Write: Cut the AI Taste

来源：基于 Tw93 / Waza 的 write 技能 改编。保留 Tw93 的 MIT 版权声明。

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 mixed-language typography match the user's or project's conventions, with the optional checker used only where its rules apply.
• Evidence: supplied text, target audience, project style references, release or product state, and requested language.
• Output: edited prose for pasted text; for repository edits, a scoped diff and the requested verification or delivery receipt.

Durable Context Preflight

See references/durable-context.md for when durable context is in scope and the redaction gate that applies before any of it becomes a durable rule.

For /write: the supplied text and current release state override memory. Durable preferences can set brevity, tone, and social-post shape; they do not override the hard rule to edit in place, keep meaning intact, and avoid change lists unless the user explicitly asks or the input is the author's own finished draft.

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 are catalogs; 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. When the input is the author's own finished draft, the default scope shrinks to typos, broken sentences, and clear AI tells: never rewrite their sentences for style, and return a per-sentence list of every deleted or rewritten sentence so the author can veto each one.
• A piece has a speaker. Smooth prose that could belong to anyone has lost something. Keep the author's colloquial words, cadence, knowledge and judgments; deliberate authorial or genre choices take precedence over these defaults. The author's affection, frustration, pride, gratitude and personal convictions are content, even when abstract or phrased as a conclusion. Preserve their intensity; do not require external evidence for a feeling or replace it with a neutral observation. Read nearby paragraphs and author revisions to separate a real stance from stock rhetoric. If that distinction is uncertain, keep the sentence. Do not invent emotion or turn "what I did" into "what you must do."
• 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. When source material exists, check it before flagging the author's wording; restore their words rather than paraphrasing them. When restoring copy, trace that passage's diffs to the nearest version before the unwanted edit and compare the restored text exactly; do not choose an older, shorter version or rewrite unrelated paragraphs.
• Prefer fewer, stronger edits. Three changes that matter beat thirty mechanical swaps that flatten the voice.

Pre-flight

1. Locate the text. Read named files or discover posts in the supplied repository before asking the user to paste anything. For "latest N," freeze the dated article set and its language mirrors, then account for each as edited, unchanged with reason, or unavailable.
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 loads references/write-zh-release-notes.md on top of references/write-zh.md
   • Bilingual or translation review loads references/write-zh-bilingual.md and the language references for both versions
   • Product/site/app localization review across multiple locales loads references/write-product-localization.md; also load references/write-zh-bilingual.md when Chinese copy is present
   • Contains Chinese characters (default prose) loads references/write-zh.md
   • English prose loads references/write-en.md
   • Other languages follow their own conventions and the supplied style; do not classify every non-Chinese text as English

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.

Document Review Mode

Activate when: PDF, document, white paper, "review this document", "check this document", "审稿"

Review checklist:

• Privacy scan: Flag sensitive information whose disclosure is not authorized for the intended audience. Preserve identity and experience the author explicitly supplies for this document or has already published; job seeking, employer names, and locations alone are not grounds to stop or delete content. Resolve uncertain disclosure before exposing it.
• Tone consistency: Flag voice shifts, register mismatches, formulaic phrasing.
• Bilingual validation: For CN/EN pairs, confirm translation accuracy and terminology consistency with references/write-zh-bilingual.md.
• Rendering check: Placeholder text remaining (Lorem ipsum, TODO, [TBD]), broken image links.
• Durable-doc scan: If the document is a review report, scorecard, or diagnostic snapshot, flag dated claims, stale line references, private paths, repo-specific commands, and current-score framing. Recommend extracting stable rules instead of preserving the snapshot as evergreen guidance.

Output format: follow the requested review or rewrite; mention privacy only when an actionable disclosure concern remains.

Paragraph Coherence Mode

Activate when: "连贯性", "段落连贯", "可读性", "coherence", "flow check", "段落顺不顺"

Check unsignalled topic shifts, openings that do not follow the previous close, and monotone sentence length across a paragraph. Each fix is the minimal one: one word, one reordered clause, or one bridging sentence. Review requests get a numbered list with paragraph locations; explicit rewrite or file-edit requests get the minimal authorized edits without asking again.

