
wandb-weave
Query and analyze W&B experiment data and Weave LLM traces using Python scripts. Use when working wi
提供方 guangzhaoli|开源
wandb-skill
A Claude Code skill for Weights & Biases and Weave.
一个用于 Weights & Biases 和 Weave 的 Claude Code 技能。
Installation / 安装
git clone https://github.com/guangzhaoli/wandb-skill.git
cp -r wandb-skill ~/.claude/skills/wandb-weave
Prerequisites / 前置条件
pip install wandb weave
export WANDB_API_KEY="your-api-key"
How It Works / 使用方式
This skill automatically triggers when you ask Claude about:
当你向 Claude 询问以下内容时,技能会自动触发:
| Trigger | 触发词 |
|---|---|
| Query W&B experiments | 查询 W&B 实验 |
| Analyze Weave traces | 分析 Weave traces |
| List projects | 列出项目 |
| Create reports | 创建报告 |
Claude will automatically select and run the appropriate script.
Claude 会自动选择并运行合适的脚本。
Scripts / 脚本
| Script | Purpose | 用途 |
|---|---|---|
| query_runs.py | Query experiment runs with filtering and sorting | 查询实验 runs,支持过滤和排序 |
| query_traces.py | Analyze LLM traces by status, model, latency | 分析 LLM traces,按状态/模型/延迟过滤 |
| list_projects.py | List all accessible entities and projects | 列出所有可访问的 entities 和 projects |
| create_report.py | Generate shareable W&B reports | 生成可分享的 W&B 报告 |
Example Prompts / 示例提问
English:
- "Query the last 10 finished runs in my-team/my-project"
- "How many error traces are there?"
- "Find LLM calls with latency over 5 seconds"
- "Create a weekly training summary report"
中文:
- "帮我查询 my-team/my-project 里最近完成的 10 个 runs"
- "分析一下 traces 里有多少错误"
- "找出延迟超过 5 秒的 LLM 调用"
- "创建一个本周训练总结报告"
License
MIT