AI Blocks › Research a topic properly
Study design and randomizer
Describe your study. Get a design, random group assignment and run order that avoid confounded results.
Study design and randomizer is a free AI skill for the job "Research a topic properly". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · MIT licence · Made by K-Dense · Level: advanced · Thinking: high
Made by K-Dense. See the original on GitHub; we copied it as it is, with its licence.
What it does
Plan an experiment so the results mean something. You leave with a design, a random assignment and a run order that stops hidden factors from muddying the answer. You describe what you are testing, the units you have and the factors involved. The skill helps choose a design, then generates it with Python scripts. They build randomisation schedules, including permuted blocks, stratified groups and whole-cluster assignment, and layouts for factorial, screening and response-surface experiments in real-world units. It also lists the common mistakes that ruin studies, such as confounded groups and unbalanced blocks, and checks your plan against them. It needs Python.
You give it
- The question you want to test
- The units, such as people or samples, and how many
- The factors and their ranges
- Any grouping variable to balance, like age (optional)
You get
- A recommended study design
- A random allocation schedule
- A run order
- A table of treatment combinations
- A list of design pitfalls to avoid
Use it when
- You are about to run a trial and need to assign people or samples to groups.
- You want to test several factors without running every combination.
- You worry the order of runs will bias your results.
- A reviewer asked how you randomised.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can run Python code.