agentsclimarketplace

Data visualization

Skill shinzoxD/knackbox/skills/data/data-visualization

Curated, auditable, benchmark-ready Agent Skills library for Claude Code, Codex, OpenCode, Cursor, and more.

Install
npx -y skills add shinzoxD/knackbox --skill data-visualization

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 28 days oldThe repository was created 28 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Choose and produce clear, honest charts from tabular or summarized data. Use whenever the user asks for a chart, dashboard, plot, visual comparison, trend view, or advice on how to visualize data, including requests to improve an existing graph or select the right chart type.

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.8 KB, 484 tokens by cl100k_base, as published. Nobody here has run it

Data Visualization

Build a visual that answers one decision-relevant question. Select the chart from the analytical task, not from novelty or decoration.

Workflow

  1. State the question the chart must answer and the intended audience.
  2. Verify the fields, units, time grain, missing values, and aggregation.
  3. Choose an encoding that matches the task.
  4. Build the simplest legible chart and label the important evidence directly.
  5. Check scale integrity, color accessibility, and mobile readability.
  6. Include the data source, transformations, and caveats.

Chart selection

  • Trend over time: line chart; use bars for short discrete periods.
  • Category comparison: sorted bars or dot plot.
  • Distribution: histogram, box plot, or density plot with sample size.
  • Relationship: scatter plot with units and an optional justified trendline.
  • Part to whole: stacked bars for a few comparable groups; avoid many slices.
  • Geographic pattern: map only when location is analytically meaningful.
  • Operational monitoring: compact time series, thresholds, and current value.

Output format

## Visual specification

**Question:** ...
**Chart:** ... because ...
**X / Y / color / facet:** ...
**Aggregation:** ...
**Annotations:** ...
**Accessibility:** palette, text alternative, table fallback
**Caveats:** ...

When code is requested, return runnable code plus the generated artifact or a precise preview description.

Rules

  1. Start quantitative axes at zero for bars unless a clearly labeled exception is necessary. Lines may use a focused scale when it does not exaggerate.
  2. Do not use 3D effects, decorative gradients, or area encodings that distort comparisons.
  3. Use color to encode meaning, not to compensate for weak hierarchy.
  4. Label units, denominators, date ranges, and filters.
  5. Do not imply causation from correlation or continuity across missing periods.
  6. Provide a table or text summary for users who cannot inspect the chart.

Edge cases

  • For dual axes, prefer separate aligned charts; use dual axes only with an explicit reason and unmistakable labels.
  • For small samples, show individual observations when privacy allows.
  • For dashboards, prioritize repeated scanning and comparison over card-heavy decoration.

Gives 0 of the 12 instructions most data analysis skills give in 484 tokens

Counted across 286 of the 286 authors here whose files we hold, read 2026-08-06

  • use excel formulas instead of hardcoded calculated valuesin 35 of 286, across 7 files
  • match existing template conventions when modifying filesin 35 of 286, across 7 files
  • document sources for all hardcoded valuesin 35 of 286, across 7 files
  • write minimal concise python codein 35 of 286, across 7 files
  • place all assumptions in separate assumption cellsin 32 of 286, across 5 files
  • apply industry-standard color coding to financial modelsin 31 of 286, across 5 files
  • format years as text stringsin 30 of 286, across 3 files
  • recalculate formulas using recalc.py after modificationsin 30 of 286, across 3 files
  • format negative numbers using parenthesesin 30 of 286, across 3 files
  • fix all identified formula errors before finishingin 27 of 286, across 1 file
  • use colorblind-safe palettesin 19 of 286, across 12 files
  • Name tests after the prevented bugin 13 of 286, across 8 files

Said here and by no other author read

  • select chart type from the analytical task
  • state the question and the intended audience
  • verify fields units aggregations and missing values
  • choose an encoding matching the task
  • build the simplest legible chart
  • label important evidence directly

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.