AI Blocks › Track your numbers
Research test picker and reporter
Give it your data and question. Get the right test, assumption checks, effect sizes and a write-up in APA style.
Research test picker and reporter is a free AI skill for the job "Track your numbers". 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
Made by K-Dense. See the original on GitHub; we copied it as it is, with its licence.
What it does
The right statistical test for your question, run properly, and written up in APA style. You describe your data and what you want to know, and you get a choice of test with the reason for it, checks that its assumptions hold, effect sizes with confidence intervals, and report-ready wording. It begins by framing the hypothesis and design: paired or independent, how many groups. It looks at each group's size, spread and missing values, then picks a test such as a t-test, ANOVA, chi-square, regression or Bayesian model. It always reports the size of the effect, not only the p-value, and can work out how many participants you need. It needs Python with scientific packages.
You give it
- Your data file or a description of it
- The research question
- The study design
- The alpha level you use (optional)
You get
- A test recommendation with reasons
- Assumption check results
- Effect sizes with confidence intervals
- A power or sample size estimate
- APA-style results text
Use it when
- You have two or three groups of results and are unsure which test fits.
- A journal asks for effect sizes and assumption checks, not just p-values.
- You need to know how many participants a study requires.
- You want a methods and results paragraph written in APA format.
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 code.