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

deep-research - Skill - OpenSmartRoute

Skillv1.0.0

deep-research

Name: deep-research
Author: heyvhuang

Research a topic thoroughly in this repo and return a structured summary with file references. Use when you need to understand how something works, find patterns across modules, or audit…

by heyvhuang(0) 0 installs

Free

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

See reviews

About

Imported from heyvhuang/ship-faster (skills/deep-research/SKILL.md). Install upstream with npx skills add heyvhuang/ship-faster --skill deep-research. Copyright stays with the author.

Deep Research (Explore)

Research $ARGUMENTS thoroughly.

Required output

Findings: 3-10 bullets, each backed by specific file references
Key code locations: a short list of the most important paths to read next
Open questions / unknowns: what you could not confirm from the repo

Method

Start broad: use Glob to find likely modules.
Then go deep: use Grep to locate exact identifiers and call sites.
Read the top-ranked files and follow references until the flow is clear.
Stop when you hit diminishing returns (two additional searches yield no new information).

Rules

Be evidence-driven: always cite file paths.
Do not implement changes; this skill is for investigation only.

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://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 deep-research 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.

heyvhuang-ship-faster-deep-research.ocm.jsonjson

{
  "ocm": "1",
  "id": "heyvhuang-ship-faster-deep-research",
  "kind": "skill",
  "name": "deep-research",
  "description": "Research a topic thoroughly in this repo and return a structured summary with file references. Use when you need to understand how something works, find patterns across modules, or audit implementations.",
  "publisher": "heyvhuang",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "coding",
      "math"
    ],
    "tags": [
      "skill-md",
      "research",
      "skills-sh"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Research a topic thoroughly in this repo and return a structured summary with file references. Use when you need to understand how something works, find patterns across modules, or audit implementations."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "skills.sh",
      "repository": "https://github.com/heyvhuang/ship-faster",
      "path": "skills/deep-research/SKILL.md",
      "ref": "HEAD",
      "url": "https://github.com/heyvhuang/ship-faster/blob/HEAD/skills/deep-research/SKILL.md",
      "key": "heyvhuang/ship-faster/skills/deep-research/SKILL.md"
    },
    "allowed_tools": [
      "Read",
      "Grep",
      "Glob"
    ]
  },
  "instructions": "# Deep Research (Explore)\n\nResearch $ARGUMENTS thoroughly.\n\n## Required output\n\n1. **Findings**: 3-10 bullets, each backed by specific file references\n2. **Key code locations**: a short list of the most important paths to read next\n3. **Open questions / unknowns**: what you could not confirm from the repo\n\n## Method\n\n- Start broad: use Glob to find likely modules.\n- Then go deep: use Grep to locate exact identifiers and call sites.\n- Read the top-ranked files and follow references until the flow is clear.\n- Stop when you hit diminishing returns (two additional searches yield no new information",
  "cost": {
    "context_tokens": 181
  }
}

Fetch it by URL: GET /api/v1/registry/heyvhuang-ship-faster-deep-research/manifest?version=1.0.0