Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →k-dense-ai/designing-the-analysis
Use when you have an approved research question and need a concrete analysis plan, before touching outcome data or fitting any model
Passed 21 of 22 test cases with the skill, and 17 of 22 without it.
and 1 more in the full report
4 fixed17 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Task 4 in our plan needs the exact same data filtering logic as Task 2. Should we write 'Run filtering similar to Task 2' in Task 4's instructions?
| Checked | Without skill | With skill |
|---|---|---|
| The response requires explicitly repeating specific task instructions rather than referencing prior steps. | Missed | Passed |
The instructions your model reads when the skill loads.
Write a comprehensive analysis plan assuming the analyst has zero context for this project and questionable statistical taste. Document everything they need: which datasets and variables, how each construct is computed, the exact model or test, the sample size / power justification, which confounds are handled and how, the decision rules, and the planned figures. Give them the whole thing as bite-sized steps. DRY. YAGNI. Pre-register. Validate pipelines on known data. Commit frequently.
Assume they are a capable programmer but know almost nothing about this domain, this dataset, or good statistical design.
Announce at start: "I'm using the designing-the-analysis skill to create the analysis plan."
Save plans to: docs/science-superpowers/plans/YYYY-MM-DD-<topic>.md
If the question document still bundles several independent investigations, stop and split it — one plan per question. Each plan should produce an interpretable, self-contained result.
docs/science-superpowers/questions/...)If you don't have a prior effect size, the design must include how you will justify the sample size anyway (smallest effect of interest, precision target, or a sensitivity analysis).
Before defining steps, map the pipeline. Data flows one direction: raw → cleaned → derived → results.
For each known confound from the survey, state how it is handled: measured and adjusted for, stratified, matched, design-excluded, or explicitly acknowledged as a limitation. "We'll see" is not a plan.
State the threats to validity you are accepting and why.
test cases passed, vs 17 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.