Open-Source natural-japanese Turns AI Writing Rules Into a Claude Agent Skill
A Claude Code agent skill strips the telltale AI smell from Japanese business writing using a 12-rule style constitution and morphological linting.
Takeaways
- natural-japanese is an open-source Agent Skill for writing natural Japanese business documents.
- Ships with a 12-article style constitution enforced before drafting, not after.
- Uses sudachipy morphological analysis in
lint.pyto flag boilerplate, monotone rhythm, and translation-ese. - Includes a
/natural-japanese scorediagnostic that rates naturalness 0 to 100 without editing. - Installs into Claude Code, Cursor, ChatGPT, or Codex via
npx skills addor plugin marketplace. - MIT licensed, over 1,100 GitHub stars, with corpus validation across 180-plus documents.
Large language models often produce Japanese business documents with vague headings, uniformly sized paragraphs, stock transitions, and heavily hedged conclusions. The open-source natural-japanese project addresses those patterns during drafting and revision. Its GitHub repository has passed 1,100 stars.
An Agent Skill packages instructions and tools that an agent can invoke for a specific task. Natural-japanese ships in that format for Claude Code and compatible agents, covering meeting minutes, research reports, internal guides, proposals, and blog posts. Its workflow applies editorial constraints before generating a draft, then checks the result with language-aware scripts.
Lock the outline before drafting
Post-draft requests to “sound more human” often replace one stock phrase with another because the model evaluates prose shaped by its own habits. Natural-japanese divides the work into planning, drafting, linting, and review so those habits can be addressed at several stages.
The first phase fixes the heading structure and applies a style constitution containing 12 drafting rules. Requirements such as leading with the conclusion and varying sentence patterns shape the initial text before formulaic structures spread through the document.