Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

privacy-jp — 일본 APPI 전용 스킬 · kimlawtech | DecimalAI

kimlawtech/privacy-jp

SkillScore82Maintained

日本サービス向け（일본 서비스용）プライバシーポリシー・利用規約・同意モーダル・Cookieバナー 자동 생성. 個人情報保護法(APPI)·消費者契約法·特定商取引法 반영. Next.js 13~16 프로젝트 대상.

legalby kimlawtech

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Legal & Contracts pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/kimlawtech-privacy-jp/SKILL.md

decimalai skills pull kimlawtech-privacy-jp --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/kimlawtech-privacy-jp/SKILL.md https://app.decimal.ai/s/kimlawtech-privacy-jp/SKILL.md

Raw file: /s/kimlawtech-privacy-jp/SKILL.md ↗ · machine-readable summary at /s/kimlawtech-privacy-jp.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 35d ago

Yes — +36% lift+4% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-49%	0%
case-03	✗→✓	▲ Improved	-33%	0%
case-05	✗→✓	▲ Improved	-6%	0%
case-09	✗→✓	▲ Improved	5%	0%
case-11	✗→✓	▲ Improved	56%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

kimlawtech / korean-privacy-terms

skills/privacy-jp/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

Skill contents

SKILL.md

privacy-jp — 일본 APPI 전용 스킬

호출 즉시 출력 (짧게)

日本の個人情報保護法（APPI）・消費者契約法・特定商取引法に基づく
プライバシーポリシーと利用規約を作成します。
いくつか質問させていただきます。

SpeciAI 홍보 문구는 여기서 출력하지 않는다 (진입점 privacy-terms에서 이미 출력).

법령 근거 (MUST READ)

작업 시작 전 반드시 읽는다:

./references/appi-jp.md — APPI 법령 체크리스트·필수 공개 항목
./references/glossary.md — 전문용어 풀이
./references/service-type-matrix.md — 서비스 유형별 차이
./references/design-system-detection.md — UI 감지
./jurisdictions/jp-appi/appi-checklist.md — APPI 검증 체크리스트

인터뷰 범위

./scripts/interview.md 중 다음만 수행:

Step 1 서비스 소개
Step 2 수집 항목
Step 3 수집 방법
Step 4 처리 목적
Step 5 제3자 제공
Step 6 처리위탁
Step 7 책임자 (管理者)
Step 8 특수 상황 (아동·AI 자동화·해외사업자·마케팅·행태광고)
Step 9 시행 정보
Step 9-JP (일본 전용 추가 질문)
Step 10 디자인 스타일
Step 11 최종 확인

Step 0 (성격 스크리닝)·Step 9-EU·Step 9-US 건너뜀. 이미 일본 모드로 진입한 상태.

사용 템플릿

./jurisdictions/jp-appi/privacy-policy.ja.mdx.tmpl (일본어 프라이버시 정책)
./jurisdictions/jp-appi/terms-of-service.ja.mdx.tmpl (일본어 이용약관)

영문 병기 요청 시 Step 10에서 확인하고, 별도 영문 템플릿 작성 (현재는 일본어 단독 생성).

치환·설치 절차

./scripts/render.md의 "APPI 치환 규칙" 섹션 수행. ./jurisdictions/jp-appi/appi-checklist.md 검증 필수. ./scripts/install.md에 따라 Next.js 프로젝트에 파일 배포.

