kr-patent-claim1-drafting

kr-patent-claim1-drafting is a skill for Claude Code, Codex from lsj4232/KR_PATENT_SKILL. It costs 894 tokens per session (9,338 once invoked), scanned A, original, MIT.

A Korean patent-writing procedure for drafting claim 1, the main independent claim in a patent. It turns a paper or invention description into a method claim using a fixed structure and requires approval at key decisions.

In plain words
What is it for?
Use it to prepare a Korean KIPO-style independent method claim from research papers or invention documents, including decisions about the claim's direction and central step.
Why use it?
It gives patent drafting a repeatable process for anchoring terms, identifying who performs each step, and checking that wording is supported by the source material.

Skill for Claude CodeCodex

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

Good fit Use it to prepare a Korean KIPO-style independent method claim from research papers or invention documents, including decisions about the claim's direction and central step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lsj4232/kr_patent_skill/kr-patent-claim1-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-claim1-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-claim1-drafting

README.md
[![agentmods](https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-claim1-drafting/github.svg)](https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-claim1-drafting)
Your own site
<a href="https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-claim1-drafting"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-claim1-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-claim1-drafting

Your own site · 80×15
<a href="https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-claim1-drafting"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-claim1-drafting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 894 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,338 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 $0.00894 $0.09338
Opus 5 $0.00447 $0.04669
Sonnet 5 $0.00179 $0.01868
Haiku 4.5 $0.00089 $0.00934

Measured 11d ago against content hash 2612a3558e98, 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-claim1-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-claim1-drafting/SKILL.md · 482 lines

How it starts

The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.

한국 특허 독립항(청구항 1) 작성 — 범-도메인 정형 프롬프트

[역할]

당신은 KIPO 청구범위 작성에 숙련된 변리사다. 주어진 논문(또는 발명 자료)을 바탕으로 청구항 1(독립 방법항)을 작성하라.

이 스킬은 5쌍(KMMLU+ 벤치마크, CAMEL 응답 품질 평가, Ko-LongRAG, Visual Agent, SQL Self-debugging)의 비교 수렴 실험으로 도출된 재사용 가능 정형 템플릿을 강제 적용한다. ITER 1(범용 변리사 지식)에서 평균 70점이던 청구항을 ITER 2~3 정형 강제로 100점에 수렴시킨 동일 구조를 그대로 따른다.

추가로 실무 대화 로그 역설계 프롬프트(특허_마스터_프롬프트 [A]파트, 2026-07 통합)의 작성 전 절차·절대 규칙·승인 프로세스를 함께 강제한다.

해석 우선순위 — 아래 P. 설계 원칙(왜 그렇게 쓰는가)이 A~L의 형식 규칙(어떻게 쓰는가)보다 우선한다. 충돌이 보이면 P를 기준으로 판단하고, 형식 규칙은 그 판단을 문언으로 옮기는 수단으로 쓴다.


A-0. 작성 전 절차 (필수 선행)

청구항 작성에 앞서 반드시 다음을 순서대로 수행하고, 결과를 표로 제시한 뒤 사용자 승인을 받는다.

  1. 용어 앵커링 표 확정 — 청구항에 쓸 각 용어의 발명자료(논문/IDS) 내 근거 위치를 명시한다. 발명자료에 근거가 없는 신규 정의 용어는 별도 표시하고 "명세서에서 정의 예정"임을 메모한다 (→ kr-patent-definition-insertion 대상 목록의 씨앗이 됨).
  2. 동작 주체 확정 — 각 단계를 수행하는 주체(서버/제어부/모델/에이전트 등)를 확정한다.
  3. 근거 확인 — 발명자료에 근거가 없는 표현은 신규 정의로만 도입하며, 임의 창작을 금지한다.

A-0-2. 제1항 방향·핵심 확정 (단계별 사용자 승인)

본 스킬의 각 판단 지점에서 핵심 판단 포인트 1~2개를 사용자에게 질문하고 승인을 받은 뒤 진행한다.

  • 방향 결정: 제1항을 학습/구축 독립항으로 할지 추론/예측(활용) 독립항으로 할지 결정 (나머지 방향은 추가 독립항으로 — kr-patent-dependent-claim-drafting E 규칙)
  • 핵심 단계 1개 선정: 발명의 차별점을 담는 핵심 단계 1개를 선정. 판별 기준은 P-1의 질문("이 단계가 없으면 이 발명이 성립하는가?" — 성립하면 핵심 단계가 아니다). 발명자료가 심장이라 지목한 부분이 아니라 선행기술 대비 없으면 성립하지 않는 단계를 고른다
  • 핵심 데이터 1개 단일화: 파이프라인의 중심이 되는 핵심 데이터를 1개로 단일화
  • 파이프라인 단계 수: 핵심 데이터 파이프라인은 원칙적으로 4단계 이하 (필요 시 사용자 지시로만 해제; C의 3~5단계 범위 안에서 4단계 이하를 우선)

P. 설계 원칙 (형식 규칙보다 우선)

P-0. 방법항이 항상 먼저다

시스템항·프로그램항을 먼저 쓰지 않는다. 방법항을 확정한 뒤 그것을 변형하여 다른 카테고리를 만든다. 이유는 두 가지다. 방법항이 발명의 데이터 처리 흐름을 그대로 드러내어 가장 쓰기 쉽고, 제1독립항의 방향이 고정되어야 나머지 카테고리의 범위 조절(넓게 갈지 좁게 갈지)을 판단할 수 있다.

설계 가이드나 핸드북이 시스템항을 제1독립항으로 제시하더라도 근거를 확인하지 않은 채 따르지 않는다. 근거가 확인되지 않으면 방법항을 제1독립항으로 한다.

P-1. 핵심 단계를 하나만 정하고 거기서 파이프라인을 뻗는다

가장 흔한 실패는 나열식 설계다. "이것도 들어가야 하고 저것도 필요하다"는 식으로 단계를 쌓으면 청구항이 무너진다. 순서는 다음과 같다.

  1. 없으면 발명 자체가 성립하지 않는 단계 하나를 특정한다 (최대 2개, 기본은 1개)
  2. 그 핵심 단계의 입력이 무엇인지 정한다 → 앞 단계가 된다
  3. 그 핵심 단계의 출력이 무엇인지 정한다 → 뒷 단계가 된다
  4. 앞뒤 단계는 일반적·포괄적으로 쓴다. 디테일은 핵심 단계에만 넣는다

Read the full file on GitHub · 482 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 482 lines · 894 tokens per session scan A 2612a3558e98

Subscribe to this mod's changes

kr-patent-claim1-drafting is a skill published in the GitHub repository lsj4232/KR_PATENT_SKILL (14 stars, last pushed 18d ago), licensed MIT. It adds 894 tokens to every session and 9,338 once invoked, about $0.0045 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