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.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

62%

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

The body is highly actionable with a clear, well-validated iterative workflow, but it is far too verbose with repeated sections and underuses its bundle files, leaving most content inline and two reference files orphaned.

Suggestions

Collapse the repeated usage sections ('How to Use', 'Command-Line Usage', 'Getting Started') into a single Quick Start and move the large checklist and troubleshooting blocks into reference files to cut the body dramatically.

Actually link references/QUICK_REFERENCE.md and references/README.md from the body so all bundle files are signaled, and move the best-practices summary content into references/best_practices.md rather than restating it inline.

Remove concept explanations and the redundant 'Smart Iteration Benefits'/'What happens behind the scenes' restatements that repeat the workflow already shown in the diagram.

Dimension	Reasoning	Score
Conciseness	The ~610-line body is padded with heavy repetition — the basic `python scripts/generate_schematic.py ... -o output.png` command is restated roughly six times across 'Quick Start', 'How to Use', 'Command-Line Usage', and 'Getting Started', plus an enormous redundant checklist section — matching the verbose/padded anchor; not a 2 because the repetition is pervasive rather than occasional.	1 / 3
Actionability	Provides copy-paste-ready bash commands with real flags (--doc-type, --iterations, -v) and a complete Python API example with the ScientificSchematicGenerator class, fully executable rather than pseudocode.	3 / 3
Workflow Clarity	The smart-iteration workflow is clearly sequenced with an explicit validation checkpoint (Gemini quality review against a per-document-type threshold) and a feedback loop (score below threshold → improve prompt → regenerate → re-review); not a 2 because validation checkpoints are explicit, not implicit.	3 / 3
Progressive Disclosure	The body is a monolithic wall of text with large inline sections (checklists, troubleshooting, best-practices summary) that belong in separate files, and only 1 of the 3 reference files (best_practices.md) is actually linked while QUICK_REFERENCE.md and README.md are orphaned; not a 3 because references are not comprehensively signaled and content is not appropriately split.	2 / 3
	Total	9 / 12 Passed

Description

82%

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, niche-scoped, and uses natural trigger terms, but it omits an explicit 'Use when...' clause, which caps completeness at 2.

Suggestions

Add an explicit trigger clause such as 'Use when creating neural network architecture diagrams, methodology flowcharts (CONSORT/PRISMA), biological pathways, circuit diagrams, or other scientific visualizations for publication.'

Keep the concrete action list but ensure the 'when' guidance is stated as explicitly as the 'what'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and behaviors — 'Create publication-quality scientific diagrams', 'quality review' via Gemini, and 'Only regenerates if quality is below threshold' — plus a specialization list, matching the 'lists multiple specific concrete actions' anchor; not a 2 because actions are concrete rather than just naming a domain.	3 / 3
Completeness	Clearly states what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2; not a 1 because the 'what' is explicit and domains are named.	2 / 3
Trigger Term Quality	Covers natural terms a user would say — 'neural network architectures', 'system diagrams', 'flowcharts', 'biological pathways', 'complex scientific visualizations' — giving good coverage rather than only some relevant keywords.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (publication-quality scientific diagrams with AI generation + review) with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (619 lines); consider splitting into references/ and linking	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: K-Dense-AI/claude-scientific-writer
Path: .claude/skills/scientific-schematics/SKILL.md
Commit: 4717803

Reviewed: about 10 hours 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.