중국어 또는 영어 산문, 기술 지침, 제품 카피를 재작성 및 다듬으며 AI 생성 패턴을 제거합니다.
- GitHub 스타
- 7,574
- 파일
- 14
- 마지막 커밋
- 2026년 11월 11일
- 라이선스
- MIT
- 허용된 도구
- —
write skill은 무엇을 하나요?
write은(는) agent skill입니다. 중국어 또는 영어 산문, 기술 지침, 제품 카피를 재작성 및 다듬으며 AI 생성 패턴을 제거합니다.
skill의 SKILL.md에서 생성된 요약입니다.
write skill 정보
작가와 기술 팀이 산문을 인간이 쓴 것처럼 다듬고 인위적인 AI 패턴을 제거할 수 있도록 지원합니다. 중국어와 영어 텍란 모두 작동하며 기술 지침, 제품 카피, 소셜 미디어 게시물을 정교하게 다듬습니다. 사용자가 초안을 편집하거나, 콘텐츠를 현지화하거나, 복잡한 문서를 명확하게 해야 할 때 에이전트가 이 SKILL을 로드해야 합니다. 감지된 언어와 대상 독자에 따라 올바른 언어 규칙과 톤을 적용하기 위해 write-zh.md 또는 write-technical.md와 같은 특정 참조 파일을 사용합니다.
과도하게 다듬거나 새로운 어휘를 만들어내는 일반적인 편집기와 달리, 이 도구는 반복적이거나 정형화된 문구를 제거하기 위한 '뺄셈'에 집중합니다. 문장 부호와 문자 혼용이 높은 기준을 충족하도록 보장하면서 원작자의 의도, 리듬, 감정적 강도를 보존합니다. 저장소 기반 작업의 경우, 조용히 재작성하는 대신 범위가 지정된 diff를 생성하여 사용자가 특정 변경 사항을 거부할 수 있도록 합니다. 이 도구는 산문과 문서 작성을 위해 특별히 설계되었으며, 코드 주석이나 커밋 메시지 작성용이 아닙니다.
agent가 수행할 수 있는 작업
- 1AI 생성 톤 제거초안에서 인위적인 패턴을 제거하여 산문이 더 자연스럽고 인간이 쓴 것처럼 들리게 합니다.
- 2기술 문서 다듬기가독성을 높이기 위해 설치 단계, 작동 지침 또는 도구 설명을 명확하게 합니다.
- 3이중 언어 현지화 검토중국어와 영어 쌍의 번역 정확도 및 용어 일관성을 확인합니다.
- 4소셜 미디어 게시물 초안 작성특정 공지 규칙과 원어민의 리듬을 따르는 Twitter 또는 X 게시물을 작성합니다.
skill의 SKILL.md를 기반으로 작성되었습니다. 모든 사용 사례는 해당 문서의 인용구와 대조 확인되었습니다.
write skill 설치 방법
각 명령은 skill 폴더를 클라이언트의 skills 디렉터리에 복사합니다. 클라이언트를 재시작하거나 새 세션을 시작하여 로드하세요.플러그인에 write skill 설치
/plugin marketplace add tw93/Waza /plugin install waza@waza
Claude Code에 write skill 설치
~/.claude/skills/write/SKILL.md
$ npx degit tw93/Waza/skills/write ~/.claude/skills/writeClaude Code (project)에 write skill 설치
.claude/skills/write/SKILL.md
$ npx degit tw93/Waza/skills/write .claude/skills/writeCodex에 write skill 설치
~/.agents/skills/write/SKILL.md
$ npx degit tw93/Waza/skills/write ~/.agents/skills/writeGemini CLI에 write skill 설치
~/.gemini/skills/write/SKILL.md
$ npx degit tw93/Waza/skills/write ~/.gemini/skills/writeClaude.ai에 write skill 설치
npx degit tw93/Waza/skills/write write && zip -r write.zip write # claude.ai → Customize → Skills → + → Create skill → Upload a skill → write.zip
자동 검사
2026년 11월 15일에 실행됨전체 보고서 →자동 검사를 통과했습니다. 보안 감사는 아닙니다. 에이전트가 실행하기 전에 스크립트를 읽어 보세요. 검사 방식
- 소스 저장소 연결 및 접근 가능tw93/waza/skills/write is public and reachablegithub.com/tw93/waza/tree/HEAD/skills/write ↗통과
- 오픈 소스 라이선스 (OSI)MITspdx.org/licenses/MIT.html ↗통과
- 최근 1년 내 커밋 또는 릴리스Last commit 2026-11-11github.com/tw93/waza/commits ↗통과
- 스크립트에 다운로드 후 실행이나 자격 증명 탈취가 없음2 scripts read; no download-and-run, remote eval, base64 execution or credential upload통과
- SKILL.md에 숨겨진 지침 없음No override phrases, safeguard switches, credential requests or hidden charactersgithub.com/tw93/waza/blob/HEAD/skills/write/SKILL.md ↗통과
- 사전 허용 도구가 제한됨No pre-approved tools; the agent asks before using onegithub.com/tw93/waza/blob/HEAD/skills/write/SKILL.md ↗통과
- SKILL.md가 Agent Skills 형식을 따름Valid name and description; says when to use it; 130 linesgithub.com/tw93/waza/blob/HEAD/skills/write/SKILL.md ↗통과
SKILL.md
GitHub에서 보기Write: 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: 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. Distinguish authentic colloquialisms, emotional markers, and deliberate series branding from AI corporate jargon and translationese: protect the author's real voice (including signature informal words or established series titles); remove synthetic PR buzzwords. 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
- 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.
