skills

Skills to guide Claude Code, Codex, and other coding agents on using the Weights & Biases AI developer platform to train models and build agents.

For model training

• Log metrics and rich media during model training and fine-tuning
• Track model training experiments
• Analyze runs and experiment results to understand how the model is learning
• Tune hyperparameters

For agent building

• Trace agentic AI applications
• Analyze traces and classify them into failure modes
• Evaluate models with labeled datasets
• Run online evaluations for production monitoring

Getting Started

npx skills add wandb/skills

Then set your W&B API key:

export WANDB_API_KEY=<your-key>

npx skills is a utility for installing skills into major coding agent CLIs. Use --global to install for all projects, or --agent <name> to target a specific agent. See the npx skills docs for more details.

Available Skills

Skill	Description	Status
wandb-models	W&B Models skill for runs, sweeps, artifacts, configs, metrics, run history, best-run selection, and model analysis.	experimental
weave-analysis	W&B Weave skill for traces, calls, evaluations, scorers, token/cost analysis, and model usage.	experimental
wandb-reports	W&B Reports skill for report authoring, workspace guidance, report media, and report/project semantics.	experimental
signal-builder	Signal Builder skill for project-grounded monitor and LLM-as-judge signal design.	experimental
wandb-launch	W&B Launch skill for queues, jobs, relaunching runs, and remote compute workflows.	experimental

Benchmarks

We maintain a growing internal benchmark suite that evaluates each skill across coding agents and task categories. The split skills are currently experimental and validated through the W&B Agent Factory benchmark harness.

Category	Tasks	Claude Code (sonnet4.6)	Codex (gpt-5.3-codex)
Weave analysis	26	97%*	63%*
Weave tooling	11	95%*	83%*
Model training	8	90%*	85%*
LLM finetuning & RL analysis	14	72%*	86%*
Failure & outlier detection	8	86%*	63%*

*Pass rates are +/- 3%. Many tasks span multiple categories.

Contributing

See CONTRIBUTING.md.