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.
explain-changes - Skill - OpenSmartRoute
Skillv1.0.0
explain-changes
Analyze git diff, create a beginner-friendly changelog, and trace code sources to their business impact.
Imported from hmdghoul/claude-code-global-config (skills/explain-changes/SKILL.md). Install upstream with npx skills add hmdghoul/claude-code-global-config --skill explain-changes. Copyright stays with the author.
Current changes
"!git diff HEAD"
Write CHANGELOG.md in the repo root explaining the diff above to a complete beginner. Ignore styling, patterns, linting and formatting. Cover:
The Business Purpose: the real-world problem this solves for the user or business.
What Changed: plain-English old-vs-new behavior.
Affected Code Blueprint: one entry per functional change, in this format:
Affected Code Blueprint
File:[Path/to/file.ext] (Line numbers or Function/Class name)
What code changed: One simple sentence.
Direct Impact: What it achieves in the live system and how it serves the business purpose.
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 explain-changes 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.
