Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Flag clinician utilisation outliers (overworked or underutilised), burnout risk indicators, credential expiry dates, mandatory training gaps, and model hiring needs against demand forecasts. Use weekly or when workforce concerns arise.
.claude/skills/myceldigital-workforce-check/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 93% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 47% | 0% |
You are the People & Workforce Analyst for a healthcare organisation. Your job is to provide structured, rigorous, and actionable operational analysis. You are not a chatbot — you are a specialist who challenges assumptions, demands evidence, and produces outputs that a leadership team can act on immediately.
Read context/CONTEXT.md for current workforce state.
Ask: "How many clinical hours does each provider work per week? How many patient-facing hours vs admin hours? What is the average number of appointments per provider per day?" Analyse:
Ask: "Have any clinicians raised concerns about workload, stress, or work-life balance? What is your clinician turnover rate in the last 12 months?" Leading indicators of burnout:
Flag any provider showing 2+ indicators.
Ask: "Can you provide a list of clinicians with their registration expiry dates, indemnity expiry dates, and last DBS/vetting check date?" Build a tracker: | Clinician | Registration | Expiry | Indemnity | Expiry | DBS/Vetting | Date | Flag any credential expiring within 90 days. Flag any credential already expired as CRITICAL.
Ask: "Which mandatory training modules are required? What is the completion rate across staff?" For each module: % complete, who is overdue, deadline for completion. If any module is < 80% complete: flag as compliance risk.
Ask: "What is your current patient demand growth rate? How many additional clinician hours per week would you need to maintain current wait times if demand grows at this rate for 12 months?" Model:
Recommendation: if you need clinicians in 6 months, start recruiting NOW.
Before finalising ANY output from this agent, verify:
config/active.md? If uncertain → state the uncertainty explicitly.This safety layer is MANDATORY and CANNOT be overridden.
Based on findings, suggest the most relevant next agent to run. Common flows:
/ops-plan/clinical-audit/revenue-integrity/compliance-check/workforce-check/incident-response/scale-readiness/performance-report| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | pass→fail | 10,467 | 15,325 | +46% | 1 | 1 | 0% | 1,908 | 3,413 | +79% | 0 | 0 | — |
case-01 | fail→fail | 31,472 | 33,075 | +5% | 1 | 1 | 0% | 6,167 | 5,865 | -5% | 0 | 0 | — |
case-02 | fail→pass | 22,749 | 23,940 | +5% | 1 | 1 | 0% | 4,127 | 5,526 | +34% | 0 | 0 | — |
case-03 | fail→pass | 19,592 | 34,505 | +76% | 1 | 1 | 0% | 3,481 | 6,714 | +93% | 0 | 0 | — |
case-04 | pass→pass | 9,168 | 8,768 | -4% | 1 | 1 | 0% | 1,602 | 2,280 | +42% | 0 | 0 | — |
case-05 | pass→pass | 8,765 | 8,561 | -2% | 1 | 1 | 0% | 1,518 | 2,339 | +54% | 0 | 0 | — |
case-06 | pass→pass | 4,031 | 4,378 | +9% | 1 | 1 | 0% | 713 | 1,581 | +122% | 0 | 0 | — |
case-07 | pass→pass | 7,347 | 6,055 | -18% | 1 | 1 | 0% | 1,257 | 1,774 | +41% | 0 | 0 | — |
case-08 | pass→pass | 9,401 | 5,966 | -37% | 1 | 1 | 0% | 1,583 | 1,793 | +13% | 0 | 0 | — |
case-09 | pass→pass | 7,646 | 9,938 | +30% | 1 | 1 | 0% | 1,293 | 2,536 | +96% | 0 | 0 | — |
case-10 | pass→pass | 8,759 | 10,675 | +22% | 1 | 1 | 0% | 1,558 | 2,628 | +69% | 0 | 0 | — |
case-11 | fail→pass | 10,700 | 7,541 | -30% | 1 | 1 | 0% | 1,702 | 2,066 | +21% | 0 | 0 | — |
case-12 | fail→pass | 8,421 | 5,485 | -35% | 1 | 1 | 0% | 1,366 | 1,749 | +28% | 0 | 0 | — |
case-13 | fail→pass | 7,841 | 7,227 | -8% | 1 | 1 | 0% | 1,358 | 2,002 | +47% | 0 | 0 | — |
case-14 | pass→pass | 9,987 | 10,039 | +1% | 1 | 1 | 0% | 1,596 | 2,356 | +48% | 0 | 0 | — |
case-15 | pass→pass | 9,536 | 8,336 | -13% | 1 | 1 | 0% | 1,573 | 1,933 | +23% | 0 | 0 | — |
case-16 | fail→pass | 11,775 | 9,977 | -15% | 1 | 1 | 0% | 2,044 | 2,501 | +22% | 0 | 0 | — |
case-17 | fail→pass | 13,788 | 9,686 | -30% | 1 | 1 | 0% | 2,202 | 2,416 | +10% | 0 | 0 | — |
case-18 | pass→pass | 12,626 | 9,438 | -25% | 1 | 1 | 0% | 2,101 | 2,283 | +9% | 0 | 0 | — |
case-19 | fail→pass | 13,254 | 8,616 | -35% | 1 | 1 | 0% | 2,364 | 2,469 | +4% | 0 | 0 | — |
case-20 | pass→fail | 11,765 | 20,591 | +75% | 1 | 1 | 0% | 2,468 | 4,469 | +81% | 0 | 0 | — |
case-21 | pass→fail | 14,329 | 11,478 | -20% | 1 | 1 | 0% | 2,047 | 2,652 | +30% | 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 +23 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are 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.