Skip to main content
scientific-schematicsby K-DenseDesignGitHub stars: 47.3k

Scientific Schematics skill: what it does and how to install it

Creates publication-quality scientific diagrams with Nano Banana 2, then reviews and selectively refines them with Gemini 3.6 Flash for the intended document type.

Summary generated from the skill's documentation.

Install

$ npx skills add K-Dense-AI/scientific-agent-skills --skill scientific-schematics

Run it in a terminal. If your agent is already running, start a new session so it picks the skill up.

About this skill

What it does. Generates PNG schematics from natural-language descriptions using Nano Banana 2, then sends each image to Gemini 3.6 Flash for quality scoring and regenerates only when it misses the threshold. A Python command supports document-type thresholds, versioned outputs and review logs.

When to use it. For neural-network architectures, flowcharts, biological pathways, system diagrams, circuits and other scientific figures. It does not produce vector files or control DPI, so print conversion and visual checking remain downstream.

History

Repo stars

47.3kAbout +18.6k since 9 Jul 2026

Before 1 Oct 2026 the curve is estimated from public event data.

Stars are counted for the whole repository, which holds 50 skills.

Show as a table
Repo stars by day
DateRepo stars
1 Oct 202647,271
24 Sept 2026 (estimated)46,976
17 Sept 2026 (estimated)46,257
10 Sept 2026 (estimated)41,836
3 Sept 2026 (estimated)30,545
27 Aug 2026 (estimated)29,347
20 Aug 2026 (estimated)29,160
13 Aug 2026 (estimated)29,027
6 Aug 2026 (estimated)28,947
30 Jul 2026 (estimated)28,894
23 Jul 2026 (estimated)28,894
16 Jul 2026 (estimated)28,841
9 Jul 2026 (estimated)28,708

Installs

1.9k

Tracking since . A chart appears once there are 7 days of data.

Installs via skills.sh

Similar skills