subagents in parallel:
Use /flow to type check (stop if fails)
Use /test to test changes in source (stop if fails)
Use /test www to test changes in www (stop if fails)
If all pass, show success summary. On failure, stop immediately and report the issue with suggested fixes.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slotcurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Installed into a catalogue, chosen by a router
Install verify and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
When a provider is down or over quota the request moves on; the trace says it did.
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
react-react-verify.ocm.jsonjson
{
"ocm": "1",
"id": "react-react-verify",
"kind": "skill",
"name": "verify",
"description": "Use when you want to validate changes before committing, or when you need to check all React contribution requirements.",
"publisher": "react",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"skill-md",
"skills-sh"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Use when you want to validate changes before committing, or when you need to check all React contribution requirements."
],
"primary": false,
"metadata": {
"source": {
"provider": "skills.sh",
"repository": "https://github.com/react/react",
"path": ".claude/skills/verify/SKILL.md",
"ref": "HEAD",
"url": "https://www.skills.sh/react/react/verify",
"key": "react/react/.claude/skills/verify/SKILL.md"
}
},
"instructions": "# Verification\n\nRun all verification steps.\n\nArguments:\n- $ARGUMENTS: Test pattern for the test step\n\n## Instructions\n\nRun these first in sequence:\n1. Run `yarn prettier` - format code (stop if fails)\n2. Run `yarn linc` - lint changed files (stop if fails)\n\nThen run these with subagents in parallel:\n1. Use `/flow` to type check (stop if fails)\n2. Use `/test` to test changes in source (stop if fails)\n3. Use `/test www` to test changes in www (stop if fails)\n\nIf all pass, show success summary. On failure, stop immediately and report the issue with suggested fixes.",
"cost": {
"context_tokens": 142
}
}
Fetch it by URL: GET /api/v1/registry/react-react-verify/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.