Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Record decisions the way good judgment compounds — the reasoning, the alternatives, the probabilities, and what would change your mind, written down BEFORE the outcome arrives, then reviewed against reality. Use when asked help me think through this decision, start a decision journal, review my past decision, or why do I keep making the same mistake. Produces the pre-registered decision entry, the review-date trigger, and the outcome review that separates bad luck from bad process.
.claude/skills/mohitagw15856-decision-journal/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 26% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 17% | 0% |
Memory is a defense attorney: after the outcome arrives, everyone remembers having known it all along, and the reasoning that actually drove the choice is quietly rewritten. A decision journal defeats that — the reasoning gets pre-registered before reality votes, so the review can ask the only question that improves judgment: was the process good, given what was knowable then? Good decisions lose sometimes; bad ones win sometimes; only the written record can tell you which you're making. This is the library's 600th skill because it's the one all the others compound through.
Ask for these if not provided:
Deciding: the actual choice + deadline] · State: known / guessed / mood flag]
Choice: option] · Because: the 2–3 load-bearing reasons] Expectations: X% that (observable) by (date); …] I'm wrong if: observable + date] · Review on: date]
(At review:)
What happened: … vs. expected: … Quadrant: skill / variance / lucky / tuition] — why] Transferable lesson: one sentence, about process not this event]
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→pass | 15,963 | 15,140 | -5% | 1 | 1 | 0% | 2,717 | 3,437 | +26% | 0 | 0 | — |
case-01 | fail→pass | 18,016 | 13,419 | -26% | 1 | 1 | 0% | 2,962 | 3,339 | +13% | 0 | 0 | — |
case-02 | pass→fail | 11,991 | 14,744 | +23% | 1 | 1 | 0% | 1,949 | 3,315 | +70% | 0 | 0 | — |
case-04 | pass→fail | 14,468 | 13,859 | -4% | 1 | 1 | 0% | 2,412 | 3,433 | +42% | 0 | 0 | — |
case-05 | pass→pass | 16,844 | 13,544 | -20% | 1 | 1 | 0% | 2,835 | 3,383 | +19% | 0 | 0 | — |
case-06 | pass→pass | 12,754 | 14,480 | +14% | 1 | 1 | 0% | 2,037 | 3,341 | +64% | 0 | 0 | — |
case-07 | pass→pass | 11,085 | 8,929 | -19% | 1 | 1 | 0% | 1,961 | 2,404 | +23% | 0 | 0 | — |
case-08 | fail→pass | 9,383 | 6,549 | -30% | 1 | 1 | 0% | 1,393 | 2,061 | +48% | 0 | 0 | — |
case-09 | pass→pass | 6,540 | 3,958 | -39% | 1 | 1 | 0% | 1,018 | 1,767 | +74% | 0 | 0 | — |
case-10 | pass→pass | 10,812 | 9,257 | -14% | 1 | 1 | 0% | 1,562 | 2,507 | +60% | 0 | 0 | — |
case-11 | pass→pass | 9,348 | 8,627 | -8% | 1 | 1 | 0% | 1,579 | 2,337 | +48% | 0 | 0 | — |
case-12 | pass→pass | 11,708 | 9,868 | -16% | 1 | 1 | 0% | 1,887 | 2,425 | +29% | 0 | 0 | — |
case-13 | pass→pass | 14,268 | 10,422 | -27% | 1 | 1 | 0% | 2,258 | 2,516 | +11% | 0 | 0 | — |
case-14 | pass→pass | 10,615 | 7,291 | -31% | 1 | 1 | 0% | 1,676 | 2,054 | +23% | 0 | 0 | — |
case-15 | pass→pass | 15,458 | 10,037 | -35% | 1 | 1 | 0% | 2,391 | 2,588 | +8% | 0 | 0 | — |
case-16 | pass→pass | 11,012 | 7,543 | -32% | 1 | 1 | 0% | 1,789 | 2,245 | +25% | 0 | 0 | — |
case-17 | fail→pass | 13,257 | 8,809 | -34% | 1 | 1 | 0% | 2,180 | 2,343 | +7% | 0 | 0 | — |
case-18 | fail→pass | 14,429 | 8,784 | -39% | 1 | 1 | 0% | 2,045 | 2,390 | +17% | 0 | 0 | — |
case-19 | fail→fail | 8,501 | 8,610 | +1% | 1 | 1 | 0% | 1,451 | 2,311 | +59% | 0 | 0 | — |
case-20 | pass→pass | 6,873 | 7,396 | +8% | 1 | 1 | 0% | 1,040 | 2,078 | +100% | 0 | 0 | — |
case-21 | fail→pass | 12,485 | 14,080 | +13% | 1 | 1 | 0% | 2,003 | 2,871 | +43% | 0 | 0 | — |
case-22 | pass→pass | 7,574 | 3,555 | -53% | 1 | 1 | 0% | 1,187 | 1,617 | +36% | 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 +18 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.