SkillAgentSearch skills...

scientific-schematics

Automates publication-quality scientific diagrams (e.g., flowcharts, architectures, pathways) when you need journal/poster-ready visuals from a natural-language description.

Install / Use

npx skills add aipoch/medical-research-skills --skill scientific-schematics

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

89/100

Category

Automation

Supported Platforms

Universal

Our assessment of scientific-schematics

scientific-schematics scores 89/100 on our quality scale, 1368th of 2,790 Automation skills we index (top 50%).

Its SKILL.md is 3.9 KB long, well organised into 12 sections with 5 code examples: a solid amount of guidance for an agent.

With 1,916 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
20/20
Description
15/15
Adoption
14/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so scientific-schematics is actively maintained.
  • Our last check on 2026-10-31 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-30. Automated pattern scan on 2026-09-30. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

scientific-schematics compared with similar skills

All 4 of these similar skills score higher than scientific-schematics; compare them before choosing.

SkillScoreStarsUpdatedFormat
scientific-schematics (this skill)by aipoch891.9k2mo agoSKILL.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
Claude-Code-Game-Studiosby Donchitos10039.7k7d agoCLAUDE.md
Scraplingby D4Vinci100103.6k2d agoMCP Server

Frequently asked questions

How do I install scientific-schematics?
Run npx skills add aipoch/medical-research-skills --skill scientific-schematics. The install tabs above show the steps for each supported agent.
Which AI agents does scientific-schematics work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is scientific-schematics safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is scientific-schematics still maintained?
The repository was last updated about 2 months ago, so scientific-schematics is actively maintained.

name: scientific-schematics description: Automates publication-quality scientific diagrams (e.g., flowcharts, architectures, pathways) when you need journal/poster-ready visuals from a natural-language description. license: MIT author: AIPOCH

Source: https://github.com/aipoch/medical-research-skills

Scientific Schematics Skill

When to Use

  • Creating journal-ready figures (clean typography, consistent styling, high resolution) from a short textual description.
  • Producing poster-friendly diagrams that prioritize readability at distance (larger labels, stronger contrast).
  • Drafting neural network architecture schematics (e.g., Transformer blocks, attention modules) for papers or slides.
  • Generating biological pathway visuals (e.g., Krebs cycle) with iterative quality review.
  • Rapidly iterating on a diagram concept when you need AI-assisted refinement loops instead of manual redraws.

Key Features

  • Text-to-diagram automation: Converts a natural-language prompt into a publication-quality schematic.
  • Iterative generate → review → refine loop: Automatically improves the figure until a quality threshold is met.
  • Document-type aware critique: Reviewer feedback adapts to journal vs poster requirements.
  • Model-configurable pipeline: Choose separate LLMs for generation and vision-based review.
  • Output validation: Performs final checks (e.g., resolution/accessibility considerations) before saving to figures/.
  • Reference guidance:
    • Best practices: references/best_practices.md
    • Supported diagram categories: references/diagram_types.md

Dependencies

  • Python 3.10+ (recommended)
  • Python packages:
    • pillow (PIL)
    • matplotlib
    • requests
  • Environment:
    • OPENROUTER_API_KEY (required)

Example Usage

1) Set the OpenRouter API key

Windows (PowerShell)

$env:OPENROUTER_API_KEY="your_key_here"

Linux/macOS

export OPENROUTER_API_KEY="your_key_here"

2) Run the generator (journal/poster)

python scripts/generate_schematic.py "Transformer architecture with attention mechanism" --doc-type journal

3) Override the generation model

python scripts/generate_schematic.py "Krebs cycle" --doc-type journal --generator anthropic/claude-3.5-sonnet

4) (Optional) Override both generator and reviewer

python scripts/generate_schematic.py "Flowchart of a clinical trial enrollment pipeline" \
  --doc-type poster \
  --generator google/gemini-2.0-flash-001 \
  --reviewer google/gemini-2.0-flash-001

Implementation Details

Pipeline Stages

  1. Generation

    • A code-capable LLM converts the prompt into a diagram image.
    • Default generator model: google/gemini-2.0-flash-001.
  2. Review

    • A vision-capable LLM evaluates the generated image against the target --doc-type.
    • Default reviewer model: google/gemini-2.0-flash-001.
    • The reviewer returns actionable critique and a numeric quality score.
  3. Refinement Loop

    • If the score is below the acceptance threshold (e.g., 8.5/10), the system re-enters generation using the reviewer’s feedback as constraints.
    • This repeats until the threshold is met or the run terminates by internal stopping conditions.
  4. Finalization

    • Performs final checks such as resolution suitability and accessibility-oriented considerations (e.g., legibility).
    • Saves the final artifact to the figures/ directory.

Key Parameters

  • --doc-type <journal|poster>: Controls review criteria (e.g., density/precision for journals vs readability/scale for posters).
  • --generator <model_id>: Model used to produce the diagram.
  • --reviewer <model_id>: Model used to critique the diagram.
  • Quality threshold: A numeric cutoff (example: 8.5/10) that determines whether refinement continues.

Related Skills

View on GitHub
GitHub Stars1.9k
CategoryAutomation
Updated2mo ago
Forks175

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions