kr-patent-drawing-mapping

kr-patent-drawing-mapping is a skill for Claude Code, Codex from lsj4232/KR_PATENT_SKILL. It costs 258 tokens per session (3,892 once invoked), scanned C, original, MIT.

A tool for reading Korean patent drawing images and assigning one reference number to each box, such as a module, object, device, or person. It creates a mapping that connects those boxes with the patent text and claims.

In plain words
What is it for?
It is for checking patent drawings, matching labels through OCR (text read from images), and producing drawing-by-drawing box-to-number tables and correction notes.
Why use it?
It helps find boxes that are missing numbers or have inconsistent labels across the drawings, description, and claims.

Skill for Claude CodeCodex

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

Good fit It is for checking patent drawings, matching labels through OCR (text read from images), and producing drawing-by-drawing box-to-number tables and correction notes.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-drawing-mapping"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-drawing-mapping.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 258 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,892 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00258 $0.03892
Opus 5 $0.00129 $0.01946
Sonnet 5 $0.00052 $0.00778
Haiku 4.5 $0.00026 $0.00389

Measured 11d ago against content hash a598fd9d8586, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

kr-patent-drawing-mapping scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

cd /tmp && rm -rf docx_extract && mkdir docx_extract && cd docx_extract
kr-patent-drawing-mapping/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

한국 특허 도면 박스별 부호 매핑

무엇을 하는가

한국 특허 명세서의 도면 이미지(docx 내 image*.tiff 또는 별도 PNG·JPG)를 시각 분석/OCR로 처리하여, 각 도면 안의 모든 박스 1개당 부호 1개가 1:1로 대응되는 박스별 부호 매핑 표를 산출한다.

kr-patent-symbol-design이 청구항·본문 텍스트로 부호 골격(시스템 부서, 방법 단계, 장비 등)을 설계한다면, 본 스킬은 도면 이미지를 직접 보고 부호 골격을 박스 단위로 채워 넣어 도면 ↔ 본문 ↔ 청구항 3자 정합성이 박스 수준에서 보장되도록 한다.

언제 사용하는가

  • 변리사가 "박스마다 부호가 있어야 한다"고 요청
  • 도면이 이미 그려졌는데 부호가 듬성듬성하거나 누락
  • kr-patent-symbol-design으로 골격 설계가 끝났으나, 도면을 보니 박스가 골격보다 훨씬 많음
  • 검토자/심사관이 "도면에 객체 부호가 부족하다" 지적
  • 외부에서 받은 명세서 docx의 도면 부호 점검·보강

입력

  • (필수) 명세서 docx 또는 별도 도면 이미지 폴더
  • (선택) 본문 텍스트 또는 추출된 txt — 박스 라벨과 본문 어휘 매칭 정합성 점검용
  • (선택) 청구항 텍스트 — 청구항 한정 표기가 도면 박스에 노출됐는지 점검용
  • (선택) 기존 부호 체계 (kr-patent-symbol-design 산출물) — 일관성 유지용

출력

  1. 도면별 박스 ↔ 부호 매핑 표 (Markdown): [사건번호] 박스별 부호 할당.md
  2. 엑셀 산출물 (3시트): [사건번호] 도면별 부호 할당.xlsx
    • 시트 1: 도면별 요약 (박스 수 + 신규/재사용 부호 목록)
    • 시트 2: 도면별 박스-부호 매핑 (전수)
    • 시트 3: 마스터 부호 체계 (전체 부호 ↔ 명칭 ↔ 계층 관계)
  3. 도면 이미지 수정 권장 사항 보고서: 도면 자체 오타, 정비 전 부호 잔존, 본문 정비 미동기화 등

작업 순서

Step 1. 도면 이미지 추출

docx에서 도면 이미지를 추출. unzipword/media/image*.tiff에 위치.

cd /tmp && rm -rf docx_extract && mkdir docx_extract && cd docx_extract
unzip -q "/path/to/spec.docx"
ls word/media/  # image1.tiff ~ imageN.tiff

Step 2. 도면 ↔ 이미지 매핑 확인

중요: image{N}.tiff의 N이 명세서의 「도 N」과 자동 일치한다고 가정하지 말 것. docx 편집 도중 순서가 뒤바뀔 수 있다. 다음 점검:

  1. 본문 §섹션별 도면 인용("도 N을 참조하면…")과 도면의 간단한 설명을 추출
  2. 첫 1~2장 도면을 Read tool로 시각 확인 → "이 이미지가 어느 도면인지" 식별
  3. 매핑 표 작성:
image1.tiff = 도 1 (시스템)
image2.tiff = 도 2 (방법 흐름도)
...
image7.tiff = 도 7 (GA 흐름도)   ← 도면 인용 정비 후

만약 명세서가 도면 인용 ±1 어긋남 상태라면 kr-patent-consistency-check로 먼저 정비 후 진행.

Step 3. TIFF → PNG 변환 (Read tool 호환)

from PIL import Image
import os
for tiff in os.listdir('word/media'):
    if tiff.endswith('.tiff'):
        img = Image.open(f'word/media/{tiff}')
        img.save(f'figures_png/{tiff.replace(".tiff", ".png")}', 'PNG')

Step 4. 도면별 시각 분석 (Read tool)

도 1부터 도 N까지 차례로 Read 호출. 각 도면에서:

Read the full file on GitHub · 230 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 · 230 lines · 258 tokens per session scan C a598fd9d8586

Subscribe to this mod's changes

kr-patent-drawing-mapping is a skill published in the GitHub repository lsj4232/KR_PATENT_SKILL (14 stars, last pushed 17d ago), licensed MIT. It adds 258 tokens to every session and 3,892 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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

document-fill

A document-filling assistant that uses a supplied template and case files to fill in forms, contracts, or legal documents. It also reports where each filled value came from and which details are missing.

code-lawyer/Legal-Agent-Skills · 61 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

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

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

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

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