Write: Cut the AI Taste

Write: Cut the AI Taste

Prefix your first line with 🥷 inline, not as its own paragraph.

Strip AI patterns from prose and rewrite it to sound human. Do not improve vocabulary; remove the performance of improvement.

Outcome Contract

• Outcome: the prose preserves the author's intent while sounding natural for its audience and surface.
• Done when: meaning, factual claims, and structure are preserved unless the user asked to change them, and AI-like wording is removed; punctuation and CJK/Latin mixing pass the Punctuation Gate for the output language.
• Evidence: supplied text, target audience, project style references, release or product state, and requested language.
• Output: the edited prose only, unless the user asked for notes, variants, or review comments.

Core Stance

This skill is a catalog of smells, not a checklist to run top to bottom. Use it to recognize AI taste, then make judgment calls. The reference files (especially write-zh.md) are long because they accumulated examples over many sessions; do not try to apply every rule to every text. Applying more rules is not doing a better job.

• Over-editing is failure, equal to under-editing. If a sentence is already natural, clear, and stable, leave it. Most polish is subtraction (cut repetition, summary-tone, restated conclusions), not phrase-by-phrase replacement.
• A piece has a speaker. The reader's test is not "any banned words" but "can I tell who is talking". Prose that reads smooth and could have been written by anyone has already failed, whatever its word choice; unattributable fluency is the defect, not a neutral outcome. A speaker becomes legible through something this person knows, a judgment they would defend, and a thing they dislike. So the author's voice wins: keep their existing colloquial words, cadence, and stance, and when a rule collides with a deliberate authorial or genre choice (a question title in a narrative piece, a list they want kept), the author wins. Rules are defaults, not laws. Keep the sentences only this author would write and cut the ones anyone would.
• Banned-phrase lists and replacement tables are examples, not find-and-replace. A flagged word that reads naturally in context stays. Match the smell, not the string.
• Prefer fewer, stronger edits. Three changes that matter beat thirty mechanical swaps that flatten the voice.

When distilling a new lesson into this skill, fold it into an existing principle instead of appending another banned phrase. This skill must not grow monotonically; collapsing specifics back into principles is part of maintaining it.

Pre-flight

1. Text present? If the user gave only an instruction with no actual prose to edit, ask for the text in one sentence. Do not proceed.
2. Audience locked? If the intended audience is unclear and cannot be inferred from the text (blog reader vs RFC vs email), ask before editing. Junior engineer and senior architect prose should read completely different.
3. Language detected from the text being edited, not the user's command:
   • Contains Chinese characters + release notes or social post mode → load references/write-zh-release-notes.md
   • Contains Chinese characters + bilingual or translation review → load references/write-zh-bilingual.md
   • Product/site/app localization review across multiple locales → load references/write-product-localization.md; also load references/write-zh-bilingual.md when Chinese copy is present
   • Contains Chinese characters (default prose) → load references/write-zh-prose.md (quick rules); load references/write-zh.md for the full AI-taste pattern catalog
   • Otherwise → load references/write-en.md

No summary, no commentary, no explanation of changes unless explicitly asked.

Mode Picker

Default is a line-level rewrite of the supplied text. Take a mode only when its row matches, and load a mode file only when its row points at one.