data-explorer

Installation
SKILL.md

Data explorer

A data explorer is one report.json: the data rows, the filters, and the blocks on each tab. This skill's template draws it like an analytics tool: tabs in a top bar, a strip of numbers (top) and a list of evidence rows (bottom) that stay on every tab, the blocks of the tab between them, and a filter sidebar where every name keeps one color across the page. You decide what to show; the template owns how it looks. You write no HTML, CSS or page script.

Words are the scarcest thing on the page. A reader scans numbers, colors and bars; prose goes in method.

When the reader has to choose between options or approve a plan, write a report instead: a page with the answer first.

The block reference is references/blocks.md; read it before step 1.

Steps

  1. Questions. From the request, write the 3 to 6 questions the reader wants answered. Each becomes a tab. Name each one's shape from the first column of Which block for which question, from the rows for a tab, not top or bottom. Done when every question has a shape and none overlaps another.

  2. Profile. Write a short script that prints, for each source file, its row count, every field with its type, range and share of nulls, and a few sample rows. Read the source's README for what each field means and how it was counted. Done when you can name the fields and the join keys each question needs, and the caveats the README states.

Installs
1
Repository
vite-hub/drop
GitHub Stars
9
First Seen
4 days ago