Skip to content
Skills Library
Data & analytics · Analysis

visualize-data

/visualize-data

Create charts, tables, and visualizations from queries. Use this whenever the user wants to see data as a chart or formatted table, or asks for a visualization.

Repository
skills ↗
Licence
Apache-2.0
Last repository change
27.10.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Create charts, tables, and visualizations from queries. Use this whenever the user wants to see data as a chart or formatted table, or asks for a visualization.

Original author description

Create charts, tables, and visualizations from queries. Use this whenever the user wants to see data as a chart or formatted table, or asks for a visualization.

How it works

  1. Goals
  2. Pre-requisites
  3. Authoring mode
  4. Recommended workflow
  5. Rules
Original SKILL.md headings · 37 lines, 454 words
SKILL.md preview
---
name: visualize-data
description: Create charts, tables, and visualizations from queries. Use this whenever the user wants to see data as a chart or formatted table, or asks for a visualization.
---

## Goals
* Create efficient but highly readable tables/charts by applying good visualization settings and formattings.
* Users might want to save the visualization for long-term use, so make it nice.

## Pre-requisites
* Set up Holistics MCP. If you call the tools through the `holistics mcp` CLI instead, follow *Calling tools via the CLI* in the `setup-amql-development` skill — parameters are one JSON object (for AQL/AML, a JSON file piped on stdin), never `key=value`.

## Authoring mode
Plugin setting: `${user_config.authoring_mode}`

Write the Viz yourself **only** when the authoring mode is `self`. It's set by, in priority order: the user in this conversation, the project's instructions (e.g. `CLAUDE.md`, `AGENTS.md`, Cursor rules — "Holistics authoring mode: self"), then the plugin setting above. Otherwise — including when the plugin setting above is an unfilled `${…}` placeholder — use Holistics AI.

**Decide the mode now, before anything else. In self mode, follow *Self mode* below and do NOT call `generate_viz`, except as its last-resort fallback.**

## Recommended workflow
### Holistics AI (default)
1. Write the AQL for the raw data (WITHOUT visualization requirements) with the [](../write-aql/) skill.
2. `generate_viz` to create a viz on top of that AQL query (apply visualization requirements and default formatting). Unless the user asked for a viz type, let it pick one.
3. `execute_viz` to run the viz and show the result to the user.

### Self mode
1. Read the dataset with `fetch_dataset`. If the data needs AQL beyond the dataset's fields (new metrics, filters, period comparisons), write it with the [](../write-aql/) skill — WITHOUT visualization requirements.
2. Write the Viz yourself using the [](../viz/) skill's references: pick the viz type, place the fields, and apply the visualization requirements and default formatting.
3. `execute_viz` to run the viz and show the result to the user. Fix any errors it reports and re-run. If it still fails after ~3 fix rounds, fall back to `generate_viz` with your last attempt and its errors.

Either way, if the viz can't be made to work, fall back to showing a plain table with `execute_aql`.

## Rules
* To visualize a plain table (no formatting, colors, etc.), you don't need a Viz — `execute_aql` is enough. Anything with formatting, conditional formatting, colors, or a chart type needs a Viz.
* To update date/time filters, change the AQL first (with [](../write-aql/)), then update the viz.
* Cohort retention should ALWAYS be visualized as Pivot Table.
* **Always** apply proper display formats to new percentage and currency dimensions/metrics.
  * Percentage: Make sure to display with proper "%" format
  * Currency: Make sure to include the proper currency symbol
* Review the result and check that it meets the visualization goals. Follow up to improve your visualizations if needed.

Versions

RepositoryScoreLicence
This page · holistics/skills90Apache-2.0
asgeirtj/system_prompts_leaks100CC0-1.0

Identical content appears in 1 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version c5f8486b1c9f (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100creating-data-visualizations
    Generate plots, charts, and graphs from data with automatic visualization type selection. Use when requesting "visualization", "plot", "chart", or "graph". Trigger with phrases like ''generate'', ''create'', or ''scaffold''.
  • 100creating-data-visualizations
    Generate plots, charts, and graphs from data with automatic visualization type selection. Use when requesting "visualization", "plot", "chart", or "graph". Trigger with phrases like 'generate', 'create', or 'scaffold'.
  • 100visualizations
    Use ONLY when the user explicitly asks to see, show, graph, visualize, chart, or plot data, or when another loaded Datadog data-domain skill directs you to visualization guidance. This is the plugin's local copy of the `datadog/visualizations` server skill; prefer it over…
  • 100svg-dashboard
    Use this skill when asked to generate SVG data visualization dashboards from investigation data or skill reports. Triggers on keywords like "generate SVG dashboard", "create a visual dashboard", "visualize this report", "SVG from the report", "visualize results", "create SVG…
  • 100chart-generation
    Use this skill for generating data-driven charts and visualizations using Python. Triggers: "create chart", "generate graph", "plot data", "visualize data", "bar chart", "line chart", "pie chart", "comparison chart", "positioning matrix", "trend chart", "market size chart", "TAM…
  • 100show
    Create and review inline visual explanations, diagrams, interactive widgets, mockups, charts, and illustrations. Triggers on "/show", "show me", "draw", "diagram this", "visualize", "map this out", "make it interactive", or a request for a mockup, chart, or illustration.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.