Same collection group
Weights & Biases Agent Skills
Use W&B and Weave skills for experiment analysis, model training workflows, agent tracing, and evaluations.
Skillby mlflow · mlflow/skills
Instrument, debug, and evaluate GenAI applications using MLflow’s tracing and evaluation skills.
npx skills add mlflow/skillsSources: Author README · Checked 2026-10-18.
The installer adds instructions. SDK dependencies and access to trace data remain prerequisites for the selected workflow.
Sources: Author README · Checked 2026-10-18.
| Capability | What it does |
|---|---|
| Trace analysis | Instrument applications and analyze spans, sessions, and failure causes. |
| Evaluation | Build datasets and scorers and inspect evaluation results. |
| Metrics | Query token usage, latency, and error trends through MLflow workflows. |
Sources: Author README · Checked 2026-10-18.
Suggested prompts for your own client. These are examples, not recorded tool executions.
Review my agent’s MLflow traces and classify recurring failure modes, separating observations from hypotheses.Design a small evaluation dataset and scorer suite for my support agent, with reproducible comparisons before and after changes.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.