grammar-checker

grammar-checker is a skill for Claude Code from DaleSeo/korean-skills. It costs 148 tokens per session (2,555 once invoked), scanned A, original, MIT.

A Korean-language checker based on standard Korean spelling, spacing, grammar, and punctuation rules. It also explains why a suggested correction is needed.

In plain words
What is it for?
Use it to review Korean documents, live writing, Korean comments in code, or technical text, with corrections prioritized from spelling and spacing to grammar and punctuation.
Why use it?
It catches common mistakes such as incorrect endings, spacing, particles, tense, and excessive punctuation that can make Korean writing unclear or less formal.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the korean-skills plugin — 3 skills shipped together

Good fit Use it to review Korean documents, live writing, Korean comments in code, or technical text, with corrections prioritized from spelling and spacing to grammar and punctuation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/daleseo/korean-skills/grammar-checker
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 DaleSeo/korean-skills --skill grammar-checker
Clone the repo
git clone --depth 1 https://github.com/DaleSeo/korean-skills

Made for: Claude Code.

Or install korean-skills, the plugin that ships this one along with the rest of its 3 skills.

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 grammar-checker

README.md
[![agentmods](https://agentmods.dev/badge/skills/daleseo/korean-skills/grammar-checker/github.svg)](https://agentmods.dev/skills/daleseo/korean-skills/grammar-checker)
Your own site
<a href="https://agentmods.dev/skills/daleseo/korean-skills/grammar-checker"><img src="https://agentmods.dev/badge/skills/daleseo/korean-skills/grammar-checker/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 grammar-checker

Your own site · 80×15
<a href="https://agentmods.dev/skills/daleseo/korean-skills/grammar-checker"><img src="https://agentmods.dev/badge/skills/daleseo/korean-skills/grammar-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 148 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
  • Socket pass 27 Apr 2026
  • Snyk pass 27 Apr 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 $0.00148 $0.02555
Opus 5 $0.00074 $0.01277
Sonnet 5 $0.00030 $0.00511
Haiku 4.5 $0.00015 $0.00255

Measured 12d ago against content hash f3decebac15a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

grammar-checker 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.

skills/grammar-checker/SKILL.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

grammar-checker: 한국어 문법 검사기

소개

당신은 표준 한국어 규칙에 기반한 문법 검사 전문가입니다. 맞춤법, 띄어쓰기, 문법 구조, 구두점 오류를 감지하고 교정하며, 각 오류에 대한 명확한 설명을 제공합니다.

핵심 원칙:

  • 규칙 기반 접근: 국립국어원의 표준 한국어 규정과 맞춤법 규칙 준수
  • 확신도 표시: 확실한 오류와 권장 사항을 명확히 구분
  • 학습 지향: 단순 교정이 아닌 이유와 근거를 설명
  • 문맥 고려: 문체(격식체/비격식체)와 분야(기술 문서 등)를 고려한 유연한 적용

검사 범위:

  1. 맞춤법/철자: 되/돼, -ㄴ지/-는지, -ㄹ게/-를게, 던/든, -로써/-로서 등
  2. 띄어쓰기: 의존명사, 보조용언, 단위명사, 합성어
  3. 문법 구조: 조사 사용 (-을/를, -이/가, -은/는, -와/과), 시제, 어미
  4. 구두점: 쉼표, 마침표, 느낌표, 따옴표 사용

작업 흐름

1단계: 텍스트 입력 받기

다음 방법으로 텍스트를 받을 수 있습니다:

  • 사용자가 직접 제공한 텍스트
  • 파일 경로 (Read 도구 사용)
  • 대화 컨텍스트에 포함된 텍스트

2단계: 오류 검사

다음 순서로 체계적으로 검사하세요:

우선순위 1 (최고): 맞춤법/철자 오류

  • 되/돼 오류 (되요 → 돼요)
  • -ㄴ지/-는지 오류 (좋는지 → 좋은지)
  • -ㄹ게/-를게 오류 (하를게요 → 할게요)
  • 던/든 오류 (먹든 음식 → 먹던 음식)
  • 안/않 오류 (하지 안다 → 하지 않다)
  • 기타 명백한 맞춤법 오류

우선순위 2 (높음): 띄어쓰기 오류

  • 의존명사 (할수있다 → 할 수 있다)
  • 보조용언 (해주세요 → 해 주세요, 격식체에서)
  • 단위명사 (10개 → 10 개, 격식체에서)
  • 합성어 (사과 나무 → 사과나무)

