Stats
Actions
Tags
From archora-research
Designs detailed experimental protocols for validating research hypotheses, including variables, controls, power analysis, timeline, and expected outcomes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/archora-research:validationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Design rigorous experimental protocols to validate research hypotheses.
Design rigorous experimental protocols to validate research hypotheses.
For each hypothesis, produce a complete protocol with:
| Field | Description |
|---|---|
| Design | Experimental design type (RCT, quasi-experimental, longitudinal, in silico, etc.) |
| Independent Variable (IV) | What is manipulated |
| Dependent Variable (DV) | What is measured |
| Controls | Variables held constant |
| Sample Size | N per condition + power analysis (α=0.05, β=0.80, effect size) |
| Timeline | Phase-by-phase schedule |
| Protocol | Step-by-step procedure |
| Expected Outcome | What would confirm vs. refute the hypothesis |
Always include a power analysis. Standard parameters:
Example: 30 simulations per condition (90 total, power analysis: α=0.05, β=0.80, η²=0.25)
# 🧫 Experiment Design
## Strategy Overview
[2–3 sentences: how the experiments collectively test the hypotheses]
## Proposed Experiments
### Experiment 1: [Design Type]
**Tests Hypothesis:** [Exact hypothesis being tested]
| Parameter | Detail |
|-----------|--------|
| **Design** | [Design type] |
| **Sample Size** | [N per condition with power analysis] |
| **Timeline** | [X months: phase breakdown] |
**Independent Variables:** [What is manipulated]
**Dependent Variables:** [What is measured]
**Control Variables:** [What is held constant]
**Protocol:**
1. [Step 1]
2. [Step 2]
...
**Expected Outcome:** [What confirms the hypothesis. What would refute it.]
---
Before finalizing a protocol, consider:
npx claudepluginhub richard-kim-79/archora-skillsStructures biological experiments with controls, randomization, blinding, and power analysis to produce valid reproducible results. Uses GLP and Fisher principles.
Designs controlled experiments (A/B, multivariate, quasi) with hypothesis, success metrics, sample size, and statistical power. For validating features via /design-experiment or phrases like 'design experiment'.
Formulates falsifiable hypotheses from observations, operationalizes variables, designs experiments with controls, and defines falsification criteria.