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.
tool-quality-audit - Skill - OpenSmartRoute
Skillv1.0.0
tool-quality-audit
Audit tool integrations for deterministic behavior, error contracts, and logging before agents depend on them. Use when adding or updating tools or MCP servers.
Imported from majiayu000/claude-skill-registry (skills/data/tool-quality-audit/SKILL.md). Install upstream with npx skills add majiayu000/claude-skill-registry --skill tool-quality-audit. Copyright stays with the author.
Tool Quality Audit
Overview
Evaluate a tool’s reliability with a checklist and small smoke tests. Emphasize deterministic outputs, clear errors, and stable schemas.
Quick start
Fill templates/tool_audit.json.
Run smoke tests manually or via your harness.
Record findings in results.json.
Core Guidance
Prefer deterministic checks before LLM-based grading.
references/tool-audit-checklist.md: Reliability and contract checklist.
templates/tool_audit.json: Audit scaffold for a tool.
Validation
Ensure audit file is filled and failures are actionable.
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 tool-quality-audit 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.
