figure-generation

The figure-generation skill creates publication-quality scientific visualizations using a three-phase pipeline involving query expansion, iterative Python code generation with execution, and VLM-based visual refinement.

1.1K
Installs
4
Use cases
9/10
Quality

Is figure-generation safe to install?

Review the source first

Review the source first: our audit of figure-generation's source files found 3 shell commands, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes arbitrary Python scripts generated by the agent and reads/writes local files, including data files and generated image outputs.

How we audit skills: our security review methodology.

Who is this skill for?

Researchers and academics who need to generate scientific plots, charts, and figures for papers.

What can you do with it?

  • Generating bar charts, line plots, heatmaps, and training curves
  • Creating ablation plots and t-SNE visualizations
  • Producing vector-ready PDF and 300 DPI PNG figures for LaTeX documents
  • Refining figure aesthetics based on visual feedback

How good is this skill?

Quality score: 9/10. The skill documentation is clear and follows a logical pipeline. It specifies requirements for publication quality, such as DPI and colorblind-friendly palettes.

What does the skill file contain?

SKILL.md
# Scientific Figure Generation

Generate publication-quality figures for research papers.

## Input

- `$0` — Description of the desired figure
- `$1` — (Optional) Path to data file (CSV, JSON, NPY, PKL) or results directory

## Scripts

### Generate figure template
```bash
python ~/.claude/skills/figure-generation/scripts/figure_template.py --type bar --output figure_script.py --name comparison
python ~/.claude/skills/figure-generation/scripts/figure_template.py --list-types
```

Available types: `bar`, `training-curve`, `heatmap`, `ablation`, `line`, `scatter`, `radar`, `violin`, `tsne`, `at...

Frequently asked questions

What file formats does the skill support for input data?

The skill accepts CSV, JSON, NPY, and PKL files.

How does the skill handle errors during code execution?

The skill captures tracebacks from failed executions and feeds them back into the generation loop for up to four retries.

Does the skill produce LaTeX code?

Yes, the skill provides the LaTeX include code block for the generated figure.

Data sourced from lingzhi227/agent-research-skills on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Related skills

customer-research

46.7K

Product marketers, founders, and researchers who need to ground their strategy in customer data

The customer-research skill provides a framework for analyzing existing research assets and gathering new insights from online communities to inform product marketing, messaging, and persona development.

lowresearchmarketingcoreyhaines31

persona-researcher

17.1K

Researchers and project teams using Google Workspace for data management and documentation

The persona-researcher skill organizes research materials, manages references, and facilitates collaboration across Google Workspace applications.

highresearchgoogle-workspacegoogleworkspace

firecrawl-lead-research

12.7K

Sales professionals, partnership managers, investors, and interviewers preparing for meetings

The firecrawl-lead-research skill generates pre-meeting intelligence briefs by scraping company websites, news, and public profiles using the Firecrawl API.

highresearchsalesfirecrawl

market-research

5.5K

Users performing business research, investor outreach, or strategic planning

The market-research skill provides a structured framework for conducting competitive analysis, investor due diligence, market sizing, and technology assessments. It enforces source attribution and requires the agent to translate data into actionable recommendations.

noneresearchbusinessaffaan-m