Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Get journaling prompts tuned to what you're actually working through — a decision, a rough patch, a goal, or just building the habit — not generic 'how was your day'. Use when asked for journaling prompts, help me start journaling, writing prompts for [situation], or what should I journal about. Produces a small set of prompts matched to your intent, a simple format and cadence that fits your time, a starter for total beginners, and a gentle note on going deeper vs. when a topic is better taken
.claude/skills/mohitagw15856-journaling-prompts/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -4% | 0% |
Blank-page journaling stalls fast. This gives you a focused, small set of prompts aimed at what you're actually here for — untangling a decision, processing something hard, chasing a goal, or just starting the habit — with a format light enough that you'll come back tomorrow.
Ask for these if not provided:
Format: when/how long/structured vs free].
Prompts
If you're just starting: one tiny prompt + 3 lines]. Go deeper (optional): follow-up questions].
> Journaling is a great reflection tool. If you're dealing with heavy or ongoing distress, consider talking to a professional — this isn't a substitute for support.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 15,990 | 13,108 | -18% | 1 | 1 | 0% | 1,824 | 2,158 | +18% | 0 | 0 | — |
case-02 | fail→pass | 20,190 | 13,660 | -32% | 1 | 1 | 0% | 1,809 | 2,237 | +24% | 0 | 0 | — |
case-03 | fail→pass | 18,506 | 13,010 | -30% | 1 | 1 | 0% | 1,956 | 2,116 | +8% | 0 | 0 | — |
case-04 | fail→pass | 19,187 | 15,415 | -20% | 1 | 1 | 0% | 1,844 | 2,067 | +12% | 0 | 0 | — |
case-05 | fail→pass | 24,869 | 15,889 | -36% | 1 | 1 | 0% | 2,481 | 2,379 | -4% | 0 | 0 | — |
case-06 | fail→pass | 19,235 | 17,855 | -7% | 1 | 1 | 0% | 2,161 | 2,438 | +13% | 0 | 0 | — |
case-07 | fail→pass | 21,606 | 11,159 | -48% | 1 | 1 | 0% | 2,253 | 2,371 | +5% | 0 | 0 | — |
case-08 | fail→pass | 18,669 | 17,014 | -9% | 1 | 1 | 0% | 1,899 | 2,225 | +17% | 0 | 0 | — |
case-09 | fail→pass | 19,501 | 13,231 | -32% | 1 | 1 | 0% | 1,837 | 2,155 | +17% | 0 | 0 | — |
case-10 | pass→pass | 18,200 | 6,855 | -62% | 1 | 1 | 0% | 1,456 | 1,974 | +36% | 0 | 0 | — |
case-11 | fail→pass | 21,432 | 14,074 | -34% | 1 | 1 | 0% | 2,120 | 2,035 | -4% | 0 | 0 | — |
case-12 | fail→pass | 12,902 | 16,241 | +26% | 1 | 1 | 0% | 1,639 | 2,148 | +31% | 0 | 0 | — |
case-13 | fail→pass | 16,511 | 13,616 | -18% | 1 | 1 | 0% | 1,578 | 1,974 | +25% | 0 | 0 | — |
case-14 | fail→pass | 20,729 | 15,055 | -27% | 1 | 1 | 0% | 1,965 | 2,085 | +6% | 0 | 0 | — |
case-15 | fail→pass | 15,468 | 15,079 | -3% | 1 | 1 | 0% | 1,701 | 2,174 | +28% | 0 | 0 | — |
case-16 | fail→pass | 18,381 | 14,227 | -23% | 1 | 1 | 0% | 1,905 | 2,099 | +10% | 0 | 0 | — |
case-17 | pass→pass | 17,029 | 13,308 | -22% | 1 | 1 | 0% | 1,808 | 2,003 | +11% | 0 | 0 | — |
case-18 | fail→pass | 17,261 | 14,079 | -18% | 1 | 1 | 0% | 1,795 | 2,275 | +27% | 0 | 0 | — |
case-19 | fail→fail | 12,873 | 12,908 | +0% | 1 | 1 | 0% | 1,258 | 1,804 | +43% | 0 | 0 | — |
case-20 | pass→pass | 43,986 | 33,370 | -24% | 1 | 1 | 0% | 8,220 | 4,636 | -44% | 0 | 0 | — |
case-21 | pass→pass | 21,717 | 14,938 | -31% | 1 | 1 | 0% | 2,456 | 2,049 | -17% | 0 | 0 | — |
case-22 | pass→pass | 32,732 | 22,781 | -30% | 1 | 1 | 0% | 3,536 | 4,060 | +15% | 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 +73 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.