用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/pymc-labs/pymc-marketing --skill research命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | research |
| description | Structure a research based on the user request. Identify what must change in order to complete the task. |
| disable-model-invocation | true |
Structure a research based on the user request. Identify what must change in order to complete the task.
You must:
No user interaction required: - DO NOT ask for clarifications or wait for input
Create temporal python files, check the logics you are thinking on the root folder. Execute this python code, and based on the output decide what should be done.
Once you test the code out of the code base using this temporal python files and functions, document the approach using natural language.
Use the python files with objective:
Delete the files once, you finish your testing.
Your goal is create a folder under .cursor/plans. You must save all your discoveries under .cursor/plans/{plan_name_folder}/research this must be a file .md.
You only need to provide the research plan and a possible tested solution.
No other md files are needed, everything must be collapse in the research file.
Media Mix Modeling with PyMC-Marketing. Use when building MMMs, specifying adstock/saturation transformations, setting priors, fitting multidimensional (geo-level) models, computing channel contributions, ROAS, running budget optimization, calibrating with lift tests, or performing sensitivity analysis. Covers the MMM class, GeometricAdstock, LogisticSaturation, BudgetOptimizerWrapper, and ArviZ diagnostics for marketing models.
Learn how to work in the current folder (repository)
Fixing and validating Jupyter notebooks in pymc-marketing. Use when notebooks fail CI, need arviz_plots 2.x migration fixes, or when source code changes require notebook output updates.