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.
recipe-post-mortem-setup - Skill - OpenSmartRoute
Skillv1.0.0
recipe-post-mortem-setup
Create a Google Docs post-mortem, schedule a Google Calendar review, and notify via Chat.
Imported from streakyc/googleworkspacecli (skills/recipe-post-mortem-setup/SKILL.md). Install upstream with npx skills add streakyc/googleworkspacecli --skill recipe-post-mortem-setup. Copyright stays with the author.
Set Up Post-Mortem
PREREQUISITE: Load the following skills to execute this recipe: gws-docs, gws-calendar, gws-chat
Create a Google Docs post-mortem, schedule a Google Calendar review, and notify via Chat.
Notify in Chat: gws chat +send --space spaces/ENG_SPACE --text '🔍 Post-mortem scheduled for [Incident].'
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 recipe-post-mortem-setup 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.