- 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.
- 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.mdon top ofreferences/write-zh.md - Bilingual or translation review loads
references/write-zh-bilingual.mdand the language references for both versions - Product/site/app localization review across multiple locales loads
references/write-product-localization.md; also loadreferences/write-zh-bilingual.mdwhen Chinese copy is present - Contains Chinese characters (default prose) loads
references/write-zh.md - Otherwise loads
references/write-en.md
- Contains Chinese characters + release notes or social post mode loads
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.
| Ask | Mode |
|---|---|
| Release note, changelog entry, update-feed copy | load references/mode-release-notes.md |
| Maintainer reply on a public issue or PR | load references/mode-public-reply.md |
| Installation steps, operating instructions, error text, or tool descriptions to clarify; wording-only edits to agent instructions | load references/write-technical.md for those passages, alongside the language reference; prompt design and code behavior stay outside this mode |
| Long draft with several sections, tables, or images that needs structural work | load references/mode-long-form.md |
| Before/after versions of the same text (a diff, two drafts, another editor's polish pass) and "is the new one better?" | load references/mode-revision-review.md |
| EN/CN pair or mixed Chinese/English copy to check for drift | load references/write-zh-bilingual.md, which owns the judgment the Punctuation Gate does not check |
| Product, site, or app copy across locales ("本地化文案", "多语言文案", "localization copy", "i18n copy", runtime catalog, release feed copy) | load references/write-product-localization.md and follow its review procedure; add references/write-zh-bilingual.md when Chinese is a locale |
| Document, PDF, or white paper to review | Document Review |
| Paragraphs that read disconnected | Paragraph Coherence |
| Tweet, thread, or launch post | Tweet / Social Post |
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"
Load references/write-zh-release-notes.md for the five announcement rules (community lead, highlights over completeness, UX framing, one stance, native rhythm) and the casual invitation close. For English posts or projects without that community voice, keep the same structure in the project's own voice.
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.mdtreats 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. Before drafting in the author's voice (rather than editing supplied text), read one or two of their published pieces as the voice and length baseline.
- 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. A material the intended reader would already predict (common sense, consensus advice, the topic's standard talking points) does not count either; if no section carries something that reader would not have guessed, ask the author for the surprising part instead of drafting the predictable version. 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.
- No em-dash. Never produce em-dash (U+2014) or en-dash (U+2013) in Chinese or English output, and replace every one in an edited draft; it is the strongest AI-tone fingerprint here. Use commas, periods, colons, or parentheses; hyphen-minus inside compound words is allowed.
- 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
Before returning any produced text (a rewrite, or generated release / reply / social copy), resolve the checker across install layouts and run it:
GATE=""
for candidate in \
"<skill-base-dir>/scripts/check-punctuation.sh" \
"<skill-base-dir>/skills/write/scripts/check-punctuation.sh"; do
[ -f "$candidate" ] && GATE="$candidate" && break
done
[ -f "${GATE:-}" ] || { echo "punctuation gate not found under the installed skill base; reinstall Waza" >&2; exit 1; }
bash "$GATE" --lang <zh|en|ja|auto> <file> # or pipe text via stdin
Replace <skill-base-dir> with the installed Write skill or Waza dispatcher directory. The first path covers direct/plugin installs; the second covers the inlined-root release ZIP.
It enforces character-level punctuation by locale and skips code, URLs, and link targets; the script header documents the rules, --fix, and --lang auto routing. Fix every finding while preserving meaning, and pass an explicit --lang for mixed-locale or predominantly-English text. Quote direction and other judgment calls stay with you and the reference files.
Gotchas
| What happened | Rule |
|---|---|
| User flagged one word as "not my voice"; only that instance was fixed | A flagged word marks a smell class, not a typo. Sweep the whole text for the same class (same register, same template shape) before returning |
| A copy-fix batch passed its checks but shipped new defects: a line now wider than its fixed-width slot, a boundary that lost its subject, a noun that reads two ways | Re-review the fix diff itself, starting with paragraphs that were rewritten or re-translated whole. Restored text carries its old defects too; flag them instead of silently re-editing the restoration |
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.
이 스킬의 파일
14write skill 질문
Claude Code에 write skill을 어떻게 설치하나요?
npx degit tw93/Waza/skills/write ~/.claude/skills/write를 실행합니다. Claude Code는 ~/.claude/skills(모든 프로젝트) 또는 .claude/skills(한 프로젝트)에서 skills를 로드하며, 설명이 작업과 일치할 때 skill을 사용합니다.
write skill을 사용할 수 있는 클라이언트는 무엇인가요?
Agent Skills 형식을 읽는 모든 클라이언트(Claude Code, Codex, Gemini CLI, claude.ai(ZIP으로 업로드))가 사용할 수 있습니다. skill 내 스크립트는 클라이언트가 코드 실행을 허용하는 경우에만 실행됩니다.
어떤 종류의 텍스트를 처리할 수 있나요?
중국어 또는 영어 산문, 기술 지침, 그리고 릴리스 노트, 소셜 게시물, 문서와 같은 제품 카피를 위해 설계되었습니다.
코드 주석을 작성하는 데 사용할 수 있나요?
아니요, 이 SKILL은 코드 주석이나 커밋 메시지용으로 설계되지 않았습니다.
작가의 원래 문체를 어떻게 유지하나요?
작가의 스타일을 대체하기보다는 인위적인 AI 패턴을 제거하는 데 집중하여, 작가의 의도, 리듬, 개인적 신념을 보존하는 것을 목표로 합니다.