来源信息
- 仓库
- google-gemini/gemini-managed-agents-templates
- 最近来源活动
- 2026年5月6日 16:01
- 检测到的 SKILL.md 语言
- 英语
- 星标
- 95
- 分支
- 38
安装方式
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
检查来源文件
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
正在显示 SKILL.md
SKILL.md
来源说明 · 只读预览- name
- python-data
- description
- Performs heavy numerical compute and statistical analysis inside the sandbox.
# Python data skill
Run complex calculations, regressions, and aggregations using pandas and
scikit-learn in the sandbox.
## Workflow
1. **Write a Python script** using `pandas`, `numpy`, or `sklearn` to:
- Join, filter, and aggregate tables.
- Compute statistics (mean, median, stddev, correlations).
- Build or evaluate ML models.
- Run statistical tests (chi-square, t-test) when appropriate.
2. **Execute in the sandbox.** Run via `python3 script.py`.
3. **Handle errors.** If the code fails, read the traceback and fix it.
4. **Return structured output.** Print results as JSON for downstream skills.
## Example output
```json
[
{"segment": "High Risk", "churn_rate": 0.34, "avg_tenure": 2.1},
{"segment": "Low Risk", "churn_rate": 0.05, "avg_tenure": 14.7}
]
```
## Notes
- Use `select_dtypes(include=["object", "str"])` for categorical columns
(avoids the pandas 4 deprecation warning).
- Install missing packages with `pip install -q <package>` before importing.
在 GitHub 查看