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

• 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

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

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.

We maintain Skill Bench in this repository to evaluate public skill changes across coding agents and task categories. Skill Bench uses W&B Agent Factory as the eval runtime for task definitions, agent profiles, sandbox execution, and structured bench rows.

Pull requests run package validation by default. A maintainer can trigger live Skill Bench runs for larger changes.

Plan a local benchmark without model calls:

python3 -m skillbench.cli plan \
  --wbaf-root ../WandBAgentFactory \
  --candidate-ref HEAD \
  --skill wandb-primary

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

See CONTRIBUTING.md.