scientific-schematics

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.6 Flash 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.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/scientific-schematics/SKILL.md

Quality

Content

56%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is actionable with a clear reviewed refine workflow and real one-level references, but it is padded with redundant quick-start sections and inlined reference-grade material. Consolidating repeated sections and moving troubleshooting/checklists into references would improve both conciseness and progressive disclosure.

Suggestions

Collapse the four near-duplicate quick-start sections ('Quick Start', 'How to Use', 'Command-Line Usage', 'Getting Started') into a single concise entry-point block.

Move the large 'Troubleshooting Common Issues' and 'Quick Reference Checklist' sections into a reference file and link to them from SKILL.md to improve progressive disclosure.

Delete marketing filler ('That's it!', 'No coding, no templates, no manual drawing required' repeats, 'Smart Iteration Benefits' lists) that restates already-stated guidance.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: the same one-liner invocation is repeated across 'Quick Start', 'How to Use', 'Command-Line Usage', and 'Getting Started', plus marketing padding ('That's it!', 'No coding, no templates') and checklists that restate guidelines already given.	2 / 5
Actionability	Provides concrete, copy-paste-ready bash commands with realistic example prompts and document-type flags covering the common cases, with only minor gaps.	4 / 5
Workflow Clarity	The generate-review-refine loop is clearly sequenced (steps 1-5) with an explicit decision checkpoint ('If quality >= threshold -> DONE') and a repeat-until condition, plus per-iteration review as validation.	4 / 5
Progressive Disclosure	Body signals one-level-deep references to real files (iterative_refinement.md, best_practices.md), but large troubleshooting/checklist/best-practices content is inlined that belongs in references, and existing bundle files (QUICK_REFERENCE.md, README.md) are not navigated.	3 / 5
	Total	13 / 20 Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinct with good trigger terms, but lacks an explicit 'Use when...' trigger clause, capping completeness. Adding concrete when-to-use phrasing would lift it to the top band.

Suggestions

Add an explicit 'Use when...' clause naming the trigger situations (e.g., 'Use when creating publication-quality scientific diagrams, neural network architectures, flowcharts, or biological pathways for papers, posters, or presentations').

Trim the implementation-mechanism detail ('Uses Gemini 3.6 Flash for quality review', 'Only regenerates if quality is below threshold') to tighten the description toward what/when.

Include common synonyms or file outputs users might say (e.g., 'figures', 'schematics', '.png/.svg diagrams') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Create publication-quality scientific diagrams', 'Uses Gemini 3.6 Flash for quality review', 'Only regenerates if quality is below threshold') plus specialized diagram types, with minor mechanism-padding gaps.	4 / 5
Completeness	Has a clear 'what' but no explicit 'when'/'Use when...' clause, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('scientific diagrams', 'neural network architectures', 'flowcharts', 'biological pathways', 'system diagrams') but is missing common synonyms and file extensions.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (publication-quality scientific schematics with named specializations like neural network architectures and biological pathways) with minimal overlap risk against other skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/claude-scientific-writer
Path: .claude/skills/scientific-schematics/SKILL.md
Commit: 14ee3e3

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.