Source: https://github.com/aipoch/medical-research-skills
Virtual Patient Roleplay
Structured standardized-patient simulation for medical training and clinical interview practice.
Educational Disclaimer: All output is for training simulation only. This skill does not provide real clinical diagnosis, treatment selection, or emergency instructions. Faculty supervision is required for formal assessment use.
Quick Check
python -m py_compile scripts/main.py
python -c "from scripts.main import PatientSimulator; sim=PatientSimulator('chest_pain'); print(sim.ask('Where does the pain go?')['patient_response'])"
When to Use
- Use this skill for OSCE-style history-taking practice, communication skills rehearsal, or debrief planning.
- Use this skill when a learner needs to practice clinical interviewing with a simulated patient response.
- Do not use this skill for real patient triage, clinical diagnosis, treatment selection, or emergency guidance.
Workflow
- Confirm the training goal, scenario type, learner level, and output focus (questioning, bedside manner, or debriefing).
- Check whether the request is for live roleplay, case setup, feedback, or post-encounter summary.
- Use the packaged simulator for supported scenarios; otherwise provide a manual roleplay scaffold without inventing unsupported medical certainty.
- Return the patient response or teaching artifact with assumptions, missed-question prompts, and debrief notes.
- If the request exceeds educational scope, stop and restate the boundary explicitly.
Usage
python -c "from scripts.main import PatientSimulator; sim=PatientSimulator('chest_pain'); print(sim.ask('Where does the pain go?')['patient_response'])"
python -c "from scripts.main import PatientSimulator; sim=PatientSimulator('headache'); print(sim.ask('Did the pain start suddenly?')['patient_response'])"
Parameters
| Parameter |
Type |
Required |
Default |
Description |
scenario |
string |
No |
chest_pain |
Scenario: chest_pain, headache, abdominal_pain |
student_question |
string |
Yes (for interaction) |
— |
Learner question posed to the patient |
difficulty |
string |
No |
intermediate |
Scenario difficulty level |
Output
- Simulated patient response
- Scenario-specific cues and debrief elements
- Explicit reminder that output is educational, not clinical advice
Scope Boundaries
- This skill supports training simulations, not real clinical triage.
- This skill does not provide diagnosis, treatment selection, or emergency instructions.
- This skill should not be used as a substitute for faculty supervision or patient care.
Stress-Case Rules
For complex multi-constraint requests, always include these explicit blocks:
- Training Objective
- Scenario Assumptions
- Roleplay Output
- Educational Limits
- Debrief and Next Checks
Error Handling
- If required inputs are missing, state exactly which fields are missing and request only the minimum additional information.
- If the task goes outside the documented scope, stop instead of guessing or silently widening the assignment.
- If
scripts/main.py fails, report the failure point, summarize what still can be completed safely, and provide a manual fallback.
- Do not fabricate clinical certainty, real patient data, or verified diagnostic outcomes.
Input Validation
This skill accepts: a scenario identifier and a learner question for standardized patient simulation in a medical training context.
If the request does not involve educational patient simulation — for example, asking for real clinical diagnosis, treatment recommendations, emergency triage, or non-medical roleplay — do not proceed with the workflow. Instead respond:
"virtual-patient-roleplay is designed for medical training simulations only. Your request appears to be outside this scope. Please provide a scenario and learner question for educational practice, or use a more appropriate tool."
References
- references/references.md — Educational standards and simulation frameworks
- references/audit-reference.md — Supported scope, audit commands, and fallback boundaries
Response Template
Use the following fixed structure for non-trivial requests:
- Objective
- Inputs Received
- Assumptions
- Workflow
- Deliverable
- Risks and Limits
- Next Checks
If the request is simple, you may compress the structure, but still keep assumptions and limits explicit when they affect correctness.
1---2name: virtual-patient-roleplay3description: Simulate standardized patient encounters for medical training, supporting OSCE-style history-taking practice, communication skills rehearsal, and educational debriefing.4license: MIT5---6> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)
7
8# Virtual Patient Roleplay
9
10Structured standardized-patient simulation for medical training and clinical interview practice.
