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.
refine - Prompt - OpenSmartRoute
Promptv1.0.0
refine
Analyst mode — Refined Story after the workshop (requires the minutes)
Prompt file imported from albegali/agentic-portal (.cursor/commands/refine.md). Copyright stays with the author.
/refine
Analyst mode — Refined Story after the workshop (requires the minutes)
Arguments: <ID…>
Recommended model: Claude Sonnet 5.5 (tier balanced, see models.toml). Switch to it before running this command.
Follow workflow/steps/refine.md with arguments : the IDs are {IDS}, the file path is {MINUTES}.
If the minutes or the ID are missing, stop and ask.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
<!-- Generated by tools/render_agents.py from workflow/workflow.toml and models.toml — do not edit; run `make agents`. -->
# /refine
Analyst mode — Refined Story after the workshop (requires the minutes)
Arguments: <ID…> <minutes file>
> Recommended model: **Claude Sonnet 5.5** (tier `balanced`, see models.toml). Switch to it before running this command.
Follow `workflow/steps/refine.md`with arguments <the text typed after the command>: the IDs are {IDS}, the file path is {MINUTES}.
If the minutes or the ID are missing, stop and ask.
Manifest
Installed into a catalogue, chosen by a router
Install refine 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.
{
"prompt": "<!-- Generated by tools/render_agents.py from workflow/workflow.toml and models.toml — do not edit; run `make agents`. -->\n# /refine\n\nAnalyst mode — Refined Story after the workshop (requires the minutes)\n\nArguments: <ID…> <minutes file>\n\n> Recommended model: **Claude Sonnet 5.5** (tier `balanced`, see models.toml). Switch to it before running this command.\n\nFollow `workflow/steps/refine.md` with arguments <the text typed after the command>: the IDs are {IDS}, the file path is {MINUTES}.\nIf the minutes or the ID are missing, stop and ask.",
"variables": [],
"notes": "Analyst mode — Refined Story after the workshop (requires the minutes)",
"metadata": {
"source": {
"provider": "github-cursor-commands",
"repository": "https://github.com/albegali/agentic-portal",
"path": ".cursor/commands/refine.md",
"ref": "0694fcfa6f9f742ee5403ca5c19a53b6c55c6d0c",
"url": "https://github.com/albegali/agentic-portal/blob/0694fcfa6f9f742ee5403ca5c19a53b6c55c6d0c/.cursor/commands/refine.md",
"key": "albegali/agentic-portal/.cursor/commands/refine.md"
}
}
}
Fetch it by URL: GET /api/v1/registry/albegali-agentic-portal-refine-cursor-command/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.