data-visualiselisted

Orchestrate visual output from tabular data or a data-analyse analysis.json into either (1) a brandable self-contained HTML dashboard (print/PDF / artifact) or (2) an Excel workbook of native charts for analysts. Use when the user says "build a dashboard", "visualise this", "make a chart / KPI cards / scorecard", "Excel charts", "chart this in a spreadsheet", "a one-pager of these numbers", "RAG status board", or wants a shareable visual summary. HTML path: inline SVG, no CDN. Excel path: openpyxl charts with OfficeCLI-aligned chartType names (column/bar/line/pie/doughnut/waterfall). Draft for review, not advice. NOT PowerPoint or letters; clean/extract first via data-tidy / data-extract; compute metrics via data-analyse when numbers must be exact.
moonlight-lupin/data-toolkit · ★ 0 · Data & Documents · score 72

Install: claude install-skill moonlight-lupin/data-toolkit

# Data Visualise This skill **orchestrates** which visual artefact to build. Two renderers, one metrics contract (`analysis.json` or declarative specs): | Artefact | Engine | Choose when | |---|---|---| | **HTML dashboard** (`.html`) | `scripts/viz.py` | Shareable one-pager, print/PDF, branded board, Cowork/Claude artifact | | **Excel charts** (`.xlsx`) | `scripts/workbook.py` | Analysts will keep working in Excel; native charts matter | Both are local, offline, and draft-for-review. PowerPoint and letters stay out of scope. ## HTML / Excel parity (treat them as peers) **Neither path requires data-analyse.** A simple table (CSV / JSON / `.xlsx`) is enough for both. What differs is only the *renderer* and how you declare the series — not whether the job is allowed. | Starting point | HTML | Excel | |---|---|---| | Plain table | `input` + block `data` / `"rows": "$source"` | `type: "chart"` with `categories` + `series` (derive from the same table in Python) | | `analysis.json` | `"blocks": "$analysis"` / `from_analysis` | same shortcut → chart sheets | | Both artefacts | same numbers → HTML blocks **and** Excel chart specs | | **Do not** steer every Excel request through analyse first, and **do not** treat HTML as the only “simple data” path. Build the category/value series once from the table, then: - HTML → `bar_chart` / `line_chart` / `donut_chart` / `waterfall` / `table`… - Excel → `chart_type` `column` / `line` / `pie` / `doughnut` / `waterfall`… Rough block ↔ cha