11
12> **Educational Disclaimer:** All output is for training simulation only. This skill does not provide real clinical diagnosis, treatment selection, or emergency instructions. Faculty supervision is required for formal assessment use.
13
14## Quick Check
15
16```bash
17python -m py_compile scripts/main.py
18python -c "from scripts.main import PatientSimulator; sim=PatientSimulator('chest_pain'); print(sim.ask('Where does the pain go?')['patient_response'])"
19```
20
21## When to Use
22
23- Use this skill for OSCE-style history-taking practice, communication skills rehearsal, or debrief planning.
24- Use this skill when a learner needs to practice clinical interviewing with a simulated patient response.
25- Do not use this skill for real patient triage, clinical diagnosis, treatment selection, or emergency guidance.
26
27## Workflow
28
291. Confirm the training goal, scenario type, learner level, and output focus (questioning, bedside manner, or debriefing).
302. Check whether the request is for live roleplay, case setup, feedback, or post-encounter summary.
313. Use the packaged simulator for supported scenarios; otherwise provide a manual roleplay scaffold without inventing unsupported medical certainty.
324. Return the patient response or teaching artifact with assumptions, missed-question prompts, and debrief notes.
335. If the request exceeds educational scope, stop and restate the boundary explicitly.
34
35## Usage
36
37```text
38python -c "from scripts.main import PatientSimulator; sim=PatientSimulator('chest_pain'); print(sim.ask('Where does the pain go?')['patient_response'])"
39python -c "from scripts.main import PatientSimulator; sim=PatientSimulator('headache'); print(sim.ask('Did the pain start suddenly?')['patient_response'])"
40```
41
42## Parameters
43
44| Parameter | Type | Required | Default | Description |
45|-----------|------|----------|---------|-------------|
46| `scenario` | string | No | `chest_pain` | Scenario: `chest_pain`, `headache`, `abdominal_pain` |
47| `student_question` | string | Yes (for interaction) | — | Learner question posed to the patient |
48| `difficulty` | string | No | `intermediate` | Scenario difficulty level |
49
50## Output
51
52- Simulated patient response
53- Scenario-specific cues and debrief elements
54- Explicit reminder that output is educational, not clinical advice
55
56## Scope Boundaries
57
58- This skill supports training simulations, not real clinical triage.
59- This skill does not provide diagnosis, treatment selection, or emergency instructions.
60- This skill should not be used as a substitute for faculty supervision or patient care.
61
62## Stress-Case Rules
63
64For complex multi-constraint requests, always include these explicit blocks:
65
661. Training Objective
672. Scenario Assumptions
683. Roleplay Output
694. Educational Limits
705. Debrief and Next Checks
71
72## Error Handling
73
74- If required inputs are missing, state exactly which fields are missing and request only the minimum additional information.
75- If the task goes outside the documented scope, stop instead of guessing or silently widening the assignment.
76- If `scripts/main.py` fails, report the failure point, summarize what still can be completed safely, and provide a manual fallback.
77- Do not fabricate clinical certainty, real patient data, or verified diagnostic outcomes.
78
79## Input Validation
80
81This skill accepts: a scenario identifier and a learner question for standardized patient simulation in a medical training context.
82
83If the request does not involve educational patient simulation — for example, asking for real clinical diagnosis, treatment recommendations, emergency triage, or non-medical roleplay — do not proceed with the workflow. Instead respond:
84> "virtual-patient-roleplay is designed for medical training simulations only. Your request appears to be outside this scope. Please provide a scenario and learner question for educational practice, or use a more appropriate tool."
85
86## References
87
88- [references/references.md](references/references.md) — Educational standards and simulation frameworks
89- [references/audit-reference.md](references/audit-reference.md) — Supported scope, audit commands, and fallback boundaries
90
91## Response Template
92
93Use the following fixed structure for non-trivial requests:
94
951. Objective
962. Inputs Received
973. Assumptions
984. Workflow
995. Deliverable
1006. Risks and Limits
1017. Next Checks
102
103If the request is simple, you may compress the structure, but still keep assumptions and limits explicit when they affect correctness.
gabrielmoreira