Vega-Lite Interactive Charts

What it does

When your agent uses it

• Visualizing an uploaded CSV with several suitable chart types
• Requesting a specific chart type such as a boxplot or stacked bar
• Producing portable Vega-Lite JSON specs with embedded data

Example prompts

• “Chart the monthly sales in sales.csv and suggest which views are most informative.”
• “Make a grouped bar chart comparing the assay results by sample group.”
• “Build a Vega-Lite boxplot of response times by endpoint with the data embedded inline.”

Requirements

• Python with pandas for the data analysis script

Workflow steps

10 steps, taken from the step headings in SKILL.md.

1. 1Analyze Data Structure
2. 2Understand Data Context
3. 3Select Meaningful Charts (5-10 suggestions)
4. 4Generate Chart Specs
5. 5Create Artifact with Inline Data Island
6. 6Provide Link
7. 7Analyze Data
8. 8Validate Chart Fits Data
9. 9Generate Spec
10. 10Create Artifact

What it can do on your machine

Read from SKILL.md and the folder at commit 63d432e. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/, which the agent can run.

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vega-Lite Interactive Charts loads about 2.1k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 114 tokens; SKILL.md has 758 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~114

When it runs · the whole SKILL.md, loaded when a task matches

~2.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~18k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from oaustegard/claude-skills at commit 63d432e, republished under its MIT licence (© oaustegard). 758 words, ~2,095 tokens.

name

charting-vega-lite

description

Create interactive data visualizations using Vega-Lite declarative JSON grammar. Supports 20+ chart types (bar, line, scatter, histogram, boxplot, grouped/stacked variations, etc.) via templates and programmatic builders. Use when users upload data for charting, request specific chart types, or mention visualizations. Produces portable JSON specs with inline data islands that work in Claude artifacts and can be adapted for production.

metadata.version

0.1.0

const DATA = [ /* embedded data array */ ];

// Later in chart specs:
spec.data = { values: DATA };

python /mnt/skills/user/charting-vega-lite/scripts/analyze_data.py /mnt/user-data/uploads/<filename>

import pandas as pd
df = pd.read_csv('/mnt/user-data/uploads/<filename>')
# Classify: numeric→quantitative, datetime→temporal, <20 unique→nominal

{"type": "Chart Name", "reason": "Why this chart", "spec": {/* vega-lite spec */}}

[View chart explorer](computer:///mnt/user-data/outputs/ChartExplorer.jsx)

Created 7 contextually relevant charts for your data.

python /mnt/skills/user/charting-vega-lite/scripts/analyze_data.py /mnt/user-data/uploads/<filename>

# 1. Analyze
python /mnt/skills/user/charting-vega-lite/scripts/analyze_data.py /mnt/user-data/uploads/assay_data.csv

# 2. Understand context: Multi-analyte immunoassay
#    Questions: Which biomarkers strongest? Patterns across samples? Variability?

# 3. Build contextual charts (5-7 specs)
#    Bar: Mean signal by assay
#    Heatmap: Sample × Assay
#    Box plot: Signal distribution by assay
#    Histogram: Overall signal distribution
#    etc.

# 4. Load data and template
df = pd.read_csv('/mnt/user-data/uploads/assay_data.csv')
data = df.to_dict(orient='records')
template = open('/mnt/skills/user/charting-vega-lite/assets/components/ChartExplorer.jsx').read()

# 5. Replace placeholders and write
artifact = template.replace('__DATA__', json.dumps(data)).replace('__CHART_SPECS__', json.dumps(charts))
# Use bash heredoc to avoid XML conflicts in tool parameters

# 6. Provide link

© oaustegard, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 19 other files (scripts, references, assets) in charting-vega-lite of oaustegard/claude-skills.

• SKILL.md
• README.md
• assets/components/ChartExplorer.jsx
• assets/templates/area.json
• assets/templates/bar.json
• assets/templates/heatmap.json
• assets/templates/line.json
• assets/templates/pie.json
• assets/templates/scatter.json
• references/advanced-charts.md
• references/chart-types.md
• references/contextual-chart-selection.md
• references/customization.md
• references/data-driven-workflow.md
• references/online-resources.md
• references/spec-builder-patterns.md
• references/vega-lite-examples-inventory.md
• … and 3 more

Open the folder on GitHubat commit 63d432e