Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →法人成り（個人事業主から法人への移行）に関する相談。税額比較シミュレーション、 法人形態の選択、設立手続き、役員報酬戦略、社会保険の比較を支援する。 Trigger: "法人成り", "会社設立", "法人化", "株式会社にしたい", "合同会社", "法人税と所得税の比較", "役員報酬", "法人成りのタイミング", "マイクロ法人", "1人法人"
.claude/skills/kazukinagata-incorporation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-05 | ✓→✗ | ▼ Worse | -47% | 0% |
| case-06 | ✓→✗ | ▼ Worse | -46% | 0% |
個人事業主から法人への移行（法人成り）に関する包括的な知識ベース。 税額比較シミュレーション、法人形態の選択、設立手続き、役員報酬戦略を支援する。
shinkoku.config.yaml を Read ツールで読み込む/setup スキルの実行を案内して終了するdb_path: MCP ツールの db_path 引数に使用output_dir: 進捗ファイル等の出力先ベースディレクトリ以下の構造で回答を組み立てる:
質問の内容に応じて、以下のリファレンスファイルを参照する:
| 質問カテゴリ | 参照ファイル | |-------------|-------------| | 個人 vs 法人の税額比較・損益分岐 | references/tax-simulation.md | | 株式会社 vs 合同会社・設立手続き | references/corporate-forms.md | | 役員報酬の設定・社会保険戦略 | references/compensation-strategy.md |
| 関連スキル | 用途 | 参照タイミング | |-----------|------|-------------| | tax-advisor | 所得税の税率・控除の詳細、ライフプランニング | 法人成り前の個人税額計算、iDeCo・小規模企業共済との比較 | | invoice-system | インボイス制度・消費税の経過措置 | 法人成り時のインボイス登録移行、2割特例の適用判定 | | consumption-tax | 消費税の計算方法・簡易課税 | 法人の消費税負担のシミュレーション |
すべての回答の末尾に以下の免責事項を付記する:
---
この回答は一般的な税務情報の提供を目的としたものであり、個別の税務アドバイスではありません。
法人成りは税務・法務・社会保険等の多面的な判断が必要です。
具体的な意思決定にあたっては、税理士・司法書士等の専門家にご相談ください。
情報は令和7年分（2025年課税年度）の税制に基づいています。| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | pass→fail | 16,695 | 6,748 | -60% | 1 | 1 | 0% | 2,951 | 1,575 | -47% | 0 | 0 | — |
case-06 | pass→fail | 17,907 | 4,974 | -72% | 1 | 1 | 0% | 2,895 | 1,565 | -46% | 0 | 0 | — |
case-01 | fail→fail | 23,101 | 7,028 | -70% | 1 | 1 | 0% | 3,915 | 1,795 | -54% | 0 | 0 | — |
case-02 | fail→fail | 19,184 | 5,502 | -71% | 1 | 1 | 0% | 2,853 | 1,624 | -43% | 0 | 0 | — |
case-03 | fail→fail | 20,491 | 5,585 | -73% | 1 | 1 | 0% | 3,221 | 1,540 | -52% | 0 | 0 | — |
case-04 | pass→fail | 16,307 | 6,163 | -62% | 1 | 1 | 0% | 2,826 | 1,689 | -40% | 0 | 0 | — |
case-07 | fail→pass | 11,400 | 10,272 | -10% | 1 | 1 | 0% | 1,885 | 2,852 | +51% | 0 | 0 | — |
case-08 | fail→fail | 19,165 | 6,650 | -65% | 1 | 1 | 0% | 3,134 | 1,764 | -44% | 0 | 0 | — |
case-09 | fail→fail | 25,717 | 5,584 | -78% | 1 | 1 | 0% | 4,089 | 1,509 | -63% | 0 | 0 | — |
case-10 | fail→fail | 21,859 | 6,726 | -69% | 1 | 1 | 0% | 3,412 | 1,585 | -54% | 0 | 0 | — |
case-11 | fail→fail | 20,785 | 8,915 | -57% | 1 | 1 | 0% | 3,491 | 1,620 | -54% | 0 | 0 | — |
case-12 | pass→fail | 16,157 | 5,332 | -67% | 1 | 1 | 0% | 2,492 | 1,504 | -40% | 0 | 0 | — |
case-13 | fail→fail | 18,216 | 16,284 | -11% | 1 | 1 | 0% | 3,088 | 1,510 | -51% | 0 | 0 | — |
case-14 | fail→pass | 11,600 | 4,602 | -60% | 1 | 1 | 0% | 2,029 | 1,992 | -2% | 0 | 0 | — |
case-15 | pass→fail | 16,555 | 4,251 | -74% | 1 | 1 | 0% | 2,663 | 1,504 | -44% | 0 | 0 | — |
case-16 | pass→pass | 15,086 | 6,987 | -54% | 1 | 1 | 0% | 2,290 | 2,357 | +3% | 0 | 0 | — |
case-17 | pass→pass | 15,651 | 10,316 | -34% | 1 | 1 | 0% | 2,297 | 3,072 | +34% | 0 | 0 | — |
case-18 | fail→fail | 17,679 | 6,457 | -63% | 1 | 1 | 0% | 2,811 | 1,665 | -41% | 0 | 0 | — |
case-19 | fail→fail | 18,321 | 5,290 | -71% | 1 | 1 | 0% | 3,140 | 1,434 | -54% | 0 | 0 | — |
case-20 | fail→pass | 9,103 | 2,232 | -75% | 1 | 1 | 0% | 1,305 | 1,683 | +29% | 0 | 0 | — |
case-21 | fail→fail | 12,964 | 5,510 | -57% | 1 | 1 | 0% | 2,345 | 1,552 | -34% | 0 | 0 | — |
case-22 | fail→fail | 19,624 | 4,043 | -79% | 1 | 1 | 0% | 3,212 | 1,449 | -55% | 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, and 5 counted toward the lift figure. The other 17 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of -9 percentage points is the difference between those two pass rates over the 5 comparable cases. 9 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.