Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Run a hard two-option decision through Benjamin Franklin's 'moral or prudential algebra' — the weighted pro/con method he described to Joseph Priestley in 1772 — including the part everyone skips: striking out reasons that cancel, and letting the ledger sit before deciding. Use when weighing job offers, relocations, build-vs-buy, take-the-promotion, shut-it-down decisions, or any 'I keep going back and forth'. Produces a completed decision ledger with a leaning, its strongest counter, and a revi
.claude/skills/mohitagw15856-franklin-decision-ledger/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✓→✗ | ▼ Worse | 13% | 0% |
| case-11 | ✓→✗ | ▼ Worse | 6% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 12% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 9% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 9% | 0% |
One-line summary of the value this skill delivers. <!-- TODO: rewrite -->
Ask for (if not already provided):
<!-- TODO: a concrete template (headings/tables) of the final artifact -->
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→fail | 10,688 | 12,530 | +17% | 1 | 1 | 0% | 2,102 | 2,380 | +13% | 0 | 0 | — |
case-02 | pass→pass | 10,204 | 8,705 | -15% | 1 | 1 | 0% | 1,851 | 2,080 | +12% | 0 | 0 | — |
case-03 | pass→pass | 12,881 | 13,515 | +5% | 1 | 1 | 0% | 2,206 | 2,400 | +9% | 0 | 0 | — |
case-04 | pass→pass | 9,587 | 9,963 | +4% | 1 | 1 | 0% | 1,742 | 1,906 | +9% | 0 | 0 | — |
case-05 | pass→pass | 18,689 | 17,995 | -4% | 1 | 1 | 0% | 3,119 | 3,410 | +9% | 0 | 0 | — |
case-06 | pass→pass | 3,902 | 3,910 | +0% | 1 | 1 | 0% | 736 | 850 | +15% | 0 | 0 | — |
case-07 | fail→fail | 9,506 | 32,801 | +245% | 1 | 1 | 0% | 1,710 | 5,920 | +246% | 0 | 0 | — |
case-08 | pass→pass | 12,116 | 14,886 | +23% | 1 | 1 | 0% | 2,597 | 2,775 | +7% | 0 | 0 | — |
case-09 | pass→pass | 13,333 | 8,908 | -33% | 1 | 1 | 0% | 1,993 | 1,572 | -21% | 0 | 0 | — |
case-10 | pass→pass | 5,754 | 13,259 | +130% | 1 | 1 | 0% | 1,052 | 2,540 | +141% | 0 | 0 | — |
case-11 | pass→fail | 13,019 | 14,950 | +15% | 1 | 1 | 0% | 2,360 | 2,499 | +6% | 0 | 0 | — |
case-12 | pass→pass | 9,215 | 17,076 | +85% | 1 | 1 | 0% | 1,594 | 3,460 | +117% | 0 | 0 | — |
case-13 | pass→pass | 13,436 | 15,762 | +17% | 1 | 1 | 0% | 2,288 | 2,787 | +22% | 0 | 0 | — |
case-14 | pass→pass | 2,966 | 4,009 | +35% | 1 | 1 | 0% | 550 | 867 | +58% | 0 | 0 | — |
case-15 | pass→pass | 8,030 | 8,559 | +7% | 1 | 1 | 0% | 1,238 | 1,950 | +58% | 0 | 0 | — |
case-16 | pass→pass | 8,234 | 21,131 | +157% | 1 | 1 | 0% | 1,759 | 4,009 | +128% | 0 | 0 | — |
case-17 | pass→pass | 11,981 | 10,487 | -12% | 1 | 1 | 0% | 1,969 | 1,996 | +1% | 0 | 0 | — |
case-18 | pass→pass | 6,038 | 12,573 | +108% | 1 | 1 | 0% | 1,299 | 2,374 | +83% | 0 | 0 | — |
case-19 | pass→pass | 11,283 | 11,087 | -2% | 1 | 1 | 0% | 2,180 | 1,957 | -10% | 0 | 0 | — |
case-20 | pass→pass | 14,012 | 16,030 | +14% | 1 | 1 | 0% | 2,443 | 3,599 | +47% | 0 | 0 | — |
case-21 | pass→pass | 10,165 | 9,361 | -8% | 1 | 1 | 0% | 1,897 | 1,871 | -1% | 0 | 0 | — |
case-22 | pass→pass | 6,107 | 7,251 | +19% | 1 | 1 | 0% | 1,292 | 1,460 | +13% | 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 -100 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.
Other measured skills in the registry, with their headline benchmark lift.