visual-content-desc

Generates detailed text descriptions of medical images and charts for.

Quality

56%

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

62%

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

The body contains genuine skill-specific content (parameters, output schema, an executable script) and a clear validated workflow, but it is bloated with generic process boilerplate, contains broken circular section references, and its script does not actually accept the documented inputs. Structure and conciseness are the main weaknesses.

Suggestions

Remove generic boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template) that is not specific to this skill, or move it to a reference file.

Make scripts/main.py accept the documented input parameters (image_type, key_features) via argparse so the listed `--help` and run commands match the Input Parameters table.

Replace the circular "See ##Features/Prerequisites/Workflow above" pointers and link the actual bundle file by name, e.g. "See [guidelines.md](references/guidelines.md) for accessibility standards."

Dimension	Reasoning	Score
Conciseness	The body has a usable core (Input Parameters, Output Format, the script) but is padded with generic boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template) and repeats the broken description verbatim; much of it could be cut. It is not pure concept-explanation fluff, so it stays above 1.	2 / 3
Actionability	It provides a real executable script, concrete commands, and a concrete output JSON schema, but the script hardcodes demo values and does not accept the documented input parameters via CLI, and the suggested `--help` invocation would fail, leaving key details missing.	2 / 3
Workflow Clarity	For this simple single-action skill the action is unambiguous (documented Input Parameters, Output Format, and script), and there are explicit validation checkpoints (the py_compile Quick Check, a scope stop-early step, and a fallback path on failure), satisfying the simple-skills allowance for a 3.	3 / 3
Progressive Disclosure	Bundle files exist (references/guidelines.md, scripts/main.py) and scripts/main.py is referenced by path, but references/ is only signaled generically rather than by file name, the SKILL.md is monolithic with inline boilerplate, and several "See ##X above" pointers are circular/placeholder rather than clear one-level-deep navigation.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 concrete domain and action but is grammatically incomplete (trailing "for."), repeats a single action, and entirely lacks a "Use when..." trigger clause. It is adequate but generic, capping most dimensions at 2.

Suggestions

Add an explicit trigger clause, e.g. "Use when describing medical images, charts, scans, or figures for accessibility, alt text, or figure legends."

List multiple distinct actions (e.g. generate descriptions, produce alt text, draft figure legends) instead of restating "Generates detailed text descriptions" once.

Fix the truncated sentence (remove the dangling "for.") so the description is grammatically complete.

Dimension	Reasoning	Score
Specificity	It names the domain ("medical images and charts") and one action ("Generates detailed text descriptions"), but does not list multiple distinct concrete actions like the score-3 anchor; it is essentially a single action restated, and the sentence is truncated with a dangling "for."	2 / 3
Completeness	It states what the skill does but provides no explicit "when" trigger guidance; per the rubric a missing "Use when..." clause caps completeness at 2.	2 / 3
Trigger Term Quality	It contains relevant natural terms ("medical images", "charts") a user might say, but offers no "Use when..." trigger clause and misses common variations such as alt text, figure legends, or accessibility, matching the some-keywords-but-incomplete anchor.	2 / 3
Distinctiveness Conflict Risk	The medical-imagery niche is fairly specific, but without explicit triggers and with only a single generic action it could still overlap with general image-description skills, fitting the somewhat-specific-but-overlapping anchor rather than a clear distinct niche.	2 / 3
	Total	8 / 12 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: f5ef65b

Reviewed: 2 days 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.