Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Synthesise overnight incidents, today's capacity vs demand, provider availability, regulatory deadlines, and operational red flags into a structured 2-minute morning briefing. Use when starting the day, preparing for a morning huddle, or when asked for an operational summary.
.claude/skills/myceldigital-morning-brief/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -7% | 0% |
You are the operations lead preparing a structured morning briefing for the healthcare CEO. Your job is to surface the 3-5 things that MUST be dealt with today and flag anything that changed overnight.
Read config/active.md for jurisdiction context. Read context/CONTEXT.md for shared operational state.
Ask: "Were there any clinical incidents, patient complaints, system outages, or staffing emergencies overnight or since the last briefing?"
If yes: for each incident, capture:
If no: confirm "No overnight incidents" and move on.
Ask: "What does today's schedule look like? How many appointment slots are filled vs available? Any providers out sick or on leave?"
Analyse:
Check: are there any regulatory deadlines in the next 30 days? Reference config/active.md for jurisdiction-specific obligations.
Common deadlines to check:
Ask: "Are there any metrics that have moved significantly since the last briefing?"
Prompt for:
For each red flag: state the metric, the direction of change, and the potential consequence if not addressed.
Produce a structured briefing:
MORNING BRIEF — [date]
INCIDENTS:
[list or "None"]
TODAY'S CAPACITY:
[fill rate, provider status, actions]
REGULATORY:
[upcoming deadlines or "Clear for 30 days"]
RED FLAGS:
[metrics of concern or "All metrics normal"]
TOP 3 PRIORITIES TODAY:
1. [most urgent — explain why]
2. [second priority]
3. [third priority]Update context/CONTEXT.md with any new incidents, deadline changes, or alerts.
Before finalising this briefing, verify:
Suggest next: If incidents were logged → /incident-response. If capacity concerns → /ops-plan. If regulatory deadlines approaching → /compliance-check.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-20 | pass→fail | 25,898 | 12,243 | -53% | 1 | 1 | 0% | 4,442 | 2,867 | -35% | 0 | 0 | — |
case-01 | fail→fail | 11,506 | 9,635 | -16% | 1 | 1 | 0% | 1,901 | 2,447 | +29% | 0 | 0 | — |
case-02 | fail→fail | 10,877 | 6,830 | -37% | 1 | 1 | 0% | 1,846 | 1,945 | +5% | 0 | 0 | — |
case-03 | fail→fail | 13,840 | 6,452 | -53% | 1 | 1 | 0% | 2,484 | 1,980 | -20% | 0 | 0 | — |
case-04 | pass→pass | 9,241 | 4,203 | -55% | 1 | 1 | 0% | 1,635 | 1,563 | -4% | 0 | 0 | — |
case-05 | pass→pass | 12,192 | 6,195 | -49% | 1 | 1 | 0% | 1,991 | 1,773 | -11% | 0 | 0 | — |
case-06 | fail→pass | 9,265 | 4,907 | -47% | 1 | 1 | 0% | 1,552 | 1,607 | +4% | 0 | 0 | — |
case-07 | fail→pass | 8,669 | 5,613 | -35% | 1 | 1 | 0% | 1,520 | 1,739 | +14% | 0 | 0 | — |
case-08 | fail→pass | 5,770 | 2,277 | -61% | 1 | 1 | 0% | 1,047 | 1,140 | +9% | 0 | 0 | — |
case-09 | fail→pass | 7,540 | 4,265 | -43% | 1 | 1 | 0% | 1,235 | 1,458 | +18% | 0 | 0 | — |
case-10 | fail→pass | 10,960 | 5,248 | -52% | 1 | 1 | 0% | 1,755 | 1,625 | -7% | 0 | 0 | — |
case-11 | pass→pass | 12,355 | 5,034 | -59% | 1 | 1 | 0% | 2,106 | 1,620 | -23% | 0 | 0 | — |
case-21 | pass→pass | 25,023 | 19,858 | -21% | 1 | 1 | 0% | 4,712 | 4,510 | -4% | 0 | 0 | — |
case-12 | fail→pass | 8,944 | 5,215 | -42% | 1 | 1 | 0% | 1,531 | 1,679 | +10% | 0 | 0 | — |
case-13 | pass→pass | 10,766 | 5,070 | -53% | 1 | 1 | 0% | 1,805 | 1,586 | -12% | 0 | 0 | — |
case-14 | pass→pass | 10,001 | 6,340 | -37% | 1 | 1 | 0% | 1,595 | 1,760 | +10% | 0 | 0 | — |
case-15 | fail→pass | 7,530 | 2,127 | -72% | 1 | 1 | 0% | 1,101 | 1,090 | -1% | 0 | 0 | — |
case-22 | pass→pass | 17,317 | 15,586 | -10% | 1 | 1 | 0% | 3,883 | 4,191 | +8% | 0 | 0 | — |
case-16 | fail→pass | 9,998 | 1,487 | -85% | 1 | 1 | 0% | 1,718 | 990 | -42% | 0 | 0 | — |
case-17 | fail→pass | 7,308 | 1,964 | -73% | 1 | 1 | 0% | 1,148 | 1,073 | -7% | 0 | 0 | — |
case-18 | fail→pass | 7,553 | 1,958 | -74% | 1 | 1 | 0% | 1,063 | 1,054 | -1% | 0 | 0 | — |
case-19 | fail→pass | 7,842 | 2,053 | -74% | 1 | 1 | 0% | 1,367 | 1,104 | -19% | 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 +45 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 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.