Building the best tools for ML practitioners
Weights & Biases publishes skills that help AI agents instrument Python and TypeScript agents and LLM applications with Weave and AgentLens tracing, covering model calls, tools, and subagent turns. Its skills also cover ML experiment work, including autonomous training research through W&B Launch, sweeps, and run and artifact inspection. Its Eval Tables skill lets agents convert W&B Table artifacts into previews with typed input, output, and score columns, while its primary skill handles mixed tasks spanning Reports, Workspaces, Automations, and Weave evaluations.
Skills
5 skills · 74 stars · Apache-2.0
Agentlens Tracing Instrument Add Forge AgentLens tracing to Python or TypeScript agents.
Wandb Autoresearch Run bounded, evidence-driven training research through W&B Launch: assess project readiness, esta…
Wandb Eval Tables Convert W&B Table artifacts into non-destructive EvalTable previews with scan-first planning, typ…
Wandb Primary Primary W&B skill for broad or mixed Weights & Biases work: project overviews, W&B runs and artif…
Weave Instrument Add Weave tracing to Python or TypeScript agents and LLM applications.