CtrlK
BlogDocsLog inGet started
Tessl Logo

medgemma-radiology

Analyzes medical images (X-ray, CT, MRI, DICOM) using MedGemma. Use when the user provides medical images or DICOM files for analysis, asks about radiological findings, or wants image comparison across time series. DICOM files are automatically converted with appropriate windowing.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A well-structured, actionable skill body with executable pipeline commands and clear plain-language reporting guidance. It is mostly concise with good navigation, though minor redundancy and the absence of an explicit batch-retry feedback loop keep it just below top marks.

Suggestions

Remove redundancy between the 'Rules' section and the report-format sections (e.g. plain-language and normal-findings guidance appear in both) to tighten conciseness.

Add an explicit validation/retry feedback loop for batch and multi-series runs (e.g. verify all expected series were processed and re-run on any that failed before writing the comparison report).

Consider moving the detailed DICOM windowing/slice-selection specifics into a separate reference file to keep SKILL.md as a tighter overview.

DimensionReasoningScore

Conciseness

Largely lean and assumes Claude's competence without explaining basic concepts, but the 'Rules' section partly restates guidance already embedded in the report-format sections, a minor instance of over-explanation that could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready executable commands (`uv run python scripts/medgemma_api.py ...`) covering single image, DICOM, multiple, and ZIP cases, plus concrete report section headers, file-naming patterns, and a defined confidence-emoji system.

5 / 5

Workflow Clarity

Clear sequence (read user_config → patient_info intake → run script → read saved JSON → write report → append disclaimer) with checkpoints for missing patient info and for reading full JSON over truncated stdout, but lacks an explicit validate→fix→retry feedback loop for batch/multi-series runs.

4 / 5

Progressive Disclosure

Well-organized into clear sections with well-signaled, one-level-deep references to scripts and reports paths; most content is appropriately placed, though some detailed DICOM handling is inlined rather than split into a separate reference.

4 / 5

Total

17

/

20

Passed

Description

87%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.

A strong, specific description that clearly states capabilities and provides explicit, natural trigger phrases covering multiple modalities. It is concise yet comprehensive, with only minor keyword-coverage gaps.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Analyzes medical images (X-ray, CT, MRI, DICOM)', 'image comparison across time series', 'DICOM files are automatically converted with appropriate windowing' — with minor coverage gaps (no mention of report generation or multi-series handling).

4 / 5

Completeness

Explicitly answers both what ('Analyzes medical images... using MedGemma', 'DICOM files are automatically converted with appropriate windowing') and when ('Use when the user provides medical images or DICOM files for analysis, asks about radiological findings, or wants image comparison across time series') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good keyword coverage including modality names ('X-ray, CT, MRI, DICOM') and natural phrases ('radiological findings', 'image comparison across time series'), but a few natural terms/extensions are absent (e.g. '.dcm', 'scan').

4 / 5

Distinctiveness Conflict Risk

Clear niche (MedGemma-based medical/radiology image analysis) with distinct modality-specific triggers and minimal overlap risk with unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 6 missing

Warning

Total

15

/

16

Passed

Repository
burakcanpolat/med-guide
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.