W&B Skills
A published set of agent skills that teach a coding agent how to drive Weights & Biases: logging metrics and media during training, tracking and analysing experiments, tuning hyperparameters, tracing agent rollouts, finding failure modes and running online evaluations.
Find alternatives to W&B Skills
What it does
- Agentic coding
- Evaluation and observability
Sources
- Pricing
-
Plan names and rates read from wandb.ai/site/pricing on 2026-09-19.
- Description
-
Official documentation · 19 Sep 2026
Read 2026-09-19: "W&B Skills teach coding agents how to use tools effectively to manage the model and agent development lifecycle", with its own two lists -- for model training, "Log metrics and rich media during model training and fine-tuning", "Track model training experiments", "Analyze runs and experiment results", "Tune hyperparameters"; for agent building, "Trace agent rollouts", "Analyze traces and find failure modes", "Evaluate agents with labeled datasets", "Run online evaluations for production monitoring".
- What it does
-
Official documentation · 19 Sep 2026
Skills a coding agent executes against a repository and a training run are agentic-coding; what they drive -- traces, evaluations and online monitoring -- is evaluation-observability.
- Sold within
-
Installed free from a registry, but useless without the product it drives: the page's own install line is "npx skills add wandb/skills" and every skill it lists acts on a Weights & Biases account.
- Name
-
Official documentation · 19 Sep 2026
The vendor's product menu lists it under Weave as "Skills -- Skills for coding agents"; the page names it "W&B Skills".
- URL
-
Official documentation · 19 Sep 2026
The product's own page under wandb.ai/site/, linked from the vendor's own product menu and read in full on 2026-09-19.
- Deployment
-
Official documentation · 19 Sep 2026
Stated on the product's own page.
- Interfaces
-
Official documentation · 14 Oct 2026
Page, read in a browser 2026-10-14: installed with
npx skills add wandb/skills, optionally linked to a coding agent such as Claude Code.
Also from Weights & Biases
-
W&B Models Platform
Experiment tracking for model training runs, recording hyperparameters, metrics and artifacts so runs can be compared, swept and reproduced.
-
W&B Weave Developer tool
Tracing, evaluation and production monitoring for LLM and agent applications, capturing each call so prompts and outputs can be scored over time.
-
CoreWeave Registry Platform
Curated central repository providing versioning, aliases, lineage tracking and governance for models and datasets across the ML lifecycle.
-
Serverless Inference API service
Hosted inference service for open-source and commercial LLMs (OpenAI, Qwen, Llama, Kimi, Phi, DeepSeek, Z.AI) without managing infrastructure.
-
CoreWeave Serverless RL Platform
Managed reinforcement-learning fine-tuning service for LLMs on CoreWeave's managed GPU cluster, billed per-token for rollouts with automatic scale-to-zero.
-
CoreWeave Serverless SFT Platform
Serverless supervised fine-tuning for LLMs on CoreWeave's managed GPU cluster, run alongside Serverless RL in a unified workflow via the Agent Reinforcement Trainer (ART) API.
Open Weights & Biases in the directory
Something wrong here? Send a correction — quote this product id: wandb-skills.