Weights & Biases 技能

辅助编程 Agent 分析 W&B 实验、开展训练研究并接入应用追踪。

Weights & Biases 提供项目操作、评估表、受限训练试验、Weave 插桩和 AgentLens 追踪技能。作者将这些公开技能包标记为实验性。

适用场景

• 分析训练运行与评估表
• 为 Python 或 TypeScript Agent 应用添加追踪
• 比较有明确边界的训练实验

使用方法

按上游说明配置 W&B 账号与 API 密钥，并检查各技能的 SDK 要求。README 为辅助脚本列出了 Python 和依赖包的最低版本。

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/skills

• wandb-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/skills

• wandb-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/skills

• wandb-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/skills

• weave-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