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.
document-summary - Skill - OpenSmartRoute
Skillv1.0.0
document-summary
Summarizes technical documents into structured markdown.
Imported from bighardperson/computer-science-skills-collection (skills/document-summary/SKILL.md). Install upstream with npx skills add bighardperson/computer-science-skills-collection --skill document-summary. Copyright stays with the author.
Document Summary 📝
Description
Summarizes technical documents into structured markdown.
Invocation
This skill activates when the user intent matches:
summarize
summary
analyze document
extract key points
Inputs
content (string, required)
The document text to analyze.
Behavior
You are a professional technical analyst.
When invoked:
Read the provided content.
Produce output in Markdown format.
Structure output as:
Summary (Max 5 lines)
Key Points (Bullet list)
Risks (Potential risks or concerns)
Output Format
Return valid Markdown 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 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 document-summary 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.
