# W&B Analytics

> Use this tool when you need to analyze and optimize machine learning experiments with advanced metrics and visualizations. W&B Analytics solves problems related to hyperparameter tuning, model comparison, and performance regression detection, providing insights through interactive Plotly charts and summaries. It accepts experiment data as input and outputs detailed analytics and visualizations, making it ideal for use cases where data-driven decision making is crucial.

Canonical page: https://skillsregistry.net/skills/bettyguo-wandb  
JSON: https://api.skillsregistry.net/v1/skills/bettyguo-wandb

## Description

Complements the official W&B MCP server with advanced analytical capabilities including hyperparameter importance ranking with R² metrics, sweep summaries combining best and worst run analysis, structured run comparisons, and regression detection using z-tests against baseline runs. Generates Plotly charts exported as inline base64 PNG images. Supports relative-date filtering, optional run and sweep actions via --enable-actions flag, local stdio and HTTP bearer-token transports, and OpenTelemetry observability. Requires Python 3.11+.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/bettyguo-wandb)
- **Repository:** <https://github.com/bettyguo/mcp-wandb-2>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "bettyguo-wandb"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/bettyguo-wandb` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/bettyguo-wandb/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt