kr-patent-symbol-design

kr-patent-symbol-design is a skill for Claude Code, Codex from lsj4232/KR_PATENT_SKILL. It costs 176 tokens per session (4,654 once invoked), scanned A, original, MIT.

A planning tool for assigning reference numbers in Korean patent documents and drawings. It creates hierarchical numbers for system parts and separates method-step numbers with an S prefix.

In plain words
What is it for?
Use it before writing or revising a patent specification to design the numbering scheme, avoid conflicts, and prepare the reference-number explanation table.
Why use it?
It prevents conflicting or unclear labels across claims, descriptions, and drawings, making their relationships easier to follow.

Skill for Claude CodeCodex

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

Good fit Use it before writing or revising a patent specification to design the numbering scheme, avoid conflicts, and prepare the reference-number explanation table.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-symbol-design"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-symbol-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 176 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,654 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 $0.00176 $0.04654
Opus 5 $0.00088 $0.02327
Sonnet 5 $0.00035 $0.00931
Haiku 4.5 $0.00018 $0.00465

Measured 12d ago against content hash b36608942d33, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

kr-patent-symbol-design 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 12d 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-symbol-design/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

한국 특허 도면 부호 체계 설계

무엇을 하는가

청구항·도면을 분석하여 한국 특허 실무에 부합하는 도면 부호 체계를 설계한다. 부호는 명세서 본문·도면·청구항 사이의 정합성 골격이므로, 명세서 본문 작성 전 단계에서 먼저 확정한다.

핵심 원칙

1. 계층적 넘버링

부호는 백 단위/십 단위/일 단위로 계층화한다. 같은 상위 부호 아래 하위 구성요소는 그 백 단위 안의 십 단위·일 단위로 배치한다.

100  시스템 (최상위)
  110  서브시스템 A
  120  서브시스템 B
    121, 122, 123, 124  서브시스템 B의 채널/단계별 구성요소
  130  서브시스템 C
    131-134  서브시스템 C의 채널별 구성요소

이 패턴이 일관되어야 변리사·심사관·법원이 "121-124가 형제 관계"임을 즉시 인식한다.

2. 시스템 부호 vs 방법 단계 부호 분리 (S-prefix)

방법 발명의 단계 부호는 반드시 S 접두사를 붙인다. 시스템 부호의 숫자와 방법 단계 부호의 숫자가 중복되어도 S 접두사로 명확히 구분되므로 실무상 허용된다.

시스템:  120  다중 게인 증폭부
         121-124  제1-4 게인 스테이지

방법:    S100  빔 진단 방법
         S110  채널 분배
         S120  병렬 증폭
         S130  유효성 판정

S110과 110이 동시에 등장해도 명확하므로 허용.

2-1. ★ 처리 로직에 ~부를 붙이지 않는다 (블록 남발 금지)

마스터 프롬프트 A-5의 절대 규칙이다. 시스템 구성을 설계할 때 물리적 실체가 있는 블록만 ~부로 분리하고, 변환·판정·산출 같은 내부 처리 로직은 단일 제어부(또는 청구항이 그렇게 부른다면 프로세서) 안으로 통합한다.

구분 ~부 분리
입력계 수신부, 스캔부, 센서부, 입출력부
저장계 저장부, 메모리, 데이터베이스 저장부
출력계 사용자 인터페이스부, 디스플레이부, 광학 출력부, 알림부, 통신부
연산 주체 ○ (단 1개) 제어부, 프로세서
내부 처리 로직 ~획득부, ~판단부, ~탐색부, ~판정부, ~검증부, ~생성부, ~산출부, ~분석부

판별 기준: 그 ~부를 떼어 내어 별도 부품으로 살 수 있는가. 없으면 처리 로직이므로 제어부에 통합한다.

설계 시 자기 점검: 청구항의 시스템 독립항에 등장하지 않는 ~부가 도면에 있으면 그것은 근거 없는 블록이다. 청구항이 메모리프로세서만 기재했다면 도면도 그 둘 + 입출력계·통신계까지만 블록화한다.

위반 시 파급이 크다: 처리 로직을 7개 ~부로 쪼개 두면 (i) 도면이 근거 없는 하드웨어 블록으로 채워지고, (ii) 본문 전체가 그 부호를 물고 서술되어 나중에 되돌리려면 60여 곳을 고쳐야 하며, (iii) 심사관이 청구항에 없는 구성을 발명의 필수 구성으로 오인할 여지를 준다. Stage 2(부호 설계) 시점에 반드시 걸러라. 본문 작성 후에는 비용이 수십 배다.

3. 충돌 회피 — 같은 카테고리 안에서만

  • 시스템 부호끼리는 절대 중복 금지
  • 방법 단계 부호(S110, S120 등)끼리도 절대 중복 금지
  • 다른 카테고리 사이(시스템 110 vs 단계 S110)는 허용

4. "왜 121부터?"가 자연스러워야

부호 추가 시 기존 패턴을 깨지 말 것. 121-124 게인 스테이지가 이미 있는데 유효성 판정부에 135-138을 주면 "왜 131-134를 비웠지?" 의문이 생긴다. 가급적 부모-자식 패턴 일관성을 유지한다.

좋음:

120  증폭부 ─ 121-124  채널별 스테이지
130  생성부 ─ 131-134  채널별 판정부

나쁨:

120  증폭부 ─ 121-124  채널별 스테이지
130  생성부 ─ 135-138  채널별 판정부 (131-134 비어있음 — 왜?)

Read the full file on GitHub · 235 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. 12d ago First seen · 235 lines · 176 tokens per session scan A b36608942d33

Subscribe to this mod's changes

kr-patent-symbol-design is a skill published in the GitHub repository lsj4232/KR_PATENT_SKILL (15 stars, last pushed 19d ago), licensed MIT. It adds 176 tokens to every session and 4,654 once invoked, about $0.0009 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

special-panels-timor-leste

Special Panels for Serious Crimes of the Dili District Court (SPSC, 2000-2006) research, drafting, and analysis. Use whenever the conversation involves the Special Panels, the Serious Crimes Unit (SCU), UNTAET and its Regulations 1999/1, 2000/11, 2000/15 and 2000/30, the 1999 referendum violence, the hybrid…

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