kr-patent-skill-updater

kr-patent-skill-updater is a skill for Claude Code, Codex from lsj4232/KR_PATENT_SKILL. It costs 212 tokens per session (2,555 once invoked), scanned A, original, MIT.

A Korean-language patent-work retrospective skill that turns lessons, mistakes, and reviewer feedback into proposed updates for related patent skills.

In plain words
What is it for?
Use it after Korean patent drafting or review work to classify lessons, request approval, and append approved guidance to the relevant skill files.
Why use it?
It helps preserve useful lessons from completed patent work instead of losing them after one task.

Skill for Claude CodeCodex

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

Good fit Use it after Korean patent drafting or review work to classify lessons, request approval, and append approved guidance to the relevant skill files.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-skill-updater"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-skill-updater.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 212 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,555 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 $0.00212 $0.02555
Opus 5 $0.00106 $0.01277
Sonnet 5 $0.00042 $0.00511
Haiku 4.5 $0.00021 $0.00255

Measured 11d ago against content hash 41b99ada6066, 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-skill-updater 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/append_learning.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-skill-updater/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

한국 특허 스킬 업데이터 (메타 스킬)

무엇을 하는가

방금 끝낸 한국 특허 작업(명세서 작성, 점검, 미팅 질문 생성 등)을 회고하여 *다른 kr-patent- 스킬에 누적시켜야 할 학습 항목**을 식별하고, 사용자 승인 후 해당 SKILL.md 파일을 자동 업데이트한다.

이 스킬이 없으면 컴파운딩 루프는 이론적 개념에 머문다. 이 스킬을 주기적으로 호출해야 다른 5개 스킬이 사용할수록 똑똑해진다.

입력

  • 방금 끝낸 작업의 컨텍스트 (대화 히스토리)
  • (선택) 검토자/발명자 피드백
  • (선택) 작업 중 발견한 실수·놀라움·예상 못 한 패턴

출력

  1. 회고 보고서: 어느 스킬에 어떤 학습 항목을 추가할지 분류한 제안 리스트
  2. 사용자 승인: 항목별 OK/NO/수정 받기
  3. SKILL.md 자동 업데이트: 승인된 항목을 해당 SKILL.md의 "누적 학습 항목" 섹션 끝에 append

분류 카테고리 (5개 스킬 매핑)

작업에서 발견된 학습 항목을 다음 카테고리 중 어디에 속하는지 판단한다:

카테고리 어떤 종류의 학습 항목? 대상 스킬
A. 발명자 정보 누락 "이번엔 X를 미리 물어봤어야 했다", IDS의 새로운 구멍 유형 kr-patent-inventor-meeting
B. 부호 설계 실수 "처음부터 X 부호 범위를 예약했어야 했다", 충돌·재설계 사례 kr-patent-symbol-design
C. 명세서 본문 가이드라인 새로운 금지 표현, 위험 패턴, 좋은 표현 양식, 검토자 지적 kr-patent-spec-drafting (+ references/ko-patent-style-rules.md)
D. 새로운 점검 항목 마스터 체크리스트에 없던 위반 유형, 정합성 오류의 새 패턴 kr-patent-consistency-check
E. docx 양식 버그·개선 폰트/들여쓰기/페이지 양식 이슈, 검토자가 지적한 표지 양식 kr-patent-docx-builder/scripts/build_kr_patent.js (스크립트 직접 수정)

분류가 모호하면 사용자에게 묻는다. "이 항목은 A로 가야 하나요, C로 가야 하나요?"

작업 순서

Step 1. 회고 트리거 확인

다음 중 하나면 진행:

  • 사용자가 명시적으로 "회고해줘", "스킬 업데이트해줘" 요청
  • 명세서 작업이 명확히 종료됨 (deliverable 전달 완료)
  • 검토자 피드백이 들어옴

명세서 작업이 진행 중이면 회고하지 않음. 흐름을 끊지 말 것.

Step 2. 대화 컨텍스트 회상

방금 끝낸 작업의 핵심 사건들을 회상한다. 우선적으로 다음에 주목:

  • 수정·재작성·되돌리기 사례: "이거 다시 해줘", "이 부분 빼고", "지난 버전이 나았다" → 첫 시도가 틀렸다는 신호. 왜 틀렸는지 분석.
  • 사용자가 직접 보완한 부분: Claude가 놓쳤는데 사용자가 짚어준 항목들.
  • 반복 질문: 사용자가 같은 종류의 질문을 두 번 이상 했다면, 첫 답이 부족했음.
  • 놀라움 (surprise): "이걸 깜빡할 줄 몰랐다" 종류의 일.
  • 검토자/발명자 피드백: 외부 인풋이 있었다면 그 내용.

Step 3. 학습 항목 추출

각 사건에 대해 다음 형식으로 추출:

[학습 항목]
- 사건: <무엇이 일어났나, 1문장>
- 일반화: <개별 사건을 일반 규칙으로>
- 대상 카테고리: A/B/C/D/E 중 하나
- 새 누적 항목 문구: <SKILL.md에 그대로 들어갈 한 줄>

좋은 항목 vs 나쁜 항목:

좋음 (일반화·재사용 가능) 나쁨 (너무 특수)
회로 발명에서 V_REF 정전위 조건은 시스템 효과로 명시 빔진단 시스템에서 V_REF=1.65V 사용
알고리즘 발명은 윈도우 크기·오버랩·업데이트 주기를 변형예에 명시 특정 모델의 LSTM 윈도우 32 사용
청구항 한정 수치가 도면 박스 라벨에 노출되면 위험 도 4의 10mV 표기 위험

Read the full file on GitHub · 161 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 · 161 lines · 212 tokens per session scan A 41b99ada6066

Subscribe to this mod's changes

kr-patent-skill-updater is a skill published in the GitHub repository lsj4232/KR_PATENT_SKILL (14 stars, last pushed 18d ago), licensed MIT. It adds 212 tokens to every session and 2,555 once invoked, about $0.0011 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