Tweet / Social Post Mode

Activate when: "推特", "twitter", "X推文", "tweet", "social post", "折叠长度", "长文推特", "发文"

Use references/write-zh-release-notes.md when writing a Chinese announcement or release note. Choose the structure and tone from the actual audience, source material and platform; community thanks, a personal stance and an invitation close are optional, not required parts of every post.

Hard Rules

• Meaning first, style second. If removing an AI pattern would change the author's intended meaning, keep the original. Removing promotion does not remove legitimate product descriptions, licensing information, or related-product explanations. Broad copy cleanup does not authorize rewriting attributed quotations or testimonials; preserve their wording unless explicitly included in the edit scope, and distinguish any paraphrase from a verbatim quote.
• No silent restructuring. Do not reorganize headings, reorder paragraphs, or merge sections unless structural changes are explicitly requested. Edit in place. Structural assets are not cleanup noise: image placeholders, links, frontmatter, and example blocks stay unless the user asked to remove them, and any deletion gets listed with its reason instead of discovered later in the diff. (Exception: references/mode-long-form.md treats structural cuts and merges as in-scope, since structure is the main problem there; it still proposes them as change-points first instead of doing them silently.)
• No invented first-person experience. When ghostwriting as the author, every personal anecdote, tool history, opinion, and quote must come from the supplied material or the author's published writing, and so does any color used to replace a flagged phrase: fix by subtraction, not by fresh imagery. The material lacking an example is a question to ask, not a gap to fill. When available and relevant, use the author's supplied or published pieces as a voice baseline. Missing published examples do not block an ordinary draft; use the requested tone without inventing their experiences or opinions.
• Material gate before drafting long-form. When asked to write rather than edit, count what you actually hold before choosing a length: supplied experience, numbers, quotes, actions, and verifiable public sources. A category name is not a material, and a restated idea is not a second material. Reasoning connects material; it does not breed material. If you cannot name a distinct material for each planned section, the plan is longer than the evidence. Resolve it by researching first, asking at most three questions in one round, or shipping a shorter piece. A target word count is not a reason to pad with invented examples or a fourth phrasing of the same point.
• Shorter than the first draft wants to be. Outward copy (README paragraphs, tweets, release notes, maintainer replies) defaults to the length of the user's previously accepted pieces; when a physical constraint exists (tweet fold line, single-line rendering), derive the budget from the constraint before writing, not after the user trims it.
• Artifact-grounded claims. For launch copy, release notes, social posts, product pages, and public replies, ground factual claims in real source material: current app behavior, runnable artifact, screenshot, product page, release page, changelog, issue/PR, or user-provided draft. Do not present handoffs, plans, old memory, or stale screenshots as current product truth, and do not turn concrete product evidence into generic marketing language. Compare the draft against the shipping artifact and tighten until the two agree.
• Typography follows the actual style. Avoid decorative punctuation when it distracts, but punctuation alone is not evidence of AI writing. Preserve intentional author choices, quotations and required titles; apply dash, emoji and spacing restrictions only when the user or target style requires them.
• Route bundled work without dropping it. Code comments and commit messages stay outside this prose skill. When explicitly requested alongside writing, handle them through the appropriate workflow or native capability and keep them in the same completion ledger; this skill grants no extra write or publishing authority.
• Match the requested handoff. Pasted-text rewrites need no explanation, except the per-sentence change list for the author's own finished draft. Repository edits need the scoped diff and verification; complete explicitly authorized commit/push steps under the project's rules. A prose-only output convention must not hide unfinished delivery.

Punctuation Gate

The bundled checker is an optional aid for its documented Chinese, English and Japanese rules. Resolve it at scripts/check-punctuation.sh beside this installed SKILL.md; do not assume a former dispatcher layout. If Bash is unavailable, use the adjacent Python checker with a supported Python runtime, or inspect the typography directly.

bash "<skill-dir>/scripts/check-punctuation.sh" --lang <zh|en|ja|auto> <file>

The helper encodes a strict house style, including dash restrictions. It is not a universal language validator: findings that conflict with the user's style, quotations or intentional author choices are not mandatory edits. Inspect suggestions before applying them; do not run --fix blindly on protected text. Pass an explicit supported language for mixed text. Unsupported languages use an appropriate available tool or manual review, not a false checker pass. Missing optional helpers do not block a simple rewrite.

Gotchas

Output

Follow the Outcome Contract. For batch edits, reconcile the original article set and mirrors before reporting completion. State missing source or verification without treating it as a pass.