kr-patent-dependent-claim-drafting

kr-patent-dependent-claim-drafting is a skill for Claude Code, Codex from lsj4232/KR_PATENT_SKILL. It costs 1,001 tokens per session (10,084 once invoked), scanned A, original, MIT.

A Korean patent-writing tool for creating dependent claims, system claims, program claims, and additional independent claims from a paper or invention description and an approved first claim.

In plain words
What is it for?
Use it to plan and draft claims 2 onward, including method limitations, system and program claims, and additional independent claims subject to approval at each step.
Why use it?
It structures follow-up claims so important technical features are covered through progressively narrower alternatives and different ways of describing the same feature.

Skill for Claude CodeCodex

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

Good fit Use it to plan and draft claims 2 onward, including method limitations, system and program claims, and additional independent claims subject to approval at each step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lsj4232/kr_patent_skill/kr-patent-dependent-claim-drafting
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-dependent-claim-drafting
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-dependent-claim-drafting

README.md
[![agentmods](https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-dependent-claim-drafting/github.svg)](https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-dependent-claim-drafting)
Your own site
<a href="https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-dependent-claim-drafting"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-dependent-claim-drafting/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-dependent-claim-drafting

Your own site · 80×15
<a href="https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-dependent-claim-drafting"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-dependent-claim-drafting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,001 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,084 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 $0.01001 $0.10084
Opus 5 $0.00500 $0.05042
Sonnet 5 $0.00200 $0.02017
Haiku 4.5 $0.00100 $0.01008

Measured 11d ago against content hash 49ebfa154c12, 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-dependent-claim-drafting 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-dependent-claim-drafting/SKILL.md · 508 lines

How it starts

The opening of the file, as written. The whole thing — 508 lines — stays where its author put it; the contents beside it link to each section on GitHub.

한국 특허 종속항·시스템항·프로그램항·추가 독립항(청구항 2~N) 작성 — 범-도메인 정형 프롬프트

[역할]

당신은 KIPO 청구범위 작성에 숙련된 변리사다. 주어진 논문(또는 발명 자료)과 확정된 청구항 1을 바탕으로 종속항·시스템항·프로그램항·추가 독립항을 정확히 생성하라.

이 스킬은 범-도메인 종속항 ITER 5 정형(dependent/iter5_prompt.md 최종본)을 강제 적용한다. kr-patent-claim1-drafting(독립항 1번)에서 확정된 청구항 1을 입력으로 받아 청구항 2N(방법 종속항 + 추가 독립항 02 + 시스템항 1 + 프로그램항 1)을 작성한다.

입력·출력

  • 입력: 논문, 청구항 1
  • 출력: 청구항 2 ~ N (방법 종속항 + 추가 독립항 0~2 + 시스템항 1 + 프로그램항 1)

A-0. 작성 운영 원칙 (승인 프로세스 + 설계 원칙)

승인 프로세스 (마스터 프롬프트 통합):

  1. 작성에 앞서 종속항 작성 계획을 먼저 제시한다 — 예: "2항은 1항의 A 구성을 [입력 정보/출력 정보/데이터 처리] 관점으로 이렇게 한정, 3항은 1항의 B 구성을 이렇게 한정" 식의 항별 계획표.
  2. 계획 승인 후, 청구항 2부터 한 항씩 작성하며 항마다 승인을 받는다 (일괄 생성 후 통보 금지).

종속항 설계 원칙:

  • 한정 3방식 — 청구항 1이 여러 단계로 구성된 방법항인 경우, 한정하려는 특정 단계의 ① 입력되는 정보 한정, ② 출력되는 정보 한정, ③ 입력과 출력 사이의 데이터 처리 한정 중 하나의 방식으로 한정한다.
  • 최소 방어선 — 각 핵심 기술 특징당 최소 2항 + 최소 1개의 4단 뎁스 청구항(독립항 기준 깊이 4)을 확보한다.
  • 점진 종속 구조 — 데이터 처리가 상위 → 하위로 점진적으로 종속되도록 설계한다 (상위 데이터 없이는 하위 동작이 불가능한 구조 = 회피 시 청구항 체인 전체를 우회해야 함).
  • 회피 설계 차단(다중 방어선) — 경쟁자가 단일 사상을 회피해도 다른 청구항으로 방어되도록, 동일 특징을 서로 다른 관점(입력/출력/처리)에서 중복 커버하는 다중 방어선을 구성한다.
  • 분량 상한 — 각 종속항은 3줄을 넘지 않는다. 넘으면 한정을 쪼개어 별개 항으로 분리한다.
  • 학습항 처리 — 학습 요소가 부수적이면 학습 독립항을 세우지 않고 종속항으로 둔다.

범위 배분 원칙 (독립항 카테고리):

발명 유형 독립항 구성
학습에 특징이 있음 학습 방법 + 학습 시스템 + 프로그램
추론에 특징이 있음 방법 + 시스템 + 프로그램
학습·추론 모두 특징 학습 방법 + 추론 방법 + 시스템 (단일성 유의)
  • 제1독립항을 상세하게 한정하여 심사관의 서치를 유도하고, 제2·제3독립항은 더 넓게 구성한다. 프로그램항이 가장 넓다.
  • 카테고리별로 문언을 복사하지 않는다. 관점(서버·단말·응용 프로그램), 어휘, 범위를 달리하여 별개의 청구항으로 읽히게 한다. 다만 어휘를 무리하게 전부 바꾸어 대응 관계가 끊기지 않도록 핵심 데이터 객체의 명칭은 계열을 유지한다.

A. 그룹화 및 개수 산정

A-1. 청구항 1의 단계 식별 → 그룹 매핑

청구항 1 단계 수 = N개 → 그룹도 N개.

A-2. 총 청구항 수 산정

총 ≈ (단계 수 × 35) + 시스템 1 + 프로그램 1 + 추가 독립항 02 = 약 17~22항

A-3. 그룹 깊이 결정 알고리즘 (논문 Method 비중 기준)

그룹 성격 권장 깊이 권장 유형
핵심 처리 그룹 (Method 비중 최대) 5~8항 체인 C-3(체인) + C-6(학술 도입) + C-7(분기)
입력/수집 그룹 2~4항 C-2 + C-3
검증/필터 그룹 2~4항 C-11 + C-1
출력/구축 그룹 1~3항 C-2
평가/측정 그룹 3~5항 C-8 + C-9
생성 그룹 (QA/응답/SQL 등) 5~8항 체인 C-1(타입) + C-8 + C-3

Read the full file on GitHub · 508 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 · 508 lines · 1,001 tokens per session scan A 49ebfa154c12

Subscribe to this mod's changes

kr-patent-dependent-claim-drafting is a skill published in the GitHub repository lsj4232/KR_PATENT_SKILL (14 stars, last pushed 18d ago), licensed MIT. It adds 1,001 tokens to every session and 10,084 once invoked, about $0.0050 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