Paste raw CSV and get a clean SVG chart with sensible scales, labels on the data, and a title that says what the chart shows.
Turn this data into one clear chart, as a standalone SVG. What I want it to show: [THE QUESTION OR THE POINT, e.g. "signups jumped after the launch"] Where it's going: [e.g. slide, blog post, report] ```csv [PASTE YOUR CSV] ``` A few rules: - Pick the chart type that fits the data, and tell me why in one sentence. - The title states the finding, not the topic. "Signups tripled after the March launch", not "Signups by month". - Label values on the chart itself where you can, instead of using a legend. - Bar charts start at zero. Two colours at most: one neutral, one to highlight what matters. - Give me a single `<svg>` with a viewBox, built from basic shapes and text, so it scales and I can edit it later. - Under the chart, tell me one thing in the data I should double check before I publish.
A bar chart fits best, because these are twelve separate monthly totals. The launch month is highlighted and labelled directly, every other bar stays neutral, and the title states the finding.
NoteThis is an example. Results change between runs and model versions. Claude Prompts is a fan project and is not affiliated with Anthropic.
A small table that needs to become one clear chart for a slide, a report or a blog post. It's comfortable up to a few hundred rows. With bigger files, summarise first, or paste a sample and describe the rest.
Tell it what you want the chart to say. "Signups jumped after the launch" gets you a focused chart, and leaving it out gets you a generic one. Mention where it'll be used too, because a slide needs bigger labels and fewer gridlines than a report does. Not sure which chart type reads better? Ask for a second version and compare.
Compare a few values on the chart with your CSV, especially totals and anything that got sorted. The title states a finding, so make sure the data backs it up. "Tripled" should mean three times. Do read the "one thing to double check" line at the end. It often catches a missing month or an outlier that would be embarrassing after you've published.
Use the copy button above. The full text is included, nothing is cut off.
Everything highlighted in yellow is a placeholder. Swap it for your own topic, audience or data.
If the result helped, press the heart. Votes decide which prompts make the weekly top 10.
Give Claude one statistic and its context, and get a short animated visual in HTML that builds the number up step by step instead of just showing it.
1. Correctness Revenue is counted more than once. JOIN orderitems produces one row per item, so SUM(o.total) adds the same order total once for every item in it. An order with three items is tripled. "Today" is the server's...
Have a slow SQL query checked for wrong results first and speed second. You get a rewrite, the indexes to add, and a way to prove it's faster.
Describe a brand in one sentence and get four different logo directions as clean SVG you can open in a browser or drop into Figma.
One vote per prompt, a fresh count every Monday, and a simple tie-break. Everything about how prompts reach the top three, in plain words.
Wrapping parts of your prompt in simple tags is one of the easiest ways to get more reliable answers from Claude. A practical guide with examples.