novel-deconstruct

Use this skill to turn AI-sounding Italian into natural prose without flattening the author's facts, argument, register, or voice. It applies an Italian-specific editorial workflow covering syntax, punctuation, cohesion, rhetoric, clichés, and common generative habits, and it can also answer usage questions. The skill knows when informal keyboard conventions should be left alone; its instructional content is in Italian.

This Claude Code skill detects Russian bureaucratic phrasing, English calques, inflated claims, chatbot artifacts, structural habits, and typography patterns. It offers modes for social posts, business letters, personal messages, copywriting, and AI-style audits, with optional voice calibration from sample texts.

Use the skill to draft or review buttons, errors, empty states, forms, and complete user flows. It diagnoses the most important problems before rewriting, follows a reusable voice profile, and checks accessibility, localization readiness, and manipulative choice framing. Legal language, financial disclosures, consent wording, and verbatim quotations are flagged with suggestions rather than silently changed.

Polish Korean LLM output by targeting stiff formality, empty intensifiers, filler connectives, template openings, hidden agents, excessive hedging, and other catalogued patterns while preserving the text’s meaning. The repository includes a prompt and skill for Claude Code and Codex, plus a shorter prompt for other LLMs.