Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.
This skill does not declare a tool allowlist. The agent host applies whatever default tools are available at runtime.
SKILL.md / Manifest
https://raw.githubusercontent.com/zechenzhangagi/ai-research-skills/main/13-mlops/swanlab/SKILL.mdRegistry
github (via claudemarketplaces.com)