virtual-patient-roleplay

Simulate standardized patient encounters for medical training, supporting OSCE-style history-taking practice, communication skills rehearsal, and educational debriefing.

Quality

66%

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/Other/virtual-patient-roleplay/SKILL.md

Quality

Content

67%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 well-structured, actionable, and cleanly separates overview from reference files, with executable commands and explicit scope handling. The main weakness is recurring redundancy of the educational boundary across several sections and one unreferenced bundle file.

Suggestions

Consolidate the repeated educational-not-clinical boundary into one section (e.g., Scope Boundaries) and have other sections reference it rather than restating it.

Link or remove references/guidelines.md so every bundle file is either surfaced in the References section or dropped from the bundle.

Add a one-line example of the ask() return dict shape (e.g. keys like patient_response) to make the executable examples fully self-explanatory.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not over-explain concepts Claude already knows (no definition of OSCE, no library tutorials). However, the educational-not-clinical boundary is restated across the Disclaimer, Scope Boundaries, Input Validation, Error Handling, and Output sections, which could be consolidated. It is above 2 (not heavily padded) but below 4 due to this recurring redundancy.	3 / 5
Actionability	Provides copy-paste-ready executable commands in Quick Check and Usage ('python -c "from scripts.main import PatientSimulator; sim=PatientSimulator(\'chest_pain\'); ..."') plus a concrete Parameters table. It is below 5 because the returned dict structure from ask() is not illustrated and only two scenarios are exemplified.	4 / 5
Workflow Clarity	A clear 5-step Workflow sequence is present with validation (the py_compile Quick Check) and an Error Handling section that defines fallback and re-statements of scope. No destructive/batch cap applies since the skill is read-only simulation. It is below 5 because validation is framed as a pre-check rather than an explicit per-step validate→fix→retry loop within the workflow.	4 / 5
Progressive Disclosure	Structure is clear with well-signaled, one-level-deep references to real files ('references/references.md — Educational standards...', 'references/audit-reference.md — Supported scope, audit commands...'). It is below 5 because references/guidelines.md exists in the bundle but is not referenced or linked from the body, a minor organization gap.	4 / 5
	Total	15 / 20 Passed

Description

66%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 specific and uses strong natural trigger terms for its medical-training niche, but it lacks an explicit 'Use when...' trigger clause, which caps completeness at 3 and leaves minor conflict risk. Adding concrete trigger guidance would raise the two capped dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when a learner needs OSCE-style history-taking practice, communication-skills rehearsal, or debrief planning with a simulated patient.'

Add a natural synonym such as 'clinical interview' or 'patient interview practice' to broaden trigger coverage without losing the niche.

Briefly signal the boundary in the description (e.g. 'for educational simulation only, not real clinical triage') to reduce overlap with clinical-decision skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'OSCE-style history-taking practice, communication skills rehearsal, and educational debriefing' — with only minor gaps in coverage (e.g., case setup, scoring). It sits above anchor 3 because it names more than 1-2 actions, but below 5 since coverage is not fully comprehensive.	4 / 5
Completeness	A clear 'what' is present ('Simulate standardized patient encounters for medical training, supporting...'), but there is no explicit 'Use when...' clause or equivalent trigger guidance, so completeness is capped at 3 per the judging guideline. It is above 2 because the 'what' is concrete, not vague.	3 / 5
Trigger Term Quality	Natural domain terms a medical educator would actually say are present ('OSCE-style', 'standardized patient', 'medical training', 'debriefing'). Good keyword coverage but a few natural synonyms (e.g., 'clinical skills', 'patient interview practice') are missing, so it does not reach 5.	4 / 5
Distinctiveness Conflict Risk	The niche is clear and distinct (standardized-patient/OSCE simulation for medical training) with low conflict risk. It does not reach 5 because the absence of an explicit trigger clause leaves minor overlap risk with general roleplay or communication-skills skills.	4 / 5
	Total	15 / 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/Other/virtual-patient-roleplay/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.