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

57%

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 ./skills/scientific-schematics/SKILL.md

Quality

Content

47%

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

The body has a clear, well-validated AI-generation workflow with real executable examples, but it is heavily verbose with repeated sections and references non-existent helper functions in its troubleshooting guidance. Progressive disclosure is weak, with two reference files left unlinked.

Suggestions

Collapse the redundant Quick Start / How to Use / Command-Line Usage / Getting Started sections into a single concise getting-started block; remove concept restatements Claude already knows.

Remove or replace troubleshooting references to non-existent functions (detect_overlaps, verify_accessibility, validate_resolution, run_quality_checks) with the actual quality-review mechanism from generate_schematic_ai.py, or delete the orphaned manual-drawing checklist sections.

Link all bundled reference files (README.md, QUICK_REFERENCE.md, best_practices.md) and move the detailed prompt-engineering examples and best-practices tables into them so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The ~600-line body is padded with redundancy (Quick Start, How to Use, Command-Line Usage, and Getting Started all repeat the same one-line command) and restates concepts Claude already knows, matching the verbose anchor.	1 / 3
Actionability	Provides genuinely executable CLI commands and a Python API example that matches the bundled script, but troubleshooting references functions (detect_overlaps, verify_accessibility, validate_resolution, run_quality_checks) that do not exist in the provided scripts, mixing real guidance with fabricated APIs.	2 / 3
Workflow Clarity	The smart iterative refinement workflow is clearly sequenced (generate -> review -> score-vs-threshold decision -> improve/regenerate) with explicit validation checkpoints and a documented review log including early-stop reasoning.	3 / 3
Progressive Disclosure	Only best_practices.md is referenced despite three reference files existing (README.md and QUICK_REFERENCE.md are never linked), and most material is inlined into a long monolithic body that could be split out.	2 / 3
	Total	8 / 12 Passed

Description

67%

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 distinctive about its scientific-diagram niche, but lacks an explicit "Use when..." trigger clause, leaving the when-to-use guidance implied rather than stated. Trigger term coverage is decent but incomplete.

Suggestions

Add an explicit trigger clause, e.g. "Use when creating scientific diagrams, neural network architecture figures, biological pathway maps, CONSORT/PRISMA flowcharts, or publication-ready schematics."

Broaden trigger terms to include generic natural phrasings like "diagram", "schematic", "figure", and "flowchart" that a user is likely to say.

Trim the implementation detail ("Uses Gemini 3.6 Flash for quality review") which is mechanism rather than capability, to keep the description tight.

Dimension	Reasoning	Score
Specificity	Lists concrete actions ("Create publication-quality scientific diagrams", "quality review", "smart iterative refinement") and enumerates specific domain targets (neural network architectures, system diagrams, flowcharts, biological pathways), matching the multiple-concrete-actions anchor.	3 / 3
Completeness	Clearly answers what the skill does, but the when-to-use guidance is only implied through the domain list rather than an explicit trigger clause; per guidelines a missing "Use when..." caps completeness at 2.	2 / 3
Trigger Term Quality	Includes some natural terms users would say ("neural network architectures", "flowcharts", "biological pathways") but misses common variations like the generic "diagram"/"schematic" trigger phrasing and lacks an explicit "Use when..." clause.	2 / 3
Distinctiveness Conflict Risk	The AI-powered scientific-diagram niche with document-type quality thresholds is clearly distinguishable from other skills and unlikely to trigger for the wrong skill; voice is appropriately third person.	3 / 3
	Total	10 / 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/scientific-agent-skills
Path: skills/scientific-schematics/SKILL.md
Commit: 757b63b

Reviewed: 2 days 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.