visual-content-desc
Generates detailed text descriptions of medical images and charts for.
25
16%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/visual-content-desc/SKILL.mdQuality
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 is truncated ('for.' ends abruptly), which severely undermines its completeness and usefulness. While it identifies a reasonably specific domain (medical image descriptions), it lacks a 'Use when...' clause, comprehensive trigger terms, and appears to be missing critical information after the trailing 'for.'
Suggestions
Complete the truncated sentence and add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to describe, interpret, or generate alt text for medical images, X-rays, MRIs, CT scans, or clinical charts.'
Add natural trigger terms users would say, such as 'radiology', 'X-ray', 'MRI', 'CT scan', 'pathology', 'alt text', 'image accessibility', 'clinical diagram'.
List additional specific actions beyond 'generates descriptions', such as 'identifies anatomical structures, summarizes chart data, provides accessibility-compliant alt text for medical visuals'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (medical images and charts) and a specific action (generates detailed text descriptions), but the description appears truncated ('for.' ends abruptly) and doesn't list multiple concrete actions. | 2 / 3 |
Completeness | The description attempts to answer 'what' (generates text descriptions of medical images) but is truncated and incomplete, and there is no 'Use when...' clause or equivalent trigger guidance. The truncation ('for.') suggests critical information is missing. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'medical images', 'charts', and 'text descriptions', but misses common variations users might say such as 'radiology', 'X-ray', 'scan', 'alt text', 'accessibility', or 'image description'. | 2 / 3 |
Distinctiveness Conflict Risk | The 'medical images' domain provides some specificity, but 'charts' is generic and could overlap with data visualization or charting skills. The truncated description makes it harder to distinguish from general image description skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is almost entirely generic boilerplate with no substantive, domain-specific content about generating medical image descriptions. It lacks concrete examples, executable code for the actual task, and meaningful workflow steps. The excessive template sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria) consume tokens without adding actionable guidance, and self-referential section pointers create confusion rather than clarity.
Suggestions
Replace the generic boilerplate with concrete examples showing actual medical image descriptions—e.g., provide a sample microscopy image description with the expected alt_text, description, and figure_text output.
Add executable code or clear step-by-step instructions for how to actually generate descriptions for each image_type (microscopy, chart, scan), including domain-specific guidance on what features to highlight.
Remove or drastically compress the Risk Assessment, Security Checklist, Lifecycle Status, and Evaluation Criteria sections—these are generic filler that don't help Claude perform the task.
Eliminate circular self-references ('See ## Features above') and consolidate the content into a lean structure: purpose, input parameters, concrete examples with expected output, and error handling.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and padded with boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria) that add no actionable value. Multiple self-referential loops ('See ## Features above', 'See ## Prerequisites above') waste tokens. The core task—generating image descriptions—could be conveyed in a fraction of the space. Much content is generic template filler not specific to this skill. | 1 / 3 |
Actionability | No concrete, executable code for the actual task of generating medical image descriptions. The 'Example Usage' only shows how to compile and run a script whose contents are unknown. The workflow steps are entirely abstract ('Confirm the user objective', 'Validate that the request matches'). There are no examples of actual input images being described or output being generated. | 1 / 3 |
Workflow Clarity | The workflow section is generic boilerplate with no specifics about how to actually describe medical images. Steps like 'Confirm the user objective' and 'Use the packaged script path' are vague. There are no validation checkpoints specific to the domain (e.g., verifying medical accuracy, checking alt text completeness). No feedback loops for error recovery in the actual description generation process. | 1 / 3 |
Progressive Disclosure | References to 'references/' directory and 'scripts/main.py' exist but no bundle files are provided, making these dead references. Multiple sections reference other sections within the same document ('See ## Features above') creating circular, confusing navigation. The document is a monolithic wall of boilerplate with no meaningful content hierarchy. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
90%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
73f6514
- Reviewed
Table of Contents
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.