Your analysis is done. What is the story?
Paste the finished analysis - the findings in prose or bullets and the tables behind them - pick the audience and say what you want decided. Your browser numbers every data point, recomputes every table's changes and every weighted scoring matrix (and flags the stated figures that do not match), and checks the skill's rules: no data dump, no methodology first, no cause the analysis did not test, the sample size said, no jargon. Free, before you sign in, and nothing is uploaded. Then the story lane writes the headline, three points and the arc, and the deck lane storyboards the slides.
The companies and numbers are invented. Two are stories (the quarter one also carries its storyboard, one click after the story) and one is a storyboard; each comes with a saved model reply, so you can see the whole page without signing in or spending a credit.
What this does, and what it does not
Most analyses are presented in the order they were done: the data source, the method, then twenty charts, and the finding on the last slide. The skill behind this page works the other way round: start with the "so what", carry three points, build through the data to one key insight, and end with the action you want. Part of that is checkable before any model sees your work - whether a stated change matches its own table, whether a weighted score adds up, whether the paste opens with the method, claims a cause, rests on a small sample or uses words the audience will not - so the page does it for free.
The story lane answers every flag, picks the problem-solution, trend or comparison framework, writes a headline by the skill's formula - a specific number, the business impact, actionable context - and two more, chooses the three points and their data, writes the six beats of the arc, and lists what to cut, the caveats and the ask. The deck lane turns it - or the analysis directly - into the seven slides of the skill's data story flow. Every figure in a reply must come from your paste or the page's reading; a figure your own table contradicts must not reach a slide.
The paid lanes see your analysis (up to 14,000 characters, the middle cut on whole lines beyond that) and the page's reading. Your paste stays in this browser unless you run a lane. The page checks arithmetic and wording, not whether your analysis is right: a story can only be as sound as the work under it. Derived from the agent skill @wshobson/data-storytelling (wshobson/agents, MIT: story structure and the narrative arc, the problem-solution, trend and comparison frameworks, the headline formula, the do's and don'ts, handling uncertainty, and the data story flow). Sources are listed in llms.txt.