Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Structure rollout plans for any operational change — workflow redesign, system update, new service line, policy change — with stakeholder mapping, training plan, adoption metrics, resistance analysis, and rollback triggers. Use when planning any significant operational change.
.claude/skills/myceldigital-change-management/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 56% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 26% | 0% |
You are the Implementation Lead 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 operational state.
Ask: "What is changing? Why? What is the expected benefit? What is the timeline?" Clarify: is this a process change, a technology change, a policy change, or a service change? Each has different implementation requirements.
Ask: "Who is affected by this change? (clinicians, admin staff, patients, referrers, regulators)" For each stakeholder group:
For each affected group:
Define: how will you know the change was successful?
Define: what would cause you to revert this change?
Document the rollback procedure before you start.
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-12 | pass→pass | 13,115 | 19,941 | +52% | 1 | 1 | 0% | 2,324 | 4,060 | +75% | 0 | 0 | — |
case-04 | pass→pass | 17,018 | 18,021 | +6% | 1 | 1 | 0% | 2,951 | 3,872 | +31% | 0 | 0 | — |
case-05 | pass→pass | 20,008 | 23,358 | +17% | 1 | 1 | 0% | 3,037 | 4,717 | +55% | 0 | 0 | — |
case-03 | fail→fail | 34,784 | 24,226 | -30% | 1 | 1 | 0% | 6,213 | 5,115 | -18% | 0 | 0 | — |
case-01 | fail→pass | 27,817 | 18,944 | -32% | 1 | 1 | 0% | 4,877 | 4,073 | -16% | 0 | 0 | — |
case-02 | fail→pass | 23,016 | 27,180 | +18% | 1 | 1 | 0% | 3,854 | 3,909 | +1% | 0 | 0 | — |
case-06 | pass→pass | 14,775 | 23,668 | +60% | 1 | 1 | 0% | 2,607 | 4,694 | +80% | 0 | 0 | — |
case-07 | pass→pass | 16,493 | 20,945 | +27% | 1 | 1 | 0% | 2,805 | 4,309 | +54% | 0 | 0 | — |
case-08 | fail→pass | 16,014 | 21,288 | +33% | 1 | 1 | 0% | 2,776 | 4,344 | +56% | 0 | 0 | — |
case-09 | fail→fail | 17,434 | 18,491 | +6% | 1 | 1 | 0% | 2,789 | 3,640 | +31% | 0 | 0 | — |
case-10 | fail→pass | 17,311 | 17,036 | -2% | 1 | 1 | 0% | 2,875 | 3,662 | +27% | 0 | 0 | — |
case-11 | fail→fail | 17,886 | 24,613 | +38% | 1 | 1 | 0% | 3,029 | 5,043 | +66% | 0 | 0 | — |
case-13 | fail→pass | 15,709 | 16,036 | +2% | 1 | 1 | 0% | 2,609 | 3,290 | +26% | 0 | 0 | — |
case-14 | fail→pass | 13,793 | 20,346 | +48% | 1 | 1 | 0% | 2,319 | 4,047 | +75% | 0 | 0 | — |
case-15 | fail→pass | 14,660 | 23,742 | +62% | 1 | 1 | 0% | 2,283 | 4,186 | +83% | 0 | 0 | — |
case-16 | fail→pass | 9,850 | 13,958 | +42% | 1 | 1 | 0% | 1,536 | 2,896 | +89% | 0 | 0 | — |
case-17 | pass→pass | 15,187 | 23,177 | +53% | 1 | 1 | 0% | 2,501 | 4,534 | +81% | 0 | 0 | — |
case-18 | pass→pass | 15,042 | 25,869 | +72% | 1 | 1 | 0% | 2,082 | 4,398 | +111% | 0 | 0 | — |
case-19 | pass→pass | 22,201 | 23,157 | +4% | 1 | 1 | 0% | 3,708 | 4,520 | +22% | 0 | 0 | — |
case-20 | pass→fail | 11,084 | 17,584 | +59% | 1 | 1 | 0% | 1,911 | 3,777 | +98% | 0 | 0 | — |
case-21 | fail→fail | 27,229 | 38,634 | +42% | 1 | 1 | 0% | 6,189 | 6,950 | +12% | 0 | 0 | — |
case-22 | pass→pass | 9,129 | 17,690 | +94% | 1 | 1 | 0% | 1,690 | 3,932 | +133% | 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 +32 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.