How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

90 days of the enterprise, pro and team plans free, no card needed. See the plans

OpenSmartRoute

debug-zoom-integration - Skill - OpenSmartRoute

Skillv1.0.0

debug-zoom-integration

Name: debug-zoom-integration
Author: anthropics

Debug broken Zoom implementations quickly. Use when auth, webhooks, SDK joins, MCP transport, or real-time media workflows are failing and you need to isolate the layer before proposing a fix.

by anthropics(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from anthropics/knowledge-work-plugins (partner-built/zoom-plugin/skills/debug-zoom-integration/SKILL.md) via skills.sh. Install upstream with npx skills add anthropics/knowledge-work-plugins --skill debug-zoom-integration. Copyright stays with the author.

Debug Zoom Integration

Use this skill when the user already built something and it is failing.

Triage Order

Auth and app configuration
Request construction or event verification
SDK initialization or platform mismatch
Media/session behavior
MCP transport and capability assumptions

Evidence To Request

Exact error text
Platform and SDK/runtime
Relevant request or payload sample
What worked versus what failed
Whether the issue is reproducible or intermittent

Reference Routing

Output

Most likely failing layer
Ranked hypotheses
Short fix plan
Verification steps

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 slot
curl -s -X POST https://osr-api.kindrock-caaab1a2.centralindia.azurecontainerapps.io/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 debug-zoom-integration 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.

Photo: RDNE Stock project

For the business

What it costs to adopt - in engineering time.

Same client, same code
One base URL
The OpenAI-compatible endpoint answers your existing SDK calls; model=auto lets the router choose.
The SDKs
One URL, every vendor
No vendor lock-in
Point your OpenAI-compatible client at one address; add, swap or retire providers in the catalogue without touching application code.
Every vendor side by side
Next eligible model answers
Failover built in
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.

anthropics-knowledge-work-plugins-debug-zoom-integration.ocm.jsonjson

{
  "ocm": "1",
  "id": "anthropics-knowledge-work-plugins-debug-zoom-integration",
  "kind": "skill",
  "name": "debug-zoom-integration",
  "description": "Debug broken Zoom implementations quickly. Use when auth, webhooks, SDK joins, MCP transport, or real-time media workflows are failing and you need to isolate the layer before proposing a fix.",
  "publisher": "anthropics",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "coding"
    ],
    "tags": [
      "skill-md",
      "skills-sh"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Debug broken Zoom implementations quickly. Use when auth, webhooks, SDK joins, MCP transport, or real-time media workflows are failing and you need to isolate the layer before proposing a fix."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "skills.sh",
      "repository": "https://github.com/anthropics/knowledge-work-plugins",
      "path": "partner-built/zoom-plugin/skills/debug-zoom-integration/SKILL.md",
      "ref": "HEAD",
      "url": "https://www.skills.sh/anthropics/knowledge-work-plugins/debug-zoom-integration",
      "key": "anthropics/knowledge-work-plugins/partner-built/zoom-plugin/skills/debug-zoom-integration/SKILL.md"
    }
  },
  "instructions": "# Debug Zoom Integration\n\nUse this skill when the user already built something and it is failing.\n\n## Triage Order\n\n1. Auth and app configuration\n2. Request construction or event verification\n3. SDK initialization or platform mismatch\n4. Media/session behavior\n5. MCP transport and capability assumptions\n\n## Evidence To Request\n\n- Exact error text\n- Platform and SDK/runtime\n- Relevant request or payload sample\n- What worked versus what failed\n- Whether the issue is reproducible or intermittent\n\n## Reference Routing\n\n- [oauth](../oauth/SKILL.md)\n- [rest-api](../rest-api/SKILL.md)\n- [webhooks](..",
  "cost": {
    "context_tokens": 214
  }
}

Fetch it by URL: GET /api/v1/registry/anthropics-knowledge-work-plugins-debug-zoom-integration/manifest?version=1.0.0