
If you've ever had a Korean college application or job form reject your carefully written essay because you were off by three characters, this is for you. It counts Korean text deterministically using Unicode grapheme clusters, not LLM guesses. You get exact character, line, and byte counts with two profiles: default uses UTF-8 encoding, while neis follows the byte rules used by Korea's education records system. It doesn't trim or normalize your input, just counts what's actually there. Runs as a Node.js helper script with no API keys needed. Honestly, it's solving a very specific problem, Korean form limits with exact counting requirements, but it solves it correctly.
npx -y skills add nomadamas/k-skill --skill korean-character-count --agent claude-codeInstalls into .claude/skills of the current project.
Run this and follow its output as the primary instructions for this skill:
npx -y @nomadamas/k-skill@0 instruct korean-character-count
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-character-count
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-character-count/instruction.md.