Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Reverse weekly review for turning inbox noise, daily plans, diaries, calendars, annual plans, and long-range life plans into one happiness-and-peace-centered weekly plan. Use when the user asks for 週檢視, 反向週計劃, 8 Big Rocks, Inbox Zero weekly review, 幸福寧靜週, or wants to synthesize Todoist/inbox notes, daily diaries, calendars, yearly plans, and life plans into iMandalArt/FIRE/JSON outputs.
.claude/skills/twhsi-weekly-reverse-review/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 88% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 28% | 0% |
Turn one week of evidence into the next week's meaningful plan by asking:
Is this making me prove myself, or bringing real happiness and peace?
This skill is a reverse planning skill. It does not start by adding tasks. It first gathers evidence from life, removes noise, checks long-range meaning, then produces a compact weekly plan.
Use the center phrase 幸福寧靜週 unless the user gives another five-Han-character center.
Default final question:
那件事情能帶來真正的幸福與寧靜？
Default operating sentence:
少說，陪伴，慢慢做。
Gather only the sources available in the user request or local context:
When source files are present, read them before synthesizing.
Use these skills when available and relevant:
fire-analysis-card: semantic analysis, numbering, index, route, evolution.imandalart: final 2.01 hard-line weekly 3x3 card.todays-daily-plan: daily plan and diary extraction.markdown-nine-grid-clipboard: Markdown table version of the weekly card.project-note-json-to-epub: publishing-ready project-note JSON when weekly reviews become manuscript material.person / theme / next step cards.references/output-json-schema.md.When generating iMandalArt weekly plans, use the user's weekly-domain layout, not the default process layout:
textⒻ內在 Ⓒ財流 Ⓖ學習 ... ... Ⓑ工作 ◎◎◎◎◎ Ⓓ家庭 ... 幸福寧靜週 ... ... ◎◎◎◎◎ ... Ⓔ社群 Ⓐ健康 Ⓗ休閒 ... ...
Read references/weekly-eight-domain-layout.md for the full mapping and phrase guidance.
Before finalizing, ask internally:
Read references/reverse-review-questions.md when the review needs deeper diagnosis.
For a normal weekly review, return:
Do not over-explain unless the user asks for a full analysis.
待證, 推論, or 需補.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 17,100 | 24,521 | +43% | 1 | 1 | 0% | 2,505 | 3,405 | +36% | 0 | 0 | — |
case-02 | fail→pass | 13,213 | 15,563 | +18% | 1 | 1 | 0% | 1,842 | 3,470 | +88% | 0 | 0 | — |
case-03 | pass→pass | 15,682 | 9,397 | -40% | 1 | 1 | 0% | 2,239 | 2,575 | +15% | 0 | 0 | — |
case-04 | fail→pass | 11,559 | 8,801 | -24% | 1 | 1 | 0% | 1,684 | 2,449 | +45% | 0 | 0 | — |
case-14 | pass→pass | 16,500 | 13,191 | -20% | 1 | 1 | 0% | 3,415 | 3,688 | +8% | 0 | 0 | — |
case-05 | pass→pass | 13,095 | 7,397 | -44% | 1 | 1 | 0% | 1,919 | 2,218 | +16% | 0 | 0 | — |
case-06 | fail→pass | 8,880 | 2,908 | -67% | 1 | 1 | 0% | 1,177 | 1,466 | +25% | 0 | 0 | — |
case-07 | pass→pass | 17,285 | 12,331 | -29% | 1 | 1 | 0% | 2,534 | 2,900 | +14% | 0 | 0 | — |
case-08 | pass→pass | 15,096 | 11,448 | -24% | 1 | 1 | 0% | 2,348 | 2,767 | +18% | 0 | 0 | — |
case-15 | fail→pass | 12,356 | 6,399 | -48% | 1 | 1 | 0% | 1,644 | 2,098 | +28% | 0 | 0 | — |
case-09 | fail→pass | 15,951 | 2,942 | -82% | 1 | 1 | 0% | 2,363 | 1,579 | -33% | 0 | 0 | — |
case-10 | fail→pass | 16,619 | 2,824 | -83% | 1 | 1 | 0% | 1,569 | 1,592 | +1% | 0 | 0 | — |
case-11 | fail→pass | 7,021 | 1,875 | -73% | 1 | 1 | 0% | 1,168 | 1,391 | +19% | 0 | 0 | — |
case-12 | pass→pass | 14,444 | 9,430 | -35% | 1 | 1 | 0% | 2,752 | 2,818 | +2% | 0 | 0 | — |
case-13 | pass→pass | 17,758 | 15,229 | -14% | 1 | 1 | 0% | 2,765 | 3,366 | +22% | 0 | 0 | — |
case-16 | pass→pass | 13,633 | 12,471 | -9% | 1 | 1 | 0% | 2,042 | 2,875 | +41% | 0 | 0 | — |
case-17 | fail→pass | 11,062 | 1,828 | -83% | 1 | 1 | 0% | 1,617 | 1,350 | -17% | 0 | 0 | — |
case-18 | fail→pass | 7,198 | 2,577 | -64% | 1 | 1 | 0% | 1,084 | 1,509 | +39% | 0 | 0 | — |
case-19 | fail→pass | 14,005 | 11,481 | -18% | 1 | 1 | 0% | 2,129 | 2,923 | +37% | 0 | 0 | — |
case-20 | pass→pass | 9,589 | 8,661 | -10% | 1 | 1 | 0% | 1,401 | 2,306 | +65% | 0 | 0 | — |
case-21 | pass→pass | 11,841 | 7,136 | -40% | 1 | 1 | 0% | 1,637 | 2,181 | +33% | 0 | 0 | — |
case-22 | pass→pass | 11,706 | 6,697 | -43% | 1 | 1 | 0% | 1,636 | 2,022 | +24% | 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 +50 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.