$ loading_
Turn query results or DataFrames into publication-quality charts with Python.
The material indicates this is essentially an open-source prompt-style visualization workflow with no declared secrets or remote endpoints, so overall risk is low. Caution is still warranted because the instructions involve generating charts with Python, handling uploaded files, and potentially querying connected data sources, which in a real host environment usually implies local code execution and data access.
The material and objective checks indicate no required secrets or environment variables. There is no request for API tokens, database passwords, or other sensitive credentials, so credential exposure risk appears low.
No remote endpoints are declared, and the system checks also show no host. The README mentions querying a connected data warehouse if available, but it does not specify sending data to unknown third-party services. Based on the provided material, there is no clear network egress path.
The README explicitly instructs the skill to write and execute Python code to generate charts, with examples using matplotlib/seaborn/plotly and saving files. This is a normal local code-execution capability for visualization, with no evidence of excessive system privileges, but it should still be treated as executable code.
The material says it can handle query results, pasted data, CSV/Excel files, and existing conversation data, and it writes chart image files. This implies possible reading of local uploaded data, access to connected data sources, and writing output files; this is normal for this kind of skill, with no obvious sign of overbroad access.
The source is the GitHub repository anthropics/knowledge-work-plugins, and the system marks it as open-source and prompt-only, which are strong risk-reducing factors because the contents are auditable. Although the license is unspecified, stars are 0, and maintenance is unknown, there are no clear high-risk red flags such as closed-source exfiltration, malicious injection, or deceptive behavior in the provided material.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "create-viz" skill from askskill: 1. Download https://raw.githubusercontent.com/anthropics/knowledge-work-plugins/main/data/skills/create-viz/SKILL.md 2. Save it as ~/.claude/skills/create-viz/SKILL.md 3. Reload skills and tell me it's ready
Use Python to turn this monthly sales data into a presentation-ready line chart. Highlight the growth trend, add a title, axis labels, and annotations for key peaks, and return reusable code.
Runnable Python plotting code that produces a clear, polished sales trend line chart.
I have a DataFrame with product categories and revenue. Choose the most appropriate chart type and generate high-quality visualization code to compare category performance with professional report-ready styling.
A recommended chart type plus high-quality Python visualization code for category comparison.
Create an interactive chart from this dataset with hover values, zooming, and legend filtering, suitable for embedding in a webpage or sharing with the team.
Chart code or an embeddable result with interactive features for data exploration and sharing.
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Create publication-quality data visualizations using Python. Generates charts from data with best practices for clarity, accuracy, and design.
/create-viz <data source> [chart type] [additional instructions]
Determine:
If data warehouse is connected and data needs querying:
If data is pasted or uploaded:
If data is from a previous analysis in the conversation:
If the user didn't specify a chart type, recommend one based on the data and question:
| Data Relationship | Recommended Chart |
|---|---|
| Trend over time | Line chart |
| Comparison across categories | Bar chart (horizontal if many categories) |
| Part-to-whole composition | Stacked bar or area chart (avoid pie charts unless <6 categories) |
| Distribution of values | Histogram or box plot |
| Correlation between two variables | Scatter plot |
| Two-variable comparison over time | Dual-axis line or grouped bar |
| Geographic data | Choropleth map |
| Ranking | Horizontal bar chart |
| Flow or process | Sankey diagram |
| Matrix of relationships | Heatmap |
Explain the recommendation briefly if the user didn't specify.
Write Python code using one of these libraries based on the need:
Code requirements:
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
# Set professional style
plt.style.use('seaborn-v0_8-whitegrid')
sns.set_palette("husl")
# Create figure with appropriate size
fig, ax = plt.subplots(figsize=(10, 6))
# [chart-specific code]
# Always include:
ax.set_title('Clear, Descriptive Title', fontsize=14, fontweight='bold')
ax.set_xlabel('X-Axis Label', fontsize=11)
ax.set_ylabel('Y-Axis Label', fontsize=11)
# Format numbers appropriately
# - Percentages: '45.2%' not '0.452'
# - Currency: '$1.2M' not '1200000'
# - Large numbers: '2.3K' or '1.5M' not '2300' or '1500000'
# Remove chart junk
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
plt.tight_layout()
plt.savefig('chart_name.png', dpi=150, bbox_inches='tight')
plt.show()
Color:
Typography:
Layout:
Accuracy:
…
Create stakeholder updates tailored to audience, cadence, and communication goals.
Review an analysis for methodology, accuracy, bias, and evidence support.
Generate people analytics reports on headcount, attrition, diversity, and org health.
Identify, categorize, and prioritize technical debt for smarter refactoring decisions.
Choose the right Zoom surface for a product use case with clear tradeoffs.
Turn an approved brief into social assets, copy, and a staged campaign.
Create clear, professional Python data visualizations and choose suitable chart types.
Create shareable interactive HTML dashboards with charts, filters, and tables.
Create clear charts faster with AI-era data visualization specs and workflows.
Create multiple SVG and PNG chart types quickly for Python and AI agents.
Create original posters, illustrations, and static visuals in PNG or PDF.
Generate concept, architecture, flow, and whiteboard diagrams in multiple formats.