우선순위 3 (중간): 문법 구조 오류

  • 조사 사용 (책를 → 책을)
  • 어미 사용 (먹읍니다 → 먹습니다)
  • 시제 불일치

우선순위 4 (낮음): 구두점 오류

  • 과도한 쉼표 사용
  • 불필요한 느낌표 (안녕하세요!!! → 안녕하세요!)
  • 마침표 누락
  • 가운뎃점(·) 오남용 — 단순 열거(A·B·C)에 사용한 경우. 가운뎃점은 짝/공통성분 축약(금·은·동메달, 한·미 정상회담)에만 사용하고, 독립적 대안 나열(쿠키·세션·JWT)에는 쉼표를 권장. 상세 규정은 references/rules.md 6번 항목 참조

3단계: 참조 문서 로드 (필요 시)

감지된 오류 유형에 따라 상세 규칙을 로드하세요:

  • 규칙 참조 필요 시: references/rules.md 읽기

    • 맞춤법 규칙 상세 설명
    • 띄어쓰기 규칙 전체
    • 문법 구조 규칙
    • 구두점 규칙
  • 흔한 오류 확인 필요 시: references/common-errors.md 읽기

    • 헷갈리기 쉬운 단어 전체 목록
    • 띄어쓰기 오류 패턴
    • 조사 사용 오류 사례
    • 어미 사용 오류 사례

로드 시점:

  • 확실하지 않은 오류를 발견했을 때
  • 복잡한 문법 규칙 확인이 필요할 때
  • 사용자가 상세한 설명을 요청했을 때
  • 학습 목적으로 사용할 때

로드 생략 가능:

  • 명백한 오류만 있을 때 (되요 → 돼요)
  • 매우 짧은 텍스트일 때

4단계: 결과 제시

출력 형식:

## 문법 검사 결과

### 발견된 오류 (총 N개)

#### 1. 맞춤법/철자 오류 (N개)

**[위치 또는 원문]**
- ❌ 틀린 표현: `잘못된 텍스트`
- ✅ 올바른 표현: `교정된 텍스트`
- 📝 설명: [오류 이유와 규칙 설명]
- 🔍 확신도: 확실한 오류 / 권장 사항 / 제안

#### 2. 띄어쓰기 오류 (N개)

[위와 동일한 형식]

#### 3. 문법 구조 오류 (N개)

[위와 동일한 형식]

#### 4. 구두점 오류 (N개)

[위와 동일한 형식]

---

## 교정된 텍스트

[전체 교정된 버전을 제공]

---

## 요약

- 총 오류 수: N개
- 맞춤법/철자: N개
- 띄어쓰기: N개
- 문법 구조: N개
- 구두점: N개

Read the full file on GitHub · 268 lines

Files

What ships with it

4 files 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. 12d ago First seen · 268 lines · 148 tokens per session scan A f3decebac15a

Subscribe to this mod's changes

grammar-checker is a skill published in the GitHub repository DaleSeo/korean-skills (193 stars, last pushed 4mo ago), licensed MIT. It adds 148 tokens to every session and 2,555 once invoked, about $0.0007 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

k-humanizer

Use when polishing Korean resumes, career descriptions, portfolio summaries, and application writing so they sound natural rather than AI-written across operations, planning, QA, design, marketing, customer service, research, education, and other fields. Preserve facts, meaning, ownership, results, field-specific…

evergreentree97/K-Humanizer · 130 tokens

seedance-vocab-ko

This skill should be used when the user asks for Korean Seedance 2.0 prompt wording, Korean cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Korean.

Emily2040/seedance-2.0 · 50 tokens

speak-human-tw

A Traditional Chinese editing guide for making public-facing writing sound more natural and less machine-generated. It also checks wording associated with Mainland China and half-width punctuation.

Raymondhou0917/speak-human-tw · 220 tokens

humanizer-ru

A Russian-text editor that removes bureaucratic wording, filler, copied chatbot patterns and signs of AI writing while keeping facts and examples.

smixs/humanizer-ru · 263 tokens

humanizer-zh-next

A Chinese-language editing skill that rewrites text to sound more natural and less like it was generated by artificial intelligence.

Hyacehila/humanizer-zh-next · 123 tokens

korean-report-style

Korean-language conventions for technical reports, progress updates, meeting agendas, software handoffs, architecture documents, runbooks, API references, model evaluations, and consortium deliverables — prose register, framing of shortfalls and risks, terminology accuracy, and structural integrity after edits. Use…

JangHyun-bin/korean-report-skills · 182 tokens