/routing-calibration

Use when calibrating or validating a maintained routing recipe against live model backends, including probe manifests and evidence reports.

BOOST

vllm-project@vllm-project

GitHub

From plugin

semantic-router

6.2k4 skills

Install

$ npx -y skills add vllm-project/semantic-router --skill routing-calibration --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/routing-calibration

Context preview

The summary Claude sees to decide when to auto-load this skill.

Use when calibrating or validating a maintained routing recipe against live model backends, including probe manifests and evidence reports.

SKILL.md

routing-calibration.SKILL.md

name: routing-calibration
description: Use when calibrating or validating a maintained routing recipe against live model backends, including probe manifests and evidence reports.

Routing calibration

Use `tools/calibration/recipe/router_calibration_loop.py` and the versioned probe schema in `config/schemas/recipe-probes-v1.schema.json`. Keep recipe changes in the local checkout; remote systems are validation mirrors only.

Treat endpoint credentials, hostnames, and private fleet details as secrets. Before a live run, validate the probe manifest and identify the exact recipe, backend, and rollback point. Record the evaluated inputs, outputs, and observed quality rather than inferring success from process health.

Run `make check`, then `make verify DOMAIN=maintained-recipes` for live recipe verification.

Read it on GitHub ↗

Ships withsemantic-router

An open, programmable decision layer for models and compute.

Get the whole plugin

Stats

HTML Bash Docker Kubernetes GitHub

+2 tags

Hugging Face Slack

6,193

Stars

1,049