visual-content-desc

Generates detailed text descriptions of medical images and charts for.

Quality

48%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/visual-content-desc/SKILL.md

Quality

Content

42%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.

The body is a heavily templated, boilerplate-heavy SKILL.md with broken 'see above' cross-references pointing to sections that actually appear below. It contains a few genuinely useful concrete elements (commands, params table, output schema) but adds almost no domain guidance for its stated medical-visual-description purpose.

Suggestions

Fix or remove the broken 'See `## Features`/`## Prerequisites`/`## Workflow` above' cross-references — those sections appear below, not above, signaling unedited templating.

Cut generic boilerplate (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template) that adds no skill-specific value, or move it into a reference file.

Add real domain guidance for describing medical images/charts (what to capture, accessibility/alt-text standards, figure-legends) and a worked input→output example, since the current main.py is only a stub with hardcoded demo input.

Dimension	Reasoning	Score
Conciseness	The body is noticeably padded with boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template, Output Requirements) that restate generic process framing Claude already knows, plus broken 'See ## X above' cross-references; it is not a 1 because some sections (params table, output schema, commands) do earn their place.	2 / 5
Actionability	Provides concrete executable commands ('python -m py_compile scripts/main.py', 'python scripts/main.py --help'), a real input-parameters table, and an output JSON schema, but offers no worked input→output example and gives zero domain guidance on how to write good medical-image descriptions — the skill's core purpose.	3 / 5
Workflow Clarity	A 5-step Workflow sequence with a documented fallback path exists, but validation checkpoints are abstract and implicit ('Validate that the request matches the documented scope') rather than concrete validate-then-proceed loops tied to the script.	3 / 5
Progressive Disclosure	Section structure is present and the referenced bundles (references/guidelines.md, scripts/main.py) are real files, but references are not signaled or linked by name (only a generic 'Reference material available in references/'), guidelines.md is a near-empty stub, and templated boilerplate that belongs elsewhere is inlined.	3 / 5
	Total	11 / 20 Passed

Description

53%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.

The description conveys a recognizable niche and one concrete action but is marred by a truncated, grammatically broken sentence ('...for.') and the complete absence of a 'when to use' trigger clause. It is serviceable but clearly unfinished templating output.

Suggestions

Complete the truncated description and add an explicit 'Use when...' clause naming concrete triggers (e.g., 'Use when describing medical images, charts, scans, or figures for accessibility/alt text').

Add natural synonyms users would say — 'alt text', 'figure legends', 'accessibility descriptions', file/type terms like 'microscopy', 'scan' — to improve trigger-term coverage.

List 2-3 concrete actions (e.g., generate image descriptions, write alt text, draft figure legends) to lift specificity from one generic action to several.

Dimension	Reasoning	Score
Specificity	Names the domain ('medical images and charts') and one concrete action ('Generates detailed text descriptions'), matching the anchor that names a domain with 1-2 concrete actions; it is not a 4 because only a single generic action is described rather than several specific ones.	3 / 5
Completeness	Provides a clear 'what' but no 'when' or 'Use when...' trigger clause, so completeness is capped at 3 per the judging guidelines; the trailing 'for.' also signals the sentence is truncated and incomplete.	3 / 5
Trigger Term Quality	Includes relevant keywords ('medical images', 'charts', 'descriptions') but misses common natural variations and synonyms users would say, such as 'alt text', 'figures', 'accessibility', 'microscopy', or 'scans'.	3 / 5
Distinctiveness Conflict Risk	The medical-images-and-charts niche is mostly distinct with only minor overlap risk against other description/figure skills; it is not a 5 because the wording is generic and the truncated description weakens the trigger signal.	4 / 5
	Total	13 / 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/Academic Writing/visual-content-desc/SKILL.md
Commit: 63c61d3

Reviewed: 4 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.