agentleFS
adityareddy-devadityareddy-dev/deskstudio/skills/chart-design/SKILL.md

chart-design

Skill43 starsChanged 23 days agoMITView on GitHub

One chart that answers one question, as an HTML file with an inline SVG, colourblind-safe, directly labelled, with the takeaway as the title. Use when you have data and a point to make with it.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run: Read ${CLAUDE_PLUGIN_ROOT}/skills/desk/SKILL.md now and follow it from step 0 to step 7 as the Design Manager with the desks above.

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Make a chart as the Design Manager.

Deliverable and standard. A chart to ${CLAUDE_PLUGIN_ROOT}/skills/desk/standards/chart.md: the form picked from the question, the takeaway as the title, direct labels, honest axes, the accent on the point, palettes from the brand file. Title and labels to standards/copy.md.

Desks.

DeskAgentTierDoes
Data Viz Designerdesk:data-viz-designerbuilderthree roughs at the senior model (form, encoding, annotation), polish rounds
Copy Editordesk:copy-editorseniorthe title is a claim, the subtitle names the measure, every label plain
Typographerdesk:typographerseniortabular figures, label sizes, number formatting
Art Directordesk:art-directordirectorthe pick and the notes
Creative Directordesk:creative-directordirectorsign-off

Inputs. The question in text, and the data inline (a small table in the ask), as a CSV or JSON path, or as a screenshot of a table to transcribe (the transcription is shown in the brief for the user to check).

Proof sizes. By --for: card og,linkedin, slide slide, dashboard desktop (as a tile sheet). Default og.

Output under .desk/out/<id>/:

  • final.html: the chart per the file contract, inline SVG, hidden data table.
  • spec.json: type, data, encodings, palette, annotations, for a library build when the project uses one.
  • data.csv: the data as used, cleaned, with the source line.
  • chart.md: the question, the form and why, the palette by job, the annotations, what was not charted and why.
  • renders/ per size.

Run. Read ${CLAUDE_PLUGIN_ROOT}/skills/desk/SKILL.md now and follow it from step 0 to step 7 as the Design Manager with the desks above. Command name for state and events: chart-design. Changes to the loop for this command:

  • The brief's Copy block holds the title, subtitle, unit and source as the strings that must appear. The Data Viz Designer may propose a better title, which goes through the Copy Editor before polish.
  • Roughs are three forms or encodings of the same data in patterns from the standard, not three colourways. If the question only supports one form, the roughs differ in pattern (title and plot, big number, small multiples).
  • Proof runs with --must-appear for the title and the unit. The Data Viz Designer's own check (bars start at zero, no dual axis, palette passes the two red-green checks) is reported in its return and counts as a proof failure when it fails.

The ask: $ARGUMENTS

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.