hypothesis-checklisted

Tests a stated hypothesis against quantitative survey data (CSV) and delivers a verdict: confirmed / partly confirmed / refuted — including a Chi-square significance test, effect size and a counter-check. Result as Markdown to reports/. Use when the user wants an assumption, claim or hunch verified/falsified. Invoke with your request as the argument, e.g. /hypothesis-check <hypothesis>.
kayspiegel/survey-insight-skills · ★ 2 · Data & Documents · score 76

Install: claude install-skill kayspiegel/survey-insight-skills

# Hypothesis Check Goal: Rigorously test the **hypothesis** in the user's request against the data and give an **evidence-backed, directional verdict** — not just describe, but test. Result as Markdown in `reports/`. ## Tool (shared analysis engine) ``` python3 scripts/survey.py <cmd> [...] [--file CSV] ``` Run these from the project root. If `scripts/survey.py` is not there, check `.claude/scripts/survey.py` or locate `survey.py` in the project. - `profile` — column overview (index, type, fill). **Always first.** - `freq COL [--by COL2] [--filter "COL=VALUE"] [--top N] [--sig]` — distribution/cross-tab. **`--sig`** (single-choice × single-choice only) returns Chi-square, p-value, Cramér's V and a warning when expected cell counts are too small. - `text COL [--filter ...] [--sample N]` — free text for qualitative evidence. `COL` = index (from `profile`) or an unambiguous name part. `--json` for machine-readable. ## Survey context If a context document sits next to the CSV (`<name>.context.md`, or `survey-context.md` when the folder holds exactly one CSV), read it before testing. It carries the subject, the glossary and the study design; use it for framing and terminology, never for figures. Its recruiting route and **"Who is missing"** section belong in this report's limitations — a hypothesis can hold in the sample and still fail for the population the sample cannot reach, and that is worth a sentence. Its **expectations** section deserves particular care here, b