Weights & Biases Skills
Guide coding agents through W&B experiment analysis, training research, and application tracing.
Weights & Biases publishes Skills for project operations, evaluation tables, bounded training trials, Weave instrumentation, and AgentLens tracing. The author labels these public bundles experimental.
Use cases
- Analyze training runs and evaluation tables
- Instrument Python or TypeScript agent applications
- Compare bounded training experiments
How to use
Configure a W&B account and API key through the upstream setup. Check each Skill’s SDK requirements; the README specifies Python and package version floors for its helpers.
Skills
agentlens-tracing-instrument
Add Forge AgentLens tracing to Python or TypeScript agents. Use when asked to trace agent turns, model calls, tools, or subagents with Forge or AgentLens.
wandb/skillswandb-autoresearch
Run bounded, evidence-driven training research through W&B Launch: assess project readiness, establish launchable code and queue capacity, smoke-test real jobs, execute serial trials, compare metrics, and persist resumable research state. Use when a coding agent is asked to autonomously test training hypotheses or tune a real W&B-tracked workload.
wandb/skillswandb-eval-tables
Convert W&B Table artifacts into non-destructive EvalTable previews with scan-first planning, typed input/output/score columns, bounded batches, verification, and safe removal. Use when a coding agent needs to create, inspect, compare, verify, or remove W&B EvalTable previews.
wandb/skillswandb-primary
Primary W&B skill for broad or mixed Weights & Biases work: project overviews, W&B runs and artifacts, Weave traces and evaluations, Reports, and Launch workflows. Use when the task spans multiple W&B surfaces or the user asks generally what is happening in a W&B project.
wandb/skillsweave-instrument
Add Weave tracing to Python or TypeScript agents and LLM applications. Use when asked to instrument model calls, tools, or agent turns with Weave.
wandb/skills