kr-patent-embodiment-addition

kr-patent-embodiment-addition is a skill for Claude Code, Codex from lsj4232/KR_PATENT_SKILL. It costs 382 tokens per session (6,251 once invoked), scanned A, original, MIT.

A skill for adding alternative implementation examples to the detailed description section of a Korean patent specification. It covers variations in algorithms, data, models, timing, user interaction, deployment, visualisation, and other technical areas.

In plain words
What is it for?
Use it to expand the detailed-implementation section with structured alternative embodiments across the listed technical categories, without editing existing patent claims.
Why use it?
It helps describe possible technical variations so the specification is not limited to one implementation. It leaves the claims section unchanged and treats the additions as possible future dependent-claim material.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to expand the detailed-implementation section with structured alternative embodiments across the listed technical categories, without editing existing patent claims.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lsj4232/kr_patent_skill/kr-patent-embodiment-addition
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add lsj4232/KR_PATENT_SKILL --skill kr-patent-embodiment-addition
Clone the repo
git clone --depth 1 https://github.com/lsj4232/KR_PATENT_SKILL

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for kr-patent-embodiment-addition

README.md
[![agentmods](https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-embodiment-addition/github.svg)](https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-embodiment-addition)
Your own site
<a href="https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-embodiment-addition"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-embodiment-addition/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for kr-patent-embodiment-addition

Your own site · 80×15
<a href="https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-embodiment-addition"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-embodiment-addition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 382 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,251 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00382 $0.06251
Opus 5 $0.00191 $0.03125
Sonnet 5 $0.00076 $0.01250
Haiku 4.5 $0.00038 $0.00625

Measured 11d ago against content hash f6aaeeb185eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

kr-patent-embodiment-addition scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

kr-patent-embodiment-addition/SKILL.md · 315 lines

How it starts

The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.

특허 명세서 실시예 추가 스킬

0. 핵심 사상

주요 실시예 외에 다양한 변형 실시예를 부가함으로써, 경쟁사가 기술적 우회로를 만들거나 미래 기술이 출현하더라도 권리 범위 안에 포함되도록 권리의 외연을 확장한다. 각 변형 실시예는 잠재적 종속청구항의 후보가 될 수 있는 형태로 기술되어야 한다.

본 스킬은 [kr-patent-definition-insertion]과 짝을 이루며, 보통 정의 삽입 → 실시예 추가 순으로 작업한다.

⛔ 절대 금지 — 청구범위 섹션 비수정 원칙

본 스킬은 명세서 본문(특히 "발명을 실시하기 위한 구체적인 내용" 절)에만 변형 실시예 단락을 부가한다. 【청구범위】 섹션 — 즉 【청구항 1】~【청구항 N】 자체 — 은 절대 수정하지 않는다.

  • 변형 실시예가 잠재적 종속청구항의 "후보"가 되도록 기술하되, 청구범위 섹션에 실제로 새 청구항을 추가하거나 기존 청구항을 수정하지 않는다.
  • 종속청구항화 여부는 추후 분할출원·계속출원·보정 단계에서 변리사가 별도로 판단할 영역이며, 본 스킬의 범위 밖이다.
  • 사용자가 "이 변형도 청구항에 넣어줘"라고 요청해도, 본 스킬은 청구범위 수정을 거부하고 "청구범위 수정은 별도 작업이며 신규사항 추가 금지 원칙·보정 가능성 등 별도 검토가 필요합니다"라고 안내한다.
  • 청구범위 수정이 정말 필요한 경우 → kr-patent-spec-drafting을 별도로 호출하거나 변리사가 직접 작성.

1. 변형 실시예 카테고리 체크리스트 (16종)

각 절의 핵심 실시예에 대하여 아래 카테고리를 점검하고, 적용 가능한 것을 모두 도출한다.

