skills/skills.volces.com/model-healthcheck

model-healthcheck

SKILL.md

Model Healthcheck Skill

When the user requests a model test, follow these steps:

Steps

  1. Get all model list Use gateway config.get to read the current config and extract all provider/model combinations from models.providers.

  2. Test all models concurrently For each model, use sessions_spawn to run a test:

    • task: "Reply with exactly: model ok. Only reply these two words."
    • model: the corresponding provider/model-id
    • runTimeoutSeconds: 30
    • cleanup: "delete"

    Fire all tests concurrently (multiple sessions_spawn calls at once), do not test sequentially.

  3. Collect results and summarize

Installs
5
First Seen
Mar 13, 2026