medgemma-assistant

Interprets lab results, checks drug interactions, evaluates symptoms, and explains medical reports in plain language. Use when the user provides lab values, asks about medications, describes symptoms, or wants a medical report explained.

Quality

81%

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

Quality

Content

75%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 an efficient, well-structured instruction skill with concrete templates and a coherent implicit workflow; it assumes Claude's competence and avoids concept padding. The main improvement would be a fully worked lab-result example and an explicitly numbered process.

Suggestions

Replace the placeholder lab-result table with one fully worked example showing real values and the resulting plain-language explanation.

Make the workflow explicit with a short numbered sequence (read patient info → configure language → analyze → save → append disclaimer) so the order is unambiguous.

Trim the opening "You are an AI assistant..." line since it restates the frontmatter description.

Dimension	Reasoning	Score
Conciseness	The body is lean — tables, bullets, and templates with no concept-explanation padding — but the intro line ("You are an AI assistant that helps with medical topics...") restates the description, a minor instance of over-explanation.	4 / 5
Actionability	Concrete guidance throughout: a lab-result table template, traffic-light drug-interaction scheme, report-save path with date format, and literal copy-paste disclaimer text; held back from 5 because the lab template uses abstract placeholders ("(value)", "(number)") rather than a fully worked example.	4 / 5
Workflow Clarity	A coherent ordered process is implied across sections (Before Analysis → analysis → Rules → Report Saving → Disclaimer) with an input-handling checkpoint ("If this file is missing... follow the patient intake flow"), though the sequence is not explicitly numbered.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with one-level-deep, clearly signaled references to runtime input files (reports/user_config.md, reports/patient_info.md) and no nested references; minor gap is that no detail is split into separate bundle files, but the single-file structure is appropriate for this size.	4 / 5
	Total	16 / 20 Passed

Description

88%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 is strong: it states four concrete capabilities and pairs them with explicit, natural-language trigger phrases covering both what and when. Minor gaps are limited to a few missing synonyms and slight overlap risk on broad symptom terms.

Suggestions

Add common synonyms to the trigger clause, e.g. "blood work" alongside "lab values" and "prescriptions" alongside "medications".

Tighten the broad "describes symptoms" trigger to a more specific framing to reduce overlap with general health-advice skills.

Dimension	Reasoning	Score
Specificity	Names four concrete actions — "Interprets lab results, checks drug interactions, evaluates symptoms, and explains medical reports" — giving comprehensive coverage of the skill's domain, matching the multiple-specific-actions anchor.	5 / 5
Completeness	Explicitly answers both "what" (the four capabilities) and "when" (concrete trigger phrases in the "Use when..." clause), matching the top anchor.	5 / 5
Trigger Term Quality	"Use when the user provides lab values, asks about medications, describes symptoms, or wants a medical report explained" supplies natural phrases users would say, but lacks common synonyms (e.g., "blood work", "prescriptions", "side effects").	4 / 5
Distinctiveness Conflict Risk	The medical-analysis niche with specific triggers (lab values, medications, medical reports) is mostly distinct, but broad terms like "symptoms" carry minor overlap risk with general health-advice skills.	4 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: burakcanpolat/med-guide
Path: .agents/skills/medgemma-assistant/SKILL.md
Commit: 83a6c1e

Reviewed: 1 day 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.