# 카테고리 예시 변형
1 알고리즘 변형 ICP → SAC-IA, FPFH, NDT 등 동등 기능 알고리즘
2 단계적/계층적 분해 단일 단계 → coarse-to-fine 다단계
3 입출력 형태 다양화 이산적 라벨 → 연속 수치, 단일 모달 → 멀티모달
4 데이터 종류 다양화 RGB → 적외선·초음파·라이다·X선·멀티스펙트럼
5 모델 구조 다양화 단일 모델 → 앙상블, 2단계 → end-to-end
6 학습/적응 메커니즘 정적 → 능동 학습, 강화학습, 전이학습
7 시간축 확장 단일 시점 → 시계열, 실시간 모니터링, 4D
8 불확실성 처리 결정적 → 강건 최적화, 확률적 최적화
9 사용자 상호작용 자동 → 인터랙티브 최적화, 사용자 피드백 루프
10 외부 시스템 연동 독립 → 표준 API, 외부 DB·플랫폼 연동
11 배포 형태 단일 서버 → 클라우드 분산, 엣지 컴퓨팅, 모바일 앱
12 가시화 형태 2D 차트 → AR, VR, 디지털 트윈 중첩, 대시보드
13 블록체인/분산원장 중앙 DB → 위변조 불가능한 분산 기록
14 추가 평가 지표 비용 → 탄소 배출, 안전성, 환경 영향, 소음·분진
15 제약 조건 다양화 단일 목적 → 다목적(파레토), 다양한 법적·실무적 제약
16 다국어/국제화 단일 언어 → 다국어 UI, 글로벌 표준 호환

운용 팁: 16개 전부를 매 절마다 적용할 필요는 없다. 절의 성격에 따라 자연스럽게 어울리는 4~7개 카테고리를 골라 적용한다.


1.5 설계 결정 축 8개 (프롬프트 ⑤) — 16카테고리와 직교 병존

위의 16카테고리는 "기술 도메인 축" — 어떤 데이터/모델/시간축/시스템을 쓸지에 대한 변형. 이와 직교(orthogonal) 하는 또 하나의 축은 "설계 결정 축" — 어떤 처리 전략/결합 방식/장애 대응을 쓸지에 대한 변형이다. 두 축은 독립적이며, 모든 명세서에 양쪽 모두 점검 권장.

Read the full file on GitHub · 315 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 315 lines · 382 tokens per session scan A f6aaeeb185eb

Subscribe to this mod's changes

kr-patent-embodiment-addition is a skill published in the GitHub repository lsj4232/KR_PATENT_SKILL (14 stars, last pushed 18d ago), licensed MIT. It adds 382 tokens to every session and 6,251 once invoked, about $0.0019 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

eac-habre

Chambres Africaines Extraordinaires (CAE) / Extraordinary African Chambers in the Courts of Senegal (EAC) research, drafting, and analysis — the Hissène Habré case. Use whenever the conversation involves the CAE/EAC, the AU-Senegal Accord of 22 August 2012, the Statute of the Chambers, the Habré trial (2015-2016), the…

jeannesulzer/international-criminal-tribunals-skills · 0 tokens

jep

Jurisdicción Especial para la Paz (JEP) — Colombia's Special Jurisdiction for Peace — research, drafting, and analysis. Use whenever the conversation involves the JEP, the SIVJRNR / Sistema Integral para la Paz, the 2016 Final Peace Agreement with the FARC-EP, Acto Legislativo 01 de 2017, Ley Estatutaria 1957 de 2019…

jeannesulzer/international-criminal-tribunals-skills · 0 tokens

nuremberg-tokyo

Post-WWII international military tribunals research, drafting, and analysis: the IMT at Nuremberg (1945-46), the twelve NMT trials under Control Council Law No. 10 (1946-49), and the IMTFE at Tokyo (1946-48). Use whenever the conversation involves Nuremberg, the Tokyo Trial, the London or Tokyo Charters, the IMT or…

jeannesulzer/international-criminal-tribunals-skills · 0 tokens

reg-64-kosovo

Regulation 64 Panels (Kosovo) research, drafting, and analysis — the UNMIK international judges and prosecutors (IJP) mechanism in the Kosovo district courts, 2000-2008/09. Use whenever the conversation involves UNMIK Regulation 2000/64, the 64 Panels, Regulations 2000/6 and 2001/2, UNSC Resolution 1244 (1999), the…

jeannesulzer/international-criminal-tribunals-skills · 0 tokens

cps-rca

Cour Pénale Spéciale de la République Centrafricaine (CPS) / Special Criminal Court in the Central African Republic (SCC-CAR) research, drafting, and analysis. Use whenever the conversation involves the CPS, the Loi organique n°15.003 of 3 June 2015, the RPP (Loi 18.010), the affaire Paoua / Lemouna et Koundjili (Issa…

jeannesulzer/international-criminal-tribunals-skills · 0 tokens

eccc

Extraordinary Chambers in the Courts of Cambodia (ECCC, Khmer Rouge Tribunal) research, drafting, and analysis. Use whenever the conversation involves the ECCC, Case 001 (Duch), Case 002 (NUON Chea, KHIEU Samphan) including the severance into Cases 002/01 and 002/02, Cases 003 and 004, the ECCC Law, the Internal…

jeannesulzer/international-criminal-tribunals-skills · 0 tokens