kr-patent-stage-recommender

kr-patent-stage-recommender is a skill for Claude Code, Codex from lsj4232/KR_PATENT_SKILL. It costs 395 tokens per session (4,952 once invoked), scanned A, original, MIT.

A diagnostic tool for deciding where to begin in an 11-stage Korean patent-specification workflow. It examines available claims, drawings, sections, definitions, wording patterns, and formatting issues.

In plain words
What is it for?
Use it to assess a DOCX, Markdown, text file, claims, IDS, drawings, reference-number table, or a stated project status, then receive a recommended starting stage and next command.
Why use it?
It shows how complete an existing draft is and highlights missing or risky parts before substantive editing begins.

Skill for Claude CodeCodex

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

Good fit Use it to assess a DOCX, Markdown, text file, claims, IDS, drawings, reference-number table, or a stated project status, then receive a recommended starting stage and next command.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-stage-recommender"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-stage-recommender.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 395 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,952 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 $0.00395 $0.04952
Opus 5 $0.00198 $0.02476
Sonnet 5 $0.00079 $0.00990
Haiku 4.5 $0.00040 $0.00495

Measured 11d ago against content hash 18b4da3e0898, 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-stage-recommender 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-stage-recommender/SKILL.md · 409 lines

How it starts

The opening of the file, as written. The whole thing — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.

한국 특허 명세서 Stage 추천 (진단 게이트)

무엇을 하는가

명세서 또는 부분 자료를 받아 kr-patent-full-workflow의 어느 Stage부터 시작해야 하는지 진단한다. /full의 Stage 0(입력 점검)을 독립 스킬로 분리·강화한 것으로, 다음과 같은 상황에서 사용한다:

  • 외부에서 받은 명세서를 어디까지 손봐야 할지 파악
  • 다른 변리사가 작성한 초안을 이어서 작업
  • 중단했던 명세서를 다시 시작
  • 단순히 "이 docx 어디까지 됐지?" 빠른 진단

본 스킬은 진단만 한다. 워크플로우 실행은 결과를 보고 변리사가 /full 또는 단일 스킬을 직접 호출.

입력

다음 중 하나 또는 복수:

  • 명세서 .docx (가장 흔함)
  • 명세서 .md 또는 .txt
  • 청구항 텍스트만
  • IDS(기술내용설명서) 파일
  • 도면 파일들
  • 부호의 설명 표만
  • 자료 없이 대화로 상태 진술 ("청구항만 있어요")

산출물

1페이지 진단 보고서 (Markdown):

  1. 자료 현황표 (6개 시그널 ✅/❌/⚠️ 표)
  2. 추천 시작 Stage + 근거 3줄
  3. 위험 신호 (있다면 — 모순·결손·정형 위반)
  4. 권장 명령 — /full <범위> 또는 /kr-patent-<단일스킬>
  5. 예상 잔여 단계 수 + 대략 작업량

추가 산출물 없음. 본문 수정·docx 생성 등은 추천된 다음 단계의 스킬이 담당.


진단 알고리즘 — 6개 시그널 검출

시그널 1: 청구항 존재·구조

검출 패턴 의미
【청구범위】 헤더 존재 청구항 섹션 있음
【청구항 N】 개수 청구항 갯수
~ 시스템·~ 방법·~ 프로그램·~ 매체 어말 카테고리 분류
제 N 항 인용 패턴 종속관계 트리

결손 시그널:

  • 청구항 없음 → IDS 단계
  • 청구항 있는데 인용 누락 → 위험 신호
  • 시스템 청구항만, 방법 청구항 없음 → 보완 권장

시그널 2: 도면·부호 사용

검출 패턴 의미
【도면의 간단한 설명】 섹션 도면 ID 등록됨
본문 안 (110), (120), (S120) 패턴 카운트 부호 사용량
부호 계층 (100→110→121) 패턴 부호 체계 설계 완료
시스템 부호(3자리)와 방법 부호(S+3자리) 분리 여부 부호 분리 설계 완료

결손 시그널:

  • 도면 ID는 있는데 본문에 부호 등장 없음 → Stage 3 미완
  • 본문 부호와 부호의 설명 불일치 → 위험 신호

시그널 3: 11개 표준 섹션 완성도

체크할 헤더:

1. 【발명의 명칭】
2. 【기술분야】
3. 【배경기술】
4. 【발명의 내용】 / 【해결하고자 하는 과제】
5. 【과제의 해결 수단】
6. 【발명의 효과】
7. 【도면의 간단한 설명】
8. 【발명을 실시하기 위한 구체적인 내용】
9. 【부호의 설명】 (선택)
10. 【청구범위】
11. 【요약서】

11개 중 N개 작성 → 진행률 = N/11.

시그널 4: ★ 자체 사전 정의 단락 적용 여부 (핵심)

정의 단락의 표준 4단 템플릿 패턴:

"<용어>이란/라 함은 ... 를 의미할 수 있다."
"... 를 포함할 수 있다."
"... 예를 들어 ..., ... 등을 포함할 수 있다."
"... 이에 한정되지 않는다."

검출 방법:

  • 라 함은 + 의미할 수 있다 동시 등장 단락 카운트
  • 한정되지 않는다 마무리 카운트

판정:

  • 둘 다 0건 → 정의 미적용 (Stage 6 진입 권장)
  • 일부만 있음 → Stage 6 부분 완료 (보강 권장)
  • 청구항 한정 용어와 비교하여 누락 용어 리스트 추출

시그널 5: ★ 변형 실시예 적용 여부 (핵심)

변형 실시예 도입어 패턴:

"한편,"
"또 다른 실시예에 있어서,"
"또한, 일 실시예에 있어서,"
"나아가,"

Read the full file on GitHub · 409 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 · 409 lines · 395 tokens per session scan A 18b4da3e0898

Subscribe to this mod's changes

kr-patent-stage-recommender is a skill published in the GitHub repository lsj4232/KR_PATENT_SKILL (14 stars, last pushed 18d ago), licensed MIT. It adds 395 tokens to every session and 4,952 once invoked, about $0.0020 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