Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.
Passed 19 of 22 test cases with the skill, and 6 of 22 without it.
and 17 more in the full report
13 fixed6 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
Here is the system overview for our multi-agent framework paper: We have three primary components — a Planner, an Executor, and a Verifier. The Planner generates multi-step plans and passes them to the Executor, which executes the actions and sends execution results to the Verifier. If the Verifier detects an error, it sends a feedback signal back to the Planner for revision. Can you generate the appropriate code script to produce a clear, paper-ready conceptual diagram for this pipeline, formatted nicely for an academic submission?
| Checked | Without skill | With skill |
|---|---|---|
| The script uses gemini-3-pro-image-preview as the generation model. | Missed | Passed |
| The script runs 3 generation attempts in a loop. | Missed | Passed |
| The script retrieves the API key using os.environ. | Missed | Passed |
The instructions your model reads when the skill loads.
Generate publication-quality figures for ML/AI conference papers. Two distinct workflows:
| Figure Type | Tool | Why |
|---|---|---|
| Architecture / system diagram | Gemini (Workflow 1) | Complex spatial layouts with boxes, arrows, labels |
| Workflow / pipeline / lifecycle | Gemini (Workflow 1) | Multi-step processes with connections |
| Bar chart, line plot, scatter | matplotlib (Workflow 2) | Precise numerical data, reproducible |
| Heatmap, confusion matrix | matplotlib/seaborn (Workflow 2) | Structured grid data |
| Ablation table as chart | matplotlib (Workflow 2) | Grouped bars or line comparisons |
| Pie / donut chart | matplotlib (Workflow 2) | Proportional data (use sparingly in ML papers) |
| Training curves | matplotlib (Workflow 2) | Loss/accuracy over steps/epochs |
Rule of thumb: If the figure has numerical axes, use matplotlib. If the figure has boxes and arrows, use Gemini.
test cases passed, vs 6 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.