Reads data points or series and identifies meaningful trends in plain language for reporting. Useful for data-driven writing and verifying trend claims.
How this skill is triggered — by the user, by Claude, or both
Slash command
/autopunk-media-skills:trend-identifierThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Reads a set of data points or a described data series and identifies the meaningful trends within it, expressed in plain, publication-ready language.
Reads a set of data points or a described data series and identifies the meaningful trends within it, expressed in plain, publication-ready language.
Required: The data series itself — paste the numbers, a description of the figures, or a summary table. Include what each value represents (e.g. percentage, count, rate per 100,000), the time period each corresponds to, and what geography or population it covers. Optional: The publication format (news article, documentary script, data visualisation caption, broadcast voice-over); the audience (general public, specialist, policymakers); any hypothesis or angle you already have about the data; a note on the source of the figures.
Two sections:
Trend Summary — 2–4 sentences describing the primary trend in plain language. Precise enough to quote directly in a story. Includes the percentage or absolute change where relevant, the time span, and one note on any meaningful caveat.
Detailed Findings — a bulleted list of 4–8 specific observations: the main trend, any sub-trends, inflection points, outliers, and an honest assessment of what the data does and does not allow you to conclude. Each bullet is one to two sentences.
Total length: 300–500 words. Tone: clear and direct — the language a senior editor would expect in a data memo, not a statistics paper.
Data: Annual road fatalities per million inhabitants, a mid-sized European country, 2010–2023.
2010: 68 2011: 61 2012: 57 2013: 54 2014: 50 2015: 49 2016: 47 2017: 46 2018: 45 2019: 43 2020: 37 2021: 41 2022: 44 2023: 43
Source: national road safety agency, administrative data. Format: opening paragraph for a long-read magazine feature on road safety. Audience: general public.
Trend Summary
Road deaths fell sharply over the first decade of this record — from 68 deaths per million people in 2010 to 43 in 2019, a reduction of 37% in nine years. The Covid-19 pandemic produced a dramatic one-year drop to 37 in 2020, as traffic volumes collapsed. But the recovery in driving has not been matched by a recovery in safety: fatalities rose in 2021 and 2022, reaching 44 — nearly erasing the gains of the previous four years — before edging back to 43 in 2023. The long-term downward trend has stalled.
Detailed Findings
npx claudepluginhub ur-grue/autopunk-media-skills --plugin autopunk-media-skillsFinds newsworthy angles, outliers, trends, and comparisons hidden in datasets. Use when you need to pitch a data story or stress-test a dataset before reporting.
Applies descriptive stats, trend analysis, outlier detection, hypothesis testing to distributions, anomalies, correlations, and business metrics.
Generate investigative journalism tipsheets from unfamiliar data collections. Use this skill whenever a user provides a dataset, document collection, database, or other raw material and wants to find leads, signals, patterns, outliers, or story tips — especially when the data is large, messy, or unfamiliar. Also trigger when the user says things like "what's in here", "anything interesting in this data", "find me leads", "tipsheet", "story ideas from this", "what jumps out", or when they drop a large dataset and want an initial assessment. This skill handles everything from a single CSV to multi-gigabyte collections with millions of records.