Same collection group
MLflow Agent Skills
Instrument, debug, and evaluate GenAI applications using MLflow’s tracing and evaluation skills.
Skillby wandb · wandb/skills
Use W&B and Weave skills for experiment analysis, model training workflows, agent tracing, and evaluations.
npx skills add wandb/skillsSources: Author README · Checked 2026-10-18.
Installation supplies instructions rather than SDK dependencies or credentials. The listed skill bundles are marked experimental by the author.
Sources: Author README · Checked 2026-10-18.
| Capability | What it does |
|---|---|
| Training analysis | Track experiments, analyze runs, and work with hyperparameter tuning workflows. |
| Agent observability | Instrument applications and analyze traces and evaluation results with Weave. |
Sources: Author README · Checked 2026-10-18.
Suggested prompts for your own client. These are examples, not recorded tool executions.
Compare selected training runs in my W&B project and explain the metrics and artifacts supporting your conclusions.Review failing Weave traces and propose a labeled evaluation dataset to distinguish tool failures from answer-quality problems.Publisher-owned documentation and public GitHub metadata reviewed on 2026-10-18. Author installation examples are retained as documented. Prompts are illustrative; no third-party package or MCP was installed or executed, and no account was connected.
Recent activity refers to the repository push timestamp. It does not establish the product’s original release date. Stars are a dated snapshot of the entire repository.