graphical-abstract-wizard

Generate graphical abstract layout recommendations based on paper abstracts

2.28x

Quality

45%

Does it follow best practices?

Impact

96%

2.28x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/Academic Writing/graphical-abstract-wizard/SKILL.md

Quality

Discovery

32%

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 identifies a specific academic niche (graphical abstracts) but is too brief to be effective for skill selection. It lacks explicit trigger guidance, detailed capability descriptions, and sufficient keyword coverage for natural user queries.

Suggestions

Add a 'Use when...' clause with trigger terms like 'graphical abstract', 'visual abstract', 'TOC graphic', 'journal figure', or 'paper visualization'

Expand the capabilities to specify concrete outputs such as 'suggests panel layouts, icon placement, color schemes, and visual hierarchy for scientific figures'

Include file type or context triggers like 'when preparing manuscript submissions' or 'when working with academic papers'

Dimension	Reasoning	Score
Specificity	Names the domain (graphical abstracts) and one action (generate layout recommendations), but lacks detail on what specific recommendations entail or what outputs are produced.	2 / 3
Completeness	Describes what it does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Includes 'graphical abstract' and 'paper abstracts' which are relevant terms, but misses common variations like 'visual abstract', 'figure summary', 'journal graphic', or 'TOC graphic'.	2 / 3
Distinctiveness Conflict Risk	The term 'graphical abstract' is fairly specific to academic publishing, but 'layout recommendations' could overlap with general design or presentation skills without clearer boundaries.	2 / 3
	Total	7 / 12 Passed

Implementation

57%

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

The skill provides good actionable examples with executable CLI commands and clear output format documentation. However, it suffers from significant bloat with boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status) that don't help Claude execute the task. The content would benefit from aggressive trimming and better organization.

Suggestions

Remove or relocate boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) to a separate METADATA.md file - these don't help Claude use the skill

Add validation guidance for output quality - how should Claude verify the generated prompts are appropriate for the abstract?

Consider splitting the detailed output format example into a separate EXAMPLES.md file, keeping only a brief example in the main skill

Remove the License and Dependencies sections - Claude doesn't need this information to execute the skill

Dimension	Reasoning	Score
Conciseness	The skill contains significant padding including boilerplate sections (License, Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) that don't add actionable value. The core functionality is reasonably explained but buried in unnecessary metadata.	2 / 3
Actionability	Provides fully executable CLI commands with clear parameter documentation, concrete examples with actual abstract text, and detailed output format examples including the exact markdown/ASCII layout structure.	3 / 3
Workflow Clarity	The usage is clear for a single-step tool invocation, but the 'Technical Details' section mentions a 4-step NLP process without explaining how to verify or troubleshoot each step. No validation checkpoints for the output quality.	2 / 3
Progressive Disclosure	Monolithic document with all content inline. Sections like Risk Assessment, Security Checklist, Evaluation Criteria, and Lifecycle Status could be in separate files or removed entirely. No references to external documentation for advanced usage.	1 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: aipoch/medical-research-skills
Commit: 4a48721

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.