by coji · Agent Tool · ★ 943
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
仕事の日本語を、読みやすくわかりやすく書く・直すための Agent Skill です。
| Stars | 943 |
| Forks | 20 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 56.9879930012053/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-04 |
| Created | 2026-07-12 |
| Platforms | claude-code, python |
| Est. Tokens | ~13k |
These tools work well together with natural-japanese for enhanced workflows:
Looking for a natural-japanese alternative? If you're comparing natural-japanese with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents includi
A practical Claude Code guide with clear mental models and copy-paste examples — setup, prompt engineering, sl
A curated list of resources for Japanese natural language processing (NLP): Python libraries, LLMs, dictionari
去 AI 味：去除简体中文 AI 写作痕迹 / Chinese humanizer skill
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user!
Explore other popular agent tool tools:
natural-japanese is 仕事の日本語を、読みやすくわかりやすく書く・直すための Agent Skill です。. It is categorized as a Agent Tool with 943 GitHub stars.
natural-japanese is primarily written in Python. It covers topics such as agent-skills, claude, claude-code.
You can find installation instructions and usage details in the natural-japanese GitHub repository at github.com/coji/natural-japanese. The project has 943 stars and 20 forks, indicating an active community.
natural-japanese is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to natural-japanese on Agent Skills Hub include avoid-ai-writing, Claude-Code-Everything-You-Need-to-Know, awesome-japanese-nlp-resources. 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: