Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate a structured tax planning checklist and review framework for any individual or business context. Use when asked to review tax planning, prepare for year-end tax, check tax efficiency, or identify tax-saving opportunities. Produces a checklist of considerations, common reliefs, and a review framework. Not a substitute for qualified tax advice.
.claude/skills/mohitagw15856-tax-planning-checklist/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 61% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 27% | 0% |
Produces a structured tax planning review framework — identifying common reliefs, year-end planning opportunities, and potential gaps. Always recommend a qualified tax adviser for implementation.
WARNING: Tax law changes frequently and varies by jurisdiction. This checklist produces a framework for discussion, not tax advice. Always verify with a qualified accountant or tax adviser before taking action.
Ask the user for these if not provided:
Jurisdiction: UK / US / Other] Entity type: Individual / Limited company / etc.] Key thresholds to note: List relevant tax-year thresholds — e.g. personal allowance, basic rate band, VAT threshold]
Based on the above, prioritise these before year-end:
| Action | Potential saving | Deadline | Adviser needed? | |---|---|---|---| | Action] | £ estimate or "significant"] | Date] | Yes / No |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 30,448 | 33,499 | +10% | 1 | 1 | 0% | 5,341 | 5,401 | +1% | 0 | 0 | — |
case-02 | fail→pass | 32,607 | 23,077 | -29% | 1 | 1 | 0% | 3,910 | 4,823 | +23% | 0 | 0 | — |
case-03 | fail→pass | 38,517 | 28,346 | -26% | 1 | 1 | 0% | 5,767 | 5,118 | -11% | 0 | 0 | — |
case-04 | pass→fail | 18,869 | 23,921 | +27% | 1 | 1 | 0% | 2,179 | 5,831 | +168% | 0 | 0 | — |
case-05 | fail→fail | 27,213 | 31,197 | +15% | 1 | 1 | 0% | 3,697 | 4,972 | +34% | 0 | 0 | — |
case-06 | pass→fail | 21,129 | 24,734 | +17% | 1 | 1 | 0% | 2,540 | 3,753 | +48% | 0 | 0 | — |
case-07 | fail→fail | 26,826 | 16,511 | -38% | 1 | 1 | 0% | 2,187 | 2,502 | +14% | 0 | 0 | — |
case-08 | fail→fail | 24,901 | 22,429 | -10% | 1 | 1 | 0% | 3,262 | 4,670 | +43% | 0 | 0 | — |
case-09 | pass→pass | 24,784 | 28,533 | +15% | 1 | 1 | 0% | 3,162 | 4,754 | +50% | 0 | 0 | — |
case-10 | fail→pass | 27,451 | 16,141 | -41% | 1 | 1 | 0% | 2,241 | 3,599 | +61% | 0 | 0 | — |
case-11 | pass→pass | 22,932 | 24,689 | +8% | 1 | 1 | 0% | 3,291 | 4,401 | +34% | 0 | 0 | — |
case-12 | pass→fail | 18,523 | 14,095 | -24% | 1 | 1 | 0% | 2,206 | 3,310 | +50% | 0 | 0 | — |
case-13 | fail→pass | 22,839 | 22,261 | -3% | 1 | 1 | 0% | 2,906 | 3,695 | +27% | 0 | 0 | — |
case-14 | fail→pass | 18,907 | 21,258 | +12% | 1 | 1 | 0% | 1,961 | 3,454 | +76% | 0 | 0 | — |
case-15 | fail→pass | 29,989 | 32,221 | +7% | 1 | 1 | 0% | 3,454 | 5,175 | +50% | 0 | 0 | — |
case-16 | fail→pass | 26,351 | 19,136 | -27% | 1 | 1 | 0% | 3,044 | 3,657 | +20% | 0 | 0 | — |
case-17 | pass→pass | 19,022 | 20,496 | +8% | 1 | 1 | 0% | 2,328 | 3,916 | +68% | 0 | 0 | — |
case-18 | fail→fail | 23,816 | 20,204 | -15% | 1 | 1 | 0% | 2,401 | 3,752 | +56% | 0 | 0 | — |
case-19 | fail→pass | 25,631 | 21,590 | -16% | 1 | 1 | 0% | 3,296 | 3,911 | +19% | 0 | 0 | — |
case-20 | pass→pass | 36,516 | 21,698 | -41% | 1 | 1 | 0% | 2,698 | 3,946 | +46% | 0 | 0 | — |
case-21 | pass→pass | 26,524 | 14,476 | -45% | 1 | 1 | 0% | 3,483 | 3,768 | +8% | 0 | 0 | — |
case-22 | fail→fail | 27,608 | 25,856 | -6% | 1 | 1 | 0% | 3,519 | 4,581 | +30% | 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 +27 percentage points is the difference between those two pass rates over the 22 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.