Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Background context for invoice-system input tax credit rules (仕入税額控除) in the shinkoku tax filing plugin. Contains eligibility requirements, the 6 permanent exceptions (帳簿のみ保存の恒久特例), transitional measures for purchases from tax-exempt businesses, and storage requirements. This skill is not user-invocable — Claude loads it automatically when responding to input tax credit questions under the invoice system.
.claude/skills/kazukinagata-tax-invoice-credit-context/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✓→✓ | = Same ✓ | -27% | 0% |
| case-05 | ✓→✓ | = Same ✓ | -26% | 0% |
| case-06 | ✓→✓ | = Same ✓ | -31% | 0% |
| case-07 | ✓→✓ | = Same ✓ | -31% | 0% |
| case-09 | ✓→✓ | = Same ✓ | -12% | 0% |
このスキルはインボイス制度における仕入税額控除の要件・例外に関するコンテキストを提供する。
仕入税額控除に関する回答を行う際は、references/input-tax-credit-rules.md を読み込んで以下を実行する:
| ファイル | 内容 | |---------|------| | references/input-tax-credit-rules.md | 仕入税額控除の原則・帳簿記載要件・恒久特例6類型・経過措置・課税売上割合と控除方式 |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 35,447 | 14,701 | -59% | 1 | 1 | 0% | 3,237 | 3,206 | -1% | 0 | 0 | — |
case-02 | fail→fail | 21,976 | 16,858 | -23% | 1 | 1 | 0% | 4,015 | 3,097 | -23% | 0 | 0 | — |
case-03 | fail→fail | 25,165 | 18,797 | -25% | 1 | 1 | 0% | 4,141 | 3,599 | -13% | 0 | 0 | — |
case-04 | pass→pass | 13,608 | 8,631 | -37% | 1 | 1 | 0% | 2,426 | 1,772 | -27% | 0 | 0 | — |
case-05 | pass→pass | 14,440 | 9,355 | -35% | 1 | 1 | 0% | 2,571 | 1,896 | -26% | 0 | 0 | — |
case-06 | pass→pass | 17,641 | 9,466 | -46% | 1 | 1 | 0% | 2,932 | 2,025 | -31% | 0 | 0 | — |
case-07 | pass→pass | 12,940 | 7,330 | -43% | 1 | 1 | 0% | 2,234 | 1,538 | -31% | 0 | 0 | — |
case-08 | fail→fail | 12,799 | 8,268 | -35% | 1 | 1 | 0% | 2,330 | 1,638 | -30% | 0 | 0 | — |
case-09 | pass→pass | 19,776 | 13,657 | -31% | 1 | 1 | 0% | 3,220 | 2,819 | -12% | 0 | 0 | — |
case-10 | pass→pass | 17,287 | 14,778 | -15% | 1 | 1 | 0% | 3,054 | 2,919 | -4% | 0 | 0 | — |
case-11 | pass→pass | 12,944 | 13,451 | +4% | 1 | 1 | 0% | 2,304 | 2,648 | +15% | 0 | 0 | — |
case-12 | pass→pass | 19,454 | 7,614 | -61% | 1 | 1 | 0% | 3,067 | 1,667 | -46% | 0 | 0 | — |
case-13 | pass→pass | 14,144 | 12,696 | -10% | 1 | 1 | 0% | 2,452 | 2,475 | +1% | 0 | 0 | — |
case-14 | pass→pass | 11,918 | 12,197 | +2% | 1 | 1 | 0% | 2,427 | 2,695 | +11% | 0 | 0 | — |
case-15 | pass→pass | 14,461 | 10,966 | -24% | 1 | 1 | 0% | 2,507 | 2,126 | -15% | 0 | 0 | — |
case-16 | pass→pass | 12,867 | 9,992 | -22% | 1 | 1 | 0% | 2,341 | 2,220 | -5% | 0 | 0 | — |
case-17 | pass→pass | 16,933 | 11,736 | -31% | 1 | 1 | 0% | 3,148 | 2,277 | -28% | 0 | 0 | — |
case-18 | pass→pass | 30,608 | 9,451 | -69% | 1 | 1 | 0% | 5,158 | 1,839 | -64% | 0 | 0 | — |
case-19 | fail→fail | 9,507 | 5,815 | -39% | 1 | 1 | 0% | 1,844 | 1,389 | -25% | 0 | 0 | — |
case-20 | pass→pass | 15,270 | 14,218 | -7% | 1 | 1 | 0% | 2,697 | 2,816 | +4% | 0 | 0 | — |
case-21 | pass→pass | 17,193 | 12,810 | -25% | 1 | 1 | 0% | 2,948 | 2,445 | -17% | 0 | 0 | — |
case-22 | pass→pass | 10,131 | 6,205 | -39% | 1 | 1 | 0% | 1,891 | 1,288 | -32% | 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 0 percentage points is the difference between those two pass rates over the 22 comparable cases.
Other measured skills in the registry, with their headline benchmark lift.