CtrlK
BlogDocsLog inGet started
Tessl Logo

virtual-patient-roleplay

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

59

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Other/virtual-patient-roleplay/SKILL.md
SKILL.md
Quality
Evals
Security

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 and highly actionable, with executable commands, clear parameters, explicit error handling, and real one-level references. Its weaknesses are redundant boundary restatements across five sections and duplicated smoke-test commands, plus small gaps like unenumerated difficulty values and an orphaned reference file.

Suggestions

Consolidate the repeated clinical-boundary statements (Disclaimer, When to Use, Scope Boundaries, Error Handling, Input Validation) into a single Scope Boundaries section and reference it elsewhere.

Deduplicate the Quick Check and Usage sections, and enumerate valid difficulty values in the parameter table (e.g. novice/intermediate/advanced).

Either reference references/guidelines.md from the body or remove it, since it duplicates content already in references/references.md.

DimensionReasoningScore

Conciseness

Sections are list-based and tight, but the clinical-boundary statement is restated in at least five places ("Educational Disclaimer", "When to Use", "Scope Boundaries", "Error Handling", "Input Validation") and the Quick Check section duplicates the Usage commands verbatim, matching 'Mostly efficient but includes some unnecessary explanation or could be tightened'. Not 2 because each section is individually lean and no basic concepts are over-explained.

3 / 5

Actionability

Concrete, copy-paste python commands ("python -m py_compile scripts/main.py", two PatientSimulator one-liners), a parameter table, an exact out-of-scope response string, and a fixed response template provide mostly executable guidance, matching the 4 anchor. Not 5: valid difficulty values are unenumerated and only two of the three scenarios are exemplified.

4 / 5

Workflow Clarity

The Workflow section gives a clear 5-step sequence with boundary checkpoints, Error Handling supplies feedback loops, and Quick Check supplies a validation command, matching 'Clear sequence with most checkpoints present'. Not 5 because the validation commands are not integrated into the numbered workflow sequence itself (no 'validate then proceed' step).

4 / 5

Progressive Disclosure

References are one level deep, clearly signaled with descriptions, and both referenced files exist (references/references.md, references/audit-reference.md) alongside scripts/main.py, matching 'Good structure; most content is appropriately placed; references mostly clear'. Not 5: references/guidelines.md exists in the bundle but is never referenced, a minor organization gap.

4 / 5

Total

15

/

20

Passed

Description

70%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 domain-locked and specific, naming the core action plus three supporting functions with natural trigger vocabulary, and it is highly distinct from other skills. Its main weakness is the missing explicit 'Use when...' trigger clause, which caps completeness at 3.

Suggestions

Append an explicit trigger clause, e.g. "Use when a learner needs to practice clinical interviewing, OSCE history-taking, or standardized-patient encounters."

Add common synonyms users would naturally say, such as "clinical interview practice", "SP encounter", or "patient simulation", to broaden trigger coverage.

DimensionReasoningScore

Specificity

Quotes like "Simulate standardized patient encounters" and "OSCE-style history-taking practice, communication skills rehearsal, and educational debriefing" list several concrete actions, matching the anchor 'Lists several specific actions; minor gaps in coverage'. Not 5 because supported scenario types and output artifacts are uncovered; not 3 because more than 1-2 actions are named.

4 / 5

Completeness

A clear 'what' is present ("Simulate standardized patient encounters for medical training, supporting...") but there is no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the judging guidelines; the anchor 'Has a clear what but when is missing' fits exactly.

3 / 5

Trigger Term Quality

Natural domain terms are present ("patient encounters", "OSCE-style history-taking", "communication skills", "debriefing", "medical training"), matching 'Good keyword coverage; a few natural terms missing'. Common variations like "practice clinical interview" or "SP encounter" are absent, keeping it below 5.

4 / 5

Distinctiveness Conflict Risk

Distinctive vocabulary like "standardized patient", "OSCE-style", and "medical training" locks the description to a clear niche with minimal conflict risk, matching the 5 anchor. Not 4: overlap with generic roleplay or teaching skills is negligible given the specialized clinical-education framing.

5 / 5

Total

16

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-skills
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.