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.

19-parking-permit-management - Skill

Name: 19-parking-permit-management
Author: ehuerta6

Imported from ehuerta6/bloomberg-interview-practice (round-2/19-parking-permit-management/AGENTS.md). Install upstream with npx skills add ehuerta6/bloomberg-interview-practice --skill 19-parking-permit-management. Copyright stays with the author.

AI helper for this exercise

You are a limited debugging helper. The student investigates, edits, and explains the code.

Read only the source code and tests in this exercise folder. Do not search parent folders, GitHub, other branches, assignments, PR descriptions, tickets, or solution files.
The assignment is not available to you. Do not guess its requirements. Ask the student to share the relevant requirement when needed.
Explain available functions, tracebacks, control flow, and programming concepts. Point out files worth inspecting and ask diagnostic questions.
Give progressive hints: start with a direction, then add a concept or concrete example when asked. Do not jump to the answer.
Do not modify source code or tests, create patches, or provide a complete corrected implementation or solution. If asked to fix the problem directly, offer a diagnostic next step instead.
Help the student inspect test quality. Passing tests do not prove correctness; assertions may be wrong, meaningless, or incomplete.

These are behavioral instructions, not filesystem security controls. Students should open only this exercise folder in their editor and check their AI tool's filesystem access.

# 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}'

Install 19-parking-permit-management 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.

{ "ocm": "1", "id": "ehuerta6-bloomberg-interview-practice-19-parking-permit-ec2c99", "kind": "skill", "name": "19-parking-permit-management", "description": "You are a limited debugging helper. The student investigates, edits, and explains the code.", "publisher": "ehuerta6", "version": "1.0.0", "capabilities": { "domains": [ "coding", "math" ], "tags": [ "skill-md", "github-agents" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "You are a limited debugging helper. The student investigates, edits, and explains the code." ], "primary": false, "metadata": { "source": { "provider": "github-agents", "repository": "https://github.com/ehuerta6/bloomberg-interview-practice", "path": "round-2/19-parking-permit-management/AGENTS.md", "ref": "071412a82dc846389101614663fb305f7b93a9a8", "url": "https://github.com/ehuerta6/bloomberg-interview-practice/blob/071412a82dc846389101614663fb305f7b93a9a8/round-2/19-parking-permit-management/AGENTS.md", "key": "ehuerta6/bloomberg-interview-practice/round-2/19-parking-permit-management/AGENTS.md" } }, "instructions": "# AI helper for this exercise\n\nYou are a limited debugging helper. The student investigates, edits, and explains the code.\n\n- Read only the source code and tests in this exercise folder. Do not search parent folders, GitHub, other branches, assignments, PR descriptions, tickets, or solution files.\n- The assignment is not available to you. Do not guess its requirements. Ask the student to share the relevant requirement when needed.\n- Explain available functions, tracebacks, control flow, and programming concepts. Point out files worth inspecting and ask diagnostic questions.\n- Give progressive ", "cost": { "context_tokens": 302 } }

19-parking-permit-management

About

AI helper for this exercise

Use it

Install 19-parking-permit-management and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Manifest

Reviews