Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Define a North Star Metric and 3-5 supporting input metrics that form a metrics constellation. Classify the business game (Attention, Transaction, Productivity) and validate against 7 criteria for an effective North Star. Use when choosing a North Star Metric, setting up a metrics framework, learning about the North Star Framework, or deciding what to measure.
.claude/skills/phuryn-north-star-metric/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 5% | 0% |
Identify a North Star Metric and 3-5 Input Metrics that form a metrics constellation. Classifies the business game being played and validates against criteria for an effective North Star. Use when defining key metrics, setting up a metrics framework, or choosing what to measure.
NSM is NOT: multiple metrics, a revenue/LTV metric (must be customer-centric), an OKR (that's a goal-setting technique), or a strategy (but choosing the right NSM is a strategic choice).
NSM IS: a single, customer-centric KPI that reflects the value customers get from the product and serves as a leading indicator of long-term business success. You can use Key Results (OKRs) to express expected change in NSM.
Free resource: The North Star Framework 101 (PDF)
Before identifying your North Star, classify your business into one of these three games:
You are a metrics strategist specializing in North Star metrics and growth measurement frameworks.
Given the following business context: $ARGUMENTS
Step 1: Classify the Business Game Determine which game this company plays: Attention, Transaction, or Productivity.
Step 2: Identify the North Star Metric Suggest a single metric that meets all seven criteria for an effective North Star:
Step 3: Identify Input Metrics Define 3-5 Input Metrics (also called leading indicators) that most directly influence and drive the North Star Metric. Each input metric should:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 19,501 | 16,902 | -13% | 1 | 1 | 0% | 3,288 | 3,288 | 0% | 0 | 0 | — |
case-02 | fail→pass | 15,922 | 13,146 | -17% | 1 | 1 | 0% | 2,676 | 3,179 | +19% | 0 | 0 | — |
case-03 | fail→pass | 14,328 | 12,674 | -12% | 1 | 1 | 0% | 2,554 | 3,072 | +20% | 0 | 0 | — |
case-04 | pass→pass | 23,246 | 13,936 | -40% | 1 | 1 | 0% | 3,108 | 3,286 | +6% | 0 | 0 | — |
case-05 | fail→pass | 13,218 | 13,357 | +1% | 1 | 1 | 0% | 2,320 | 2,802 | +21% | 0 | 0 | — |
case-06 | fail→pass | 15,075 | 10,762 | -29% | 1 | 1 | 0% | 2,622 | 2,761 | +5% | 0 | 0 | — |
case-07 | pass→pass | 15,494 | 13,918 | -10% | 1 | 1 | 0% | 2,589 | 3,218 | +24% | 0 | 0 | — |
case-08 | fail→pass | 18,022 | 16,284 | -10% | 1 | 1 | 0% | 2,860 | 3,196 | +12% | 0 | 0 | — |
case-09 | fail→pass | 17,214 | 12,668 | -26% | 1 | 1 | 0% | 2,163 | 3,036 | +40% | 0 | 0 | — |
case-10 | fail→pass | 17,608 | 15,872 | -10% | 1 | 1 | 0% | 2,963 | 3,597 | +21% | 0 | 0 | — |
case-11 | fail→pass | 20,940 | 12,954 | -38% | 1 | 1 | 0% | 2,903 | 3,155 | +9% | 0 | 0 | — |
case-12 | fail→pass | 12,285 | 11,494 | -6% | 1 | 1 | 0% | 1,966 | 2,792 | +42% | 0 | 0 | — |
case-13 | fail→pass | 22,255 | 16,151 | -27% | 1 | 1 | 0% | 2,792 | 3,307 | +18% | 0 | 0 | — |
case-14 | fail→pass | 16,419 | 14,137 | -14% | 1 | 1 | 0% | 2,320 | 3,320 | +43% | 0 | 0 | — |
case-15 | fail→pass | 14,580 | 12,111 | -17% | 1 | 1 | 0% | 2,367 | 3,013 | +27% | 0 | 0 | — |
case-16 | fail→fail | 14,150 | 13,286 | -6% | 1 | 1 | 0% | 2,396 | 3,140 | +31% | 0 | 0 | — |
case-17 | fail→pass | 13,859 | 11,029 | -20% | 1 | 1 | 0% | 2,372 | 3,058 | +29% | 0 | 0 | — |
case-18 | fail→pass | 14,517 | 12,742 | -12% | 1 | 1 | 0% | 2,399 | 2,992 | +25% | 0 | 0 | — |
case-19 | fail→pass | 19,834 | 14,321 | -28% | 1 | 1 | 0% | 2,855 | 3,278 | +15% | 0 | 0 | — |
case-20 | pass→pass | 12,583 | 13,196 | +5% | 1 | 1 | 0% | 2,067 | 3,017 | +46% | 0 | 0 | — |
case-21 | pass→fail | 10,535 | 17,671 | +68% | 1 | 1 | 0% | 2,219 | 3,172 | +43% | 0 | 0 | — |
case-22 | pass→fail | 27,211 | 13,461 | -51% | 1 | 1 | 0% | 4,163 | 3,180 | -24% | 0 | 0 | — |
case-23 | pass→fail | 25,389 | 17,956 | -29% | 1 | 1 | 0% | 4,282 | 3,835 | -10% | 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. 23 cases were attempted. The headline lift of +57 percentage points is the difference between those two pass rates over the 23 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.