CtrlK
BlogDocsLog inGet started
Tessl Logo

scientific-schematics

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.

68

2.87x
Quality

55%

Does it follow best practices?

Impact

95%

2.87x

Average score across 3 eval scenarios

SecuritybySnyk

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/scientific-schematics/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

85%

75%

Journal Submission: Generate CONSORT Flow Diagram

Doc-type quality thresholds and review log

Criteria
Without context
With context

Uses generate_schematic.py

0%

100%

Correct doc-type flag

0%

100%

Correct journal threshold

0%

100%

Output to figures/ subfolder

0%

100%

API key via env var

0%

100%

Smart iteration explained

66%

100%

Max iterations constraint

0%

100%

Review log mentioned

0%

0%

100%

10%

Generate Figures for an Academic Poster Presentation

Specific prompts and figures/ output organization

Criteria
Without context
With context

Poster doc-type used

0%

100%

Output in figures/ subfolder

100%

100%

Specific transformer prompt

100%

100%

Specific pathway prompt

100%

100%

Specific IoT prompt

100%

100%

Colorblind palette referenced

100%

100%

Prompt rationale explains specificity

100%

100%

figures/ location justified

100%

100%

No figure numbers in prompts

100%

100%

100%

100%

Automate Figure Generation Pipeline for a Grant Proposal

Python API and iterative refinement

Criteria
Without context
With context

Uses ScientificSchematicGenerator

0%

100%

Uses generate_iterative() method

0%

100%

Grant doc-type or threshold

0%

100%

API key from environment

0%

100%

Max iterations set to 2

0%

100%

Max iterations limit explained

0%

100%

Reads final_score from results

0%

100%

Reads early_stop from results

0%

100%

Reads iterations list from results

0%

100%

Output to figures/ subfolder

0%

100%

Repository
K-Dense-AI/claude-scientific-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.