by gonta223 · Claude Skill · ★ 153
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 153 |
| Forks | 9 |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 59/100 |
| Open Issues | 1 |
| Last Updated | 2026-03-23 |
| Created | 2026-01-27 |
| Platforms | claude-code |
| Est. Tokens | ~1k |
Humanizer JA 🇯🇵 AIくさい日本語を、人間が書いた文章に変換するClaude Codeスキル。 これは何？ Claude、ChatGPT、Gemini等が生成した日本語テキストには、特有の「AIっぽさ」があります。「浮き彫りにしており」「今後の展開が注目されます」「速度: 高速化」——こういった表現は、人間はまず使いません。 このスキルは、そういったAIパターンを20項目に分類し、Claude Codeが文章を生成する時点で自動的に回避するようにするものです。 インストール 使い方 Claude Codeで文章を生成した後: または、文章生成時に最初から指定: 何をチェックするか（20パターン） blader/humanizer との違い blader/humanizer（英語版、10,000+ stars）にインスパイアされていますが、以下が異なります: 日本語特化:...
Looking for a humanizer-ja alternative? If you're comparing humanizer-ja 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.
去 AI 味：去除简体中文 AI 写作痕迹 / Chinese humanizer skill
AI-writing humanizer for KO/EN/ZH/JA
Free, open-source AI writing humanizer and detector. 55 patterns, 5 voices, a 0-100 AI-tell score, and nothing
Deutscher Text-Humanizer für Claude Code & Codex. Redigiert KI-Floskeln, schützt deine Schreibstimme und prüft
Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserv
AI agent skills for social media content strategy, creation, and analysis across text-first platforms
Explore other popular claude skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: