AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Scientific Schematics Generator

Describe a scientific diagram in plain language and get a publication-quality PNG, auto-regenerated only when an AI reviewer scores it below your document type's threshold.

Image & VideoIntermediate★ 33,030⑂ 3,248AI score 9/10Last updated: Aug 9, 2026

What it does

  • Turns a natural-language description into a publication-style diagram using the Nano Banana 2 image model.
  • Scores each image with Gemini 3.6 Flash and regenerates (up to 2 iterations) only if it falls below the threshold for your document type: journal 8.5, conference/thesis 8.0, preprint/report 7.5, poster 7.0, presentation 6.5.
  • Saves versioned PNGs (name_v1.png, name_v2.png), a copy at your requested path, and name_review_log.json with score, critique, and stop reason.
  • Applies publication conventions by default: white background, Okabe-Ito colorblind-safe palette, sans-serif labels, generous spacing.
  • States its limits honestly: raster PNG only (no PDF/SVG/EPS), no DPI control, RGB only, and misspelled labels must be caught by eye.

Who it's for

  • Researchers who need a methodology flowchart or architecture figure for a paper, thesis, or grant fast.
  • Grad students burning hours in TikZ, Illustrator, or draw.io.
  • Anyone building conference posters or talk slides.
  • Less suitable if your journal strictly requires vector art or 300 dpi TIFF without post-processing.

Examples

  1. CONSORT trial flow: python scripts/generate_schematic.py "CONSORT participant flow diagram with 500 screened, 150 excluded, 350 randomized" -o figures/consort.png --doc-type journal.
  2. Model architecture: describe "Transformer encoder-decoder with multi-head attention and cross-attention connections" and use --doc-type presentation for a faster, lower-threshold run.
  3. Signaling pathway: "EGFR → RAS → RAF → MEK → ERK with phosphorylation steps labelled" at --doc-type poster, then read the critique field in the review log before deciding to re-run.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/scientific-schematics/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/scientific-schematics folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/scientific-schematics/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/scientific-schematics ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  2. Copy the skill into Claude Code's skills folder: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/scientific-schematics ~/.claude/skills/
  3. Install the Python dependency: pip install requests (or uv pip install requests).
  4. Get an API key at https://openrouter.ai/keys — both the image generation and the review calls are billed.
  5. Export the key: export OPENROUTER_API_KEY='sk-or-v1-...', and add the line to ~/.zshrc or ~/.bashrc to make it permanent.
  6. Restart Claude Code and ask for a diagram, or run the script directly: python ~/.claude/skills/scientific-schematics/scripts/generate_schematic.py "your description" -o figures/out.png --doc-type journal.
  7. Afterwards, check figures/out_review_log.json for the score and critique, and proofread every label in the image yourself — nothing in the pipeline catches typos.
View source on GitHub ↗License: MIT