PluginBench
Skill
Review
Audit score 70

korean-spell-check

nomadamas/k-skill

Conservative Korean spell-check and proofreading with change-focused suggestions.

What is korean-spell-check?

Proofread Korean text using the Nara/PNU spell-check engine. Handles long input by chunking and returns focused correction suggestions rather than full rewrites. Use when you need reliable Korean grammar and spelling validation.

  • Detects spelling and grammar errors in Korean text
  • Chunks long input to handle large documents efficiently
  • Returns change-focused correction suggestions
  • Uses conservative Nara/PNU spell-check surfaces
  • Provides actionable proofreading feedback

How to install korean-spell-check

npx skills add https://github.com/nomadamas/k-skill --skill korean-spell-check
Prerequisites
  • Node.js 18 or later
  • npx package manager access
Claude Code
Cursor
Windsurf
Cline

How to use korean-spell-check

  1. 1.Run `npx -y @nomadamas/k-skill@0 instruct korean-spell-check` to retrieve full runtime-specific instructions
  2. 2.Review the helper files with `npx -y @nomadamas/k-skill@0 files korean-spell-check`
  3. 3.Pass Korean text to the spell-check function
  4. 4.Review the returned correction suggestions
  5. 5.Apply changes as needed to your text

Use cases

Good for
  • Proofread Korean-language documents before publication
  • Validate user-submitted Korean text in applications
  • Correct spelling and grammar in Korean content
  • Batch-process multiple Korean texts for quality assurance
  • Identify and suggest fixes for common Korean writing errors
Who it's for
  • Korean content creators and writers
  • Developers building Korean-language applications
  • QA teams validating Korean text quality
  • Localization specialists working with Korean content

korean-spell-check FAQ

What spell-check engine does this use?

It uses the Nara/PNU Korean spell-check surfaces, which provide conservative and reliable Korean grammar and spelling validation.

How does it handle very long documents?

The skill automatically chunks long input into manageable pieces to process efficiently while maintaining accuracy.

What format are the corrections returned in?

Corrections are returned as change-focused suggestions highlighting specific errors and proposed fixes, rather than full text rewrites.

Is there a CLI setup required?

Yes, you must run the `instruct` command first to get runtime-specific instructions for your environment (Dolshoi vault/CloakBrowser or generic).

What languages does this support?

This skill is designed specifically for Korean (ko-KR) text proofreading.

Full instructions (SKILL.md)

Source of truth, from nomadamas/k-skill.


name: korean-spell-check description: Use Nara/PNU Korean spell-check surfaces conservatively to proofread Korean text, chunk long input, and return change-focused correction suggestions. license: MIT metadata: category: writing locale: ko-KR phase: v1

korean-spell-check

<!-- k-skill:cli-stub — generated by scripts/generate-skill-stubs.js; edit skill.json / instruction.md instead -->

Get the full instructions (required first step)

Run this and follow its output as the primary instructions for this skill:

npx -y @nomadamas/k-skill@0 instruct korean-spell-check

The CLI detects the current runtime (Dolshoi vault/CloakBrowser vs generic) and prints only the applicable instructions, always up to date. Helper files bundled with the CLI are listed by:

npx -y @nomadamas/k-skill@0 files korean-spell-check

Keep the CLI and every coding-agent skill install current (including Vercel Agent Skills) with:

npx -y @nomadamas/k-skill@0 update

If npx is unavailable, install Node.js 18+ or follow https://github.com/NomaDamas/k-skill#readme, or read the source instructions at https://github.com/NomaDamas/k-skill/blob/main/korean-spell-check/instruction.md.

Hard rules even without the CLI

  • Never execute payment, message/email delivery, final submission, cancellation, or public posting without the user's explicit approval immediately beforehand.
  • Never ask for, print, or store plaintext credentials in chat, files, or shell arguments.
  • Never bypass legal, physical-presence, CAPTCHA, identity-proofing, or electronic-signature boundaries.