Rewrites complex statistics (percentage changes, relative risk, confidence intervals) into plain language for a general audience without losing factual accuracy.
How this skill is triggered — by the user, by Claude, or both
Slash command
/autopunk-media-skills:statistics-explainerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Rewrites a complex statistic — including percentage changes, relative risk, confidence intervals, medians, and index numbers — in plain language that a general audience can understand without sacrificing factual accuracy.
Rewrites a complex statistic — including percentage changes, relative risk, confidence intervals, medians, and index numbers — in plain language that a general audience can understand without sacrificing factual accuracy.
Required: The statistic as it appears in the source (exact wording or data point). The context — what the statistic is measuring and from what study, report, or dataset. Optional: The audience (general public, specialist readers, etc.); the publication register (tabloid, broadsheet, academic journal); any related comparison figure that might help contextualise it.
Two to three rewrite options, each one to three sentences. A brief note explaining the key misinterpretation risk in the original. Where relevant, a suggested accuracy caveat (one sentence) to include alongside the plain-language version. No tables or bullet lists in the output — the rewrites should read as they would appear in an article.
Statistic: "The intervention group showed a relative risk reduction of 40% compared to the control group, with a confidence interval of 0.55–0.65 (p < 0.01)." Context: A clinical trial testing a new medication for reducing the recurrence of a common respiratory illness. The trial involved 2,400 participants. Baseline recurrence rate in the control group was 20% over 12 months. Audience: General news readers. Publication: national broadsheet health section.
Rewrite options:
Option 1: "In the trial, people who took the medication were significantly less likely to fall ill again within a year. Of every 100 people on the medication, about 12 had a recurrence — compared to 20 out of 100 who received no treatment."
Option 2: "The medication reduced the chance of falling ill again within a year from 20 in 100 people down to about 12 in 100. Researchers said the result was statistically robust and unlikely to be a chance finding."
Option 3 (most conservative): "Among trial participants, recurrence dropped from roughly 1 in 5 people in the untreated group to around 1 in 8 in the treated group over a 12-month period."
Key misinterpretation risk: The original states a "40% relative risk reduction." Most readers — and many journalists — interpret this as "40% of people were helped," which is wrong. The actual reduction is 8 percentage points (from 20% to 12%). The relative figure (40%) is mathematically correct but routinely misleads. All three rewrites use absolute numbers to avoid this.
Suggested accuracy caveat (include if editorial space allows): "The trial was conducted over 12 months; whether protection persists beyond that period has not been established."
npx claudepluginhub ur-grue/autopunk-media-skills --plugin autopunk-media-skillsSummarizes statistical reports into plain, journalist-ready language, extracting key findings and flagging verification needs before publication.
Statistical analysis for medical research papers. Generates reproducible Python/R code with publication-ready tables and figures for diagnostic accuracy, survival analysis, regression, propensity score, and repeated measures.
Translates academic research into accessible public content: op-eds, blog posts, community reports, policy briefs, podcast/media prep.