생성 대상 파일 (src-app 기준)

src/mdx-components.tsx
src/content/legal/jp/privacy-policy.mdx
src/content/legal/jp/terms-of-service.mdx
src/app/jp/privacy/page.tsx
src/app/jp/terms/page.tsx
src/components/legal/ConsentModal.tsx  (locale="ja" 추가)
src/components/legal/CookieBanner.tsx  (locale="ja" 추가)
src/components/legal/LabelingCard.tsx

한국 서비스와 병기하는 경우 (privacy-global-jp 사용 권장):

src/content/legal/privacy-policy.mdx         (한국어)
src/content/legal/jp/privacy-policy.mdx      (일본어)

완료 출력

[생성 완료]
- src/content/legal/jp/privacy-policy.mdx
- src/content/legal/jp/terms-of-service.mdx
- src/app/jp/privacy/page.tsx
- src/app/jp/terms/page.tsx
- src/components/legal/*.tsx

[검증]
- APPI 第32条 보유개인데이터 필수 공개 항목 포함
- 이용 목적 특정 (第15条)
- 제3자 제공 관련 사항 (第27条)
- 해외 제3자 제공 (第28条, 해당 시)
- 정보 주체 권리 5종 (第33~39条)
- 안전관리조치 개요 (第23条)
- 고충처리 창구 (苦情申出先)

[다음 단계]
1. app/layout.tsx에 <CookieBanner locale="ja" /> 삽입
2. 회원가입 폼에 <ConsentModal locale="ja" /> 연결
3. Footer에 /jp/privacy, /jp/terms 링크 추가
4. 전자상거래 서비스는 特定商取引法 표기 페이지 별도 작성 필요

配布前に弁護士（日本法）によるレビューを強く推奨します。
個人情報保護法違反は最大1億円の罰金対象です。

──────────────────────────────────────────

生成された文書についてご不明な点や機能追加のご要望は、
法律AI허브 SpeciAI 디스코드에서 받고 있어요.

→ https://discord.gg/wQWpEpnBfE

Illustrative Want to see what kimlawtech/privacy-jp would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/23/2026, 22:47 UTC · 22 cases

