No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by snflkd · Claude Skill · ★ 696
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is fluent-korean safe to install? View the security audit →
fluent-korean (Claude Code output-style) 이 플러그인은 LLM, 특히 클로드와 코딩 에이전트가 명확한 한국어를 유창하게 구사하도록 지시하는 출력 스타일을 제공합니다. 수려한 문체보다는 확실한 의미 전달을 추구하며, 비교적 자연스러운 문장을 목표로 합니다. 한국어로 명령을 입력하는 경우, 작업 결과물에 한국어가 포함된 경우에 특히 유용합니다. Claude Code 환경에 적합한 Plugin이지만, 글쓰기 지침에 해당하는 텍스트를 적절하게 활용하면 다른 AI에도 적용할 수 있습니다. 설치법은 아래에서 다시 자세하게 설명드리겠으나, 현재 사용 중인 LLM에게 아래와 같이 한 문장으로 말하는 것을 추천드립니다. EN: A Claude Code output style that stops Claude from writing broken machine-Korean: dropped particles and endings, telegraphic noun strings, and metaphor-swapped vocabulary. It prioritizes clear, unambiguous meaning over elegant prose, aiming for reasonably natural sentences. Ships as two variants: one that keeps Claude Code's coding instructions, and one without them. The guideline text itself can also be pasted into other AI environments as a plain writing instruction. Written by a Korean-literature major; the Korean parts of this README are human-written. If you're at Anthropic and want Claude to write proper Korean, the maintainer would love to hear from you. 왜 필요한가 최근 AI 모델은 한국어를 능숙하게 쓰지 못하는데, 토큰 사용량을 낮추고 컨텍스트 제한에 대응하기 위해 말을 간결하게 하도록 설정된 코딩 에이전트들은 더 그렇습니다. 이런 현상을 최대한 개선하는 도구가 바로 fluent-korean입니다.
| Stars | 696 |
| Forks | 52 |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 61.9247498846841/100 |
| Last Updated | 2026-08-23 |
| Created | 2026-07-10 |
| Platforms | claude-code |
| Est. Tokens | ~9k |
These tools work well together with fluent-korean for enhanced workflows:
Looking for a fluent-korean alternative? If you're comparing fluent-korean with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
AI-writing humanizer for KO/EN/ZH/JA
200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture.
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
🎭 AI 写小说：从零生成 10-50 章完整中文小说，三层问答 · 创作记忆 · 悬念钩子 · 自动校验，长篇网文连载皆宜｜开源免费，适配主流 coding agent｜AI novel writing skill
Conquer Any Code in VSCode: One-Click Comments, Conversions, UI-to-Code, and AI Batch Processing of Files! 在 V
A practical Claude Code guide with clear mental models and copy-paste examples — setup, prompt engineering, sl
Explore other popular claude skill tools:
fluent-korean is Claude Code가 명확한 한국어를 구사하게 만드는 output-style 플러그인 | Claude Code output-style for clear, fluent Korean. It is categorized as a Claude Skill with 696 GitHub stars.
You can find installation instructions and usage details in the fluent-korean GitHub repository at github.com/snflkd/fluent-korean. The project has 696 stars and 52 forks, indicating an active community.
fluent-korean is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to fluent-korean on Agent Skills Hub include patina, claude-skills, claudepro-directory. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: