Skip to content
Get packs

Visualize Data

Makes the agent design, build, and QA quantitative charts that match the analytical takeaway

Source Download skill
Repository
XiaomiMiMo/MiMo-Code
Stars
13,743
Licence
MIT
Files
2 files

What it does

Once installed, the agent treats charts as evidence rather than decoration. Before drawing anything, it states the question the chart should answer, checks the data's grain, units, filters, and missing values, and picks a chart type that fits the relationship in the data (for example a line chart for change over time, a bar chart for category comparison, a waterfall for contributions to change). It then labels axes, sorts and scales sensibly, and checks the finished output against the source numbers.

Great for

  • Analysts who want clear, correct charts for reports, dashboards, or slides
  • Developers producing reproducible Matplotlib or SVG figures for files and notebooks
  • Anyone who wants a chart-QA pass to catch misleading axes or wrong values

Skip it if

  • Users who need a fully interactive dashboard with a specific BI tool, since the skill steers toward static or native-notebook output and avoids adding UI frameworks
  • Decisions that depend on causal claims, because the skill warns against implying causality but cannot establish it from a chart

Try asking

  • “Make a line chart of monthly active users for the last 12 months and label the key change”
  • “Turn this CSV of regional sales into a bar chart sorted by revenue with a source note”
  • “Review this chart I made for errors in scale, labels, or values before I put it in the report”
  • “Create a waterfall showing what drove the change in profit between Q1 and Q2”
Step-by-step guide: how to use Visualize DataInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    visualize-data.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip visualize-data.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip visualize-data.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Tell the agent the intended takeaway and audience up front so it can choose the chart type and title accordingly
  • Provide the data file or rows so the agent can recompute plotted values during QA
  • Ask for the reproducible code or notebook if you need an auditable chart you can rerun

What's inside

  • agents/openai.yaml
  • SKILL.md

Redistributed unmodified from XiaomiMiMo/MiMo-Code under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.