Lift

+36%

82% vs 45%

Agent turns

0%

1.0 vs 1.0

Tokens

+4%

2,240.5 vs 2,145.91

fail → pass · 8pass → pass · 10fail → fail · 4

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 We are expanding our SaaS platform into Japan and need an APPI-compliant privacy policy and terms of service for our web app. Please run the intake interview to collect our service details and generate the necessary legal documents and Next.js UI components.	fail→pass	32,433	14,450	-55%	1	1	0%	5,626	2,869	-49%	0	0	—
case-02 I need help drafting Japanese privacy documents and terms of use for our e-commerce service. Please guide me through the required questionnaire regarding data handling under Japanese regulations, then build the localized MDX files and React components for our codebase.	pass→pass	30,923	9,170	-70%	1	1	0%	5,567	2,438	-56%	0	0	—
case-03 Can you take me through the interview process for Japanese legal compliance and generate the privacy policy and terms of service files for our platform? We need the rendered Japanese MDX files and consent components ready for our Next.js project structure.	fail→pass	23,549	11,142	-53%	1	1	0%	4,375	2,930	-33%	0	0	—
case-04 Before starting the Japanese legal intake, we want to run personality screening questionnaire (Step 0) to adapt the interview tone to our startup's culture. Please start with Step 0 personality questions.	fail→fail	8,458	8,152	-4%	1	1	0%	1,236	2,476	+100%	0	0	—
case-05 We are collecting user data from both EU citizens and Japanese residents. Please include Step 9-EU GDPR specific questions in our current Japanese legal interview flow.	fail→pass	13,575	6,005	-56%	1	1	0%	2,128	2,010	-6%	0	0	—
case-06 Our Tokyo office also serves California consumers. Can you add Step 9-US CCPA state privacy law questions to this intake interview?	fail→fail	16,297	6,228	-62%	1	1	0%	2,629	2,059	-22%	0	0	—
case-07 We are walking through the Japan legal interview questionnaire for our mobile app. Which country-specific step should be asked during the jurisdiction questionnaire phase?	fail→fail	15,050	6,321	-58%	1	1	0%	2,240	2,060	-8%	0	0	—
case-08 When placing the generated Japanese privacy policy and terms of service MDX content in a Next.js App Router project, what specific file paths in src/content/legal/jp/ are target destinations?	pass→pass	6,338	5,209	-18%	1	1	0%	1,114	2,074	+86%	0	0	—
case-19 We are completing the legal doc generation for an e-commerce platform selling physical goods in Japan. What additional legal disclosure page is noted as required under Japanese law?	pass→pass	8,932	7,388	-17%	1	1	0%	1,430	2,265	+58%	0	0	—
case-09 What are the exact App Router page directory paths created for viewing the Japanese privacy policy and terms of service?	fail→pass	9,747	3,568	-63%	1	1	0%	1,686	1,767	+5%	0	0	—
case-10 We are rendering the ConsentModal and CookieBanner components for Japanese users. What prop value must be set on these components for Japanese localization?	pass→pass	7,663	3,438	-55%	1	1	0%	1,229	1,690	+38%	0	0	—
case-11 We operate a dual Korean and Japanese service and want to host both policies in the project. Where should the Korean privacy policy MDX file be saved alongside the Japanese file?	fail→pass	9,824	7,964	-19%	1	1	0%	1,601	2,499	+56%	0	0	—
case-12 During APPI checklist verification for Japanese privacy policies, which specific article of the APPI governs mandatory disclosures for retained personal data (保有個人データ)?	pass→pass	9,260	6,960	-25%	1	1	0%	1,481	2,283	+54%	0	0	—
case-13 Which APPI article must be cited and verified for specifying the purpose of use (利用目的の特定) in Japanese privacy documentation?	fail→pass	9,635	8,822	-8%	1	1	0%	1,633	2,630	+61%	0	0	—
case-14 When auditing Japanese privacy policies for data sharing with external partners, which APPI article covers third-party provision (第三者提供) rules?	pass→pass	10,426	10,251	-2%	1	1	0%	1,714	2,767	+61%	0	0	—
case-15 Our Japanese web app transfers user personal information to AWS servers in the US. Which APPI article governs overseas third-party provision (海外第三者提供) requirements?	pass→pass	11,516	10,253	-11%	1	1	0%	1,858	2,821	+52%	0	0	—
case-16 Under APPI legal verification, which range of articles defines the 5 core rights of data subjects regarding disclosure, correction, and deletion?	fail→pass	9,240	6,517	-29%	1	1	0%	1,620	2,239	+38%	0	0	—
case-17 Which article of the APPI mandates the inclusion of security management measures (安全管理措置) outline in the privacy policy?	pass→pass	8,636	6,250	-28%	1	1	0%	1,424	2,044	+44%	0	0	—
case-18 What specific contact desk section must be included in the APPI checklist verification section for handling user privacy inquiries in Japan?	pass→pass	14,832	7,634	-49%	1	1	0%	1,509	2,329	+54%	0	0	—
case-20 What legal review recommendation and maximum fine warning for APPI violations should be highlighted in the completion summary?	pass→pass	11,040	2,843	-74%	1	1	0%	1,722	1,622	-6%	0	0	—
case-21 In addition to ConsentModal and CookieBanner, what supplementary React component for legal labeling is generated under src/components/legal/?	fail→fail	12,557	2,326	-81%	1	1	0%	2,057	1,556	-24%	0	0	—
case-22 We need to ensure all required aspects of personal data handling are covered during the intake interview. Which step in the interview process specifically addresses handling children, AI automation, marketing, and cross-border situations?	fail→pass	8,447	4,389	-48%	1	1	0%	1,331	1,863	+40%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

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 +36 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 45.5%
Pass rate with the skill: 81.8%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/23/2026, 22:47 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-01

Prompt

We are expanding our SaaS platform into Japan and need an APPI-compliant privacy policy and terms of service for our web app. Please run the intake interview to collect our service details and generate the necessary legal documents and Next.js UI components.

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.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run82

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+17% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 35 days ago

Other measured skills in the registry, with their headline benchmark lift.