Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Collect and validate patient information during medical intake process. Use when a healthcare provider needs to gather patient demographics, medical history, insurance information, and consent forms in a structured workflow.
.claude/skills/migrateforce-patient-intake/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 106% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -50% | 0% |
This skill guides agents through the patient intake process, ensuring complete and accurate data collection while maintaining HIPAA compliance. The skill handles:
| Field | Type | Required | Description | |-------|------|----------|-------------| | patient_name | string | yes | Full legal name | | date_of_birth | date | yes | DOB in YYYY-MM-DD format | | ssn_last_four | string | no | Last 4 digits of SSN | | insurance_provider | string | no | Primary insurance | | policy_number | string | no | Insurance policy number | | chief_complaint | string | yes | Reason for visit |
| Field | Type | Description | |-------|------|-------------| | intake_form_id | string | Unique identifier for the completed intake | | validation_status | enum | 'complete' | 'incomplete' | 'needs_review' | | missing_fields | array | List of fields that need completion | | next_steps | array | Recommended follow-up actions |
Agent: I'll help you complete the patient intake. Let me start by collecting some basic information.
Agent: What is the patient's full legal name?
User: John Michael Smith
Agent: And their date of birth?
User: March 15, 1985
Agent: What is the primary reason for today's visit?
User: Annual physical exam and blood pressure check| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 11,099 | 6,135 | -45% | 1 | 1 | 0% | 1,435 | 1,734 | +21% | 0 | 0 | — |
case-02 | fail→fail | 7,833 | 5,081 | -35% | 1 | 1 | 0% | 1,484 | 1,639 | +10% | 0 | 0 | — |
case-03 | pass→fail | 15,530 | 13,193 | -15% | 1 | 1 | 0% | 2,581 | 2,972 | +15% | 0 | 0 | — |
case-04 | pass→pass | 14,355 | 9,686 | -33% | 1 | 1 | 0% | 3,100 | 2,456 | -21% | 0 | 0 | — |
case-05 | pass→pass | 9,344 | 9,425 | +1% | 1 | 1 | 0% | 1,704 | 2,299 | +35% | 0 | 0 | — |
case-06 | fail→pass | 11,260 | 3,609 | -68% | 1 | 1 | 0% | 2,175 | 1,279 | -41% | 0 | 0 | — |
case-07 | fail→pass | 5,057 | 4,913 | -3% | 1 | 1 | 0% | 749 | 1,540 | +106% | 0 | 0 | — |
case-08 | fail→pass | 6,473 | 4,041 | -38% | 1 | 1 | 0% | 982 | 1,321 | +35% | 0 | 0 | — |
case-09 | fail→pass | 5,162 | 3,708 | -28% | 1 | 1 | 0% | 921 | 1,251 | +36% | 0 | 0 | — |
case-10 | fail→fail | 3,587 | 5,800 | +62% | 1 | 1 | 0% | 746 | 1,747 | +134% | 0 | 0 | — |
case-11 | pass→pass | 3,706 | 5,505 | +49% | 1 | 1 | 0% | 587 | 1,777 | +203% | 0 | 0 | — |
case-12 | fail→pass | 11,149 | 1,967 | -82% | 1 | 1 | 0% | 1,806 | 897 | -50% | 0 | 0 | — |
case-13 | fail→fail | 9,027 | 8,152 | -10% | 1 | 1 | 0% | 1,625 | 1,924 | +18% | 0 | 0 | — |
case-14 | pass→pass | 8,933 | 5,887 | -34% | 1 | 1 | 0% | 1,611 | 1,416 | -12% | 0 | 0 | — |
case-15 | pass→pass | 10,970 | 5,226 | -52% | 1 | 1 | 0% | 1,923 | 1,450 | -25% | 0 | 0 | — |
case-16 | pass→pass | 4,674 | 2,166 | -54% | 1 | 1 | 0% | 682 | 881 | +29% | 0 | 0 | — |
case-17 | fail→fail | 4,819 | 1,672 | -65% | 1 | 1 | 0% | 714 | 875 | +23% | 0 | 0 | — |
case-18 | pass→pass | 10,947 | 1,903 | -83% | 1 | 1 | 0% | 1,886 | 886 | -53% | 0 | 0 | — |
case-19 | fail→pass | 11,000 | 4,049 | -63% | 1 | 1 | 0% | 2,301 | 1,420 | -38% | 0 | 0 | — |
case-20 | fail→pass | 6,190 | 5,490 | -11% | 1 | 1 | 0% | 1,046 | 1,682 | +61% | 0 | 0 | — |
case-21 | pass→pass | 9,993 | 1,583 | -84% | 1 | 1 | 0% | 1,652 | 796 | -52% | 0 | 0 | — |
case-22 | pass→pass | 9,543 | 2,079 | -78% | 1 | 1 | 0% | 1,702 | 901 | -47% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +27 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.