Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Compile operational, quality, workforce, and compliance metrics into structured reports — weekly operational, monthly board, quarterly strategic — with trend analysis, benchmarking, and narrative synthesis. Pulls insights from every other agent. Use weekly for operational reports, monthly for board preparation, or ad-hoc when stakeholders need a summary.
.claude/skills/myceldigital-performance-report/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 61% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 27% | 0% |
You are the Executive 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 all current alerts and state. Reference outputs from other agents if available.
Ask: "What type of report do you need?" A) Weekly operational — for the leadership team. Focus on this week vs last week, incidents, capacity, immediate actions. B) Monthly board report — for the board/investors. Focus on KPIs, trends, strategic progress, risks, asks. C) Quarterly strategic — for strategic planning. Focus on market position, competitive landscape, growth trajectory, investment needs. D) Ad-hoc — specific topic or stakeholder request.
Weekly:
Monthly (board):
Quarterly:
Do NOT just present numbers. For each section:
The best board reports tell a STORY: here is where we are, here is where we are going, here is what we need.
Produce a structured document with:
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-03 | fail→fail | 22,942 | 14,307 | -38% | 1 | 1 | 0% | 4,050 | 3,445 | -15% | 0 | 0 | — |
case-01 | fail→fail | 22,778 | 15,997 | -30% | 1 | 1 | 0% | 3,998 | 3,721 | -7% | 0 | 0 | — |
case-02 | fail→fail | 21,958 | 19,029 | -13% | 1 | 1 | 0% | 4,002 | 4,242 | +6% | 0 | 0 | — |
case-04 | fail→fail | 6,571 | 14,714 | +124% | 1 | 1 | 0% | 1,142 | 3,300 | +189% | 0 | 0 | — |
case-05 | fail→fail | 13,780 | 10,222 | -26% | 1 | 1 | 0% | 1,798 | 2,305 | +28% | 0 | 0 | — |
case-06 | fail→pass | 12,990 | 10,090 | -22% | 1 | 1 | 0% | 1,939 | 2,538 | +31% | 0 | 0 | — |
case-07 | fail→pass | 12,788 | 15,082 | +18% | 1 | 1 | 0% | 2,127 | 3,431 | +61% | 0 | 0 | — |
case-08 | fail→pass | 15,067 | 12,755 | -15% | 1 | 1 | 0% | 2,158 | 2,926 | +36% | 0 | 0 | — |
case-09 | fail→pass | 13,780 | 11,068 | -20% | 1 | 1 | 0% | 2,050 | 2,670 | +30% | 0 | 0 | — |
case-10 | fail→fail | 7,642 | 10,570 | +38% | 1 | 1 | 0% | 1,300 | 2,615 | +101% | 0 | 0 | — |
case-11 | fail→pass | 11,792 | 10,905 | -8% | 1 | 1 | 0% | 2,043 | 2,596 | +27% | 0 | 0 | — |
case-12 | pass→pass | 13,128 | 18,778 | +43% | 1 | 1 | 0% | 2,151 | 3,907 | +82% | 0 | 0 | — |
case-13 | fail→fail | 9,660 | 7,792 | -19% | 1 | 1 | 0% | 1,622 | 2,169 | +34% | 0 | 0 | — |
case-14 | fail→pass | 12,648 | 16,339 | +29% | 1 | 1 | 0% | 2,056 | 3,706 | +80% | 0 | 0 | — |
case-15 | fail→pass | 13,342 | 12,992 | -3% | 1 | 1 | 0% | 2,358 | 3,186 | +35% | 0 | 0 | — |
case-16 | pass→pass | 22,811 | 16,731 | -27% | 1 | 1 | 0% | 3,067 | 3,723 | +21% | 0 | 0 | — |
case-17 | fail→fail | 17,198 | 15,329 | -11% | 1 | 1 | 0% | 2,831 | 3,326 | +17% | 0 | 0 | — |
case-18 | fail→fail | 10,008 | 14,476 | +45% | 1 | 1 | 0% | 1,514 | 3,234 | +114% | 0 | 0 | — |
case-19 | pass→pass | 13,321 | 12,471 | -6% | 1 | 1 | 0% | 2,211 | 2,784 | +26% | 0 | 0 | — |
case-20 | pass→pass | 17,346 | 21,502 | +24% | 1 | 1 | 0% | 3,139 | 4,023 | +28% | 0 | 0 | — |
case-21 | pass→pass | 18,669 | 13,257 | -29% | 1 | 1 | 0% | 3,496 | 3,160 | -10% | 0 | 0 | — |
case-22 | pass→fail | 2,447 | 4,812 | +97% | 1 | 1 | 0% | 382 | 1,760 | +361% | 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.