Style DNA Ghostwriter — AI skill for Claude Code

---

The problem

Style guides and linters only enforce rules a team bothered to *write down*. The rest of a codebase's real personality — how errors get handled, how components get structured, whether arrow functions or declarations are preferred, how Tailwind utilities or CSS modules are used, how verbose docstrings actually are — lives nowhere except the code itself. AI-generated code ignores all of that and defaults to generic, textbook style, which is exactly what makes it stand out as not-quite-belonging.

**Style DNA Ghostwriter** fixes this by learning conventions the way a new senior engineer would: by reading the code, not the wiki page nobody updated.

$ style-dna analyze ./my_web_app

Analyzed 42 files from './my_web_app' (0 Python, 42 Web).
Style profile saved to: style_profile.json

## Web Conventions
- Detected frameworks/tools: Next.js, React, Tailwind CSS, TypeScript.

### JavaScript / TypeScript
- Use single quotes for JS/TS strings.
- Omit semicolons at end of statements.
- Prefer arrow functions (`const fn = () => {}`).
- Prefer named exports.
- Use path aliases (`@/...`) for imports instead of deep relative paths.
- Prefer `interface` over `type` for object shapes in TypeScript.

### React / Next.js
- Next.js routing: App Router (`app/`).
- Define React components as arrow functions (`const Button = () => ...`).
- Component file naming: PascalCase.
- ~40% of components use 'use client' directive.
- State management: zustand.