figure-legend-gen

Generate standardized figure legends for scientific charts and graphs.

Quality

33%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/Academic Writing/figure-legend-gen/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 clear domain (scientific figure legends) but is too brief to be effective for skill selection. It lacks explicit trigger guidance, comprehensive action details, and sufficient keyword coverage for users who might phrase requests differently.

Suggestions

Add a 'Use when...' clause with trigger terms like 'figure caption', 'chart legend', 'plot description', 'scientific publication', or 'manuscript figures'

Expand specific capabilities such as 'format axis labels, describe statistical annotations, cite data sources, follow journal style guidelines'

Include common file/context triggers like 'when working with matplotlib, R plots, Excel charts, or preparing figures for publication'

Dimension	Reasoning	Score
Specificity	Names the domain (scientific charts/graphs) and a general action (generate figure legends), but doesn't list multiple concrete actions like formatting options, citation styles, or specific legend components.	2 / 3
Completeness	Describes what the skill 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 relevant terms like 'figure legends', 'scientific charts', and 'graphs', but misses common variations users might say such as 'plot captions', 'chart descriptions', 'figure captions', or specific chart types.	2 / 3
Distinctiveness Conflict Risk	The focus on 'scientific' and 'figure legends' provides some distinction, but could overlap with general scientific writing skills or chart creation skills without clearer boundaries.	2 / 3
	Total	7 / 12 Passed

Implementation

35%

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

This skill suffers from severe verbosity and redundancy, with multiple sections repeating similar information and boilerplate content that doesn't serve the specific task of generating figure legends. While it provides some actionable CLI examples and a useful chart types table, the core value proposition (how to actually generate quality legends) is buried under generic workflow templates, security checklists, and self-referential section pointers.

Suggestions

Remove redundant sections: consolidate the scattered workflow guidance into one clear section, eliminate duplicate --help commands, and remove generic boilerplate (Risk Assessment, Security Checklist, Lifecycle Status) that doesn't add skill-specific value.

Add concrete legend generation examples: show actual input images paired with expected legend output text to demonstrate what quality legends look like for each chart type.

Remove circular references ('See ## X above') and reorganize so information flows linearly without requiring readers to jump around the document.

Focus the content on what makes figure legends good - the Legend Structure section is valuable but needs expansion with actual examples rather than just listing components.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with significant redundancy - multiple sections reference each other circularly ('See ## Prerequisites above', 'See ## Usage above'), duplicate command examples (--help appears 4 times), boilerplate sections like Risk Assessment and Security Checklist that don't add skill-specific value, and generic content Claude already knows.	1 / 3
Actionability	Provides concrete CLI commands and parameter tables which are useful, but the actual script implementation details are missing - we don't know what the script actually does internally. The examples are executable but the core functionality (how legends are actually generated) remains abstract.	2 / 3
Workflow Clarity	Multiple workflow sections exist but they're scattered and redundant (Example Usage has a 'run plan', separate Workflow section, Implementation Details). The steps are listed but validation checkpoints are generic ('validate the request') rather than specific to figure legend generation.	2 / 3
Progressive Disclosure	References external files appropriately (references/legend_templates.md, references/academic_style_guide.md), but the main document is bloated with sections that should be condensed or removed. The circular 'See ## X above' references create confusion rather than clear navigation.	2 / 3
	Total	7 / 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 12 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.