scientific-schematics

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

Quality

81%

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

Quality

Content

92%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.

A well-organized, actionable skill body that leads with executable commands, clearly explains the internal generate-review-refine pipeline with validation, and correctly delegates detail to real one-level-deep reference files. Only minor conciseness trimming is warranted.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence (no basic concept explanations), with well-structured sections; minor feature-bullet wording ('Document-type aware critique', 'Model-configurable pipeline') slightly restates the implementation details and could be trimmed.	4 / 5
Actionability	It provides fully executable, copy-paste ready commands covering environment setup and four usage variants (basic, generator override, both-override), plus documented key parameters that cover the common cases.	5 / 5
Workflow Clarity	The pipeline is clearly sequenced (Generation → Review → Refinement Loop → Finalization) with an explicit feedback loop gated by a numeric quality threshold (8.5/10) and final validation checks during finalization.	5 / 5
Progressive Disclosure	The body is a clear overview with well-signaled one-level-deep references to real bundle files (references/best_practices.md, references/diagram_types.md, scripts/generate_schematic.py), with content appropriately split and easy to navigate.	5 / 5
	Total	19 / 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.

A clear, domain-specific description that states both capability and trigger condition with concrete examples. It loses points for relying on a single concrete action and a relatively narrow trigger clause rather than comprehensive trigger coverage.

Suggestions

Broaden the 'when' clause into an explicit 'Use when...' listing multiple natural trigger phrases (e.g., scientific figures, schematics, publication visuals, journal figures, poster diagrams).

Switch to third-person voice ('Use when the user needs...') instead of second person ('when you need') to align with the description voice guideline.

Name additional concrete actions beyond 'automates' (e.g., generate, refine, validate) to lift specificity from a single action to comprehensive coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('publication-quality scientific diagrams') and one concrete action ('Automates ... from a natural-language description'), but the listed examples (flowcharts, architectures, pathways) are diagram types rather than distinct actions, so coverage is not comprehensive.	3 / 5
Completeness	It answers both 'what' (automates publication-quality scientific diagrams from NL) and 'when' ('when you need journal/poster-ready visuals'), but the 'when' is a single trigger path that could be more explicit and broader.	4 / 5
Trigger Term Quality	It includes natural terms a user would say ('flowcharts, architectures, pathways', 'journal/poster-ready visuals', 'natural-language description'), but omits common synonyms such as 'figure' or 'schematic' in the trigger clause.	4 / 5
Distinctiveness Conflict Risk	The niche (publication-ready scientific schematics for journals/posters) is distinct with clear triggers, with only minor overlap risk against general diagramming skills.	4 / 5
	Total	15 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/scientific-schematics/SKILL.md
Commit: 63c61d3

Reviewed: 5 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.