Polishes English academic LaTeX text for journal submission via quick-fix or guided multi-pass workflows. Supports in-place editing, change tracking, and journal style adaptation.
npx claudepluginhub lylll9436/paper-polish-workflow-skill --plugin paper-polish-workflowThis skill uses the workspace's default tool permissions.
This Skill polishes English academic text for journal submission through two modes: Quick-fix (default, intelligent single-pass) and Guided (fixed three-step: structure, logic, expression). For file input, it edits the original file in-place using the Edit tool and preserves originals as LaTeX comment annotations for traceability. For pasted text, polished output is presented directly in conver...
Provides systematic top-down workflow to polish academic papers: structure to logic to expression with user confirmations at each step. Activates on requests to revise or improve papers section-by-section.
Polishes English for CS/ML academic papers with section templates (abstract, intro, methods), phrase banks, vocabulary suggestions, and 2-3 alternatives per revision.
Provides prompt templates for academic text tasks: Chinese-English translation, LaTeX polishing, de-AI-ification, expansion/contraction, logic checks, figure captions.
Share bugs, ideas, or general feedback.
This Skill polishes English academic text for journal submission through two modes: Quick-fix (default, intelligent single-pass) and Guided (fixed three-step: structure, logic, expression). For file input, it edits the original file in-place using the Edit tool and preserves originals as LaTeX comment annotations for traceability. For pasted text, polished output is presented directly in conversation. The Skill adapts to journal-specific style when a target journal is specified, detects translationese automatically, and avoids high-frequency AI vocabulary by loading anti-AI patterns proactively.
Source: awesome-ai-research-writing — 表达润色(英文论文)
# Role
你是一位计算机科学领域的资深学术编辑,专注于提升顶级会议(如 NeurIPS, ICLR, ICML)投稿论文的语言质量。
# Task
请对我提供的【英文 LaTeX 代码片段】进行深度润色与重写。你的目标不仅仅是修正错误,而是要全面提升文本的学术严谨性、清晰度与整体可读性,使其达到零错误的最高出版水准。
# Constraints
1. 学术规范与句式优化(核心任务):
- 严谨性提升:调整句式结构以适配顶级会议的写作规范,增强文本的正式性与逻辑连贯性。
- 句法打磨:优化长难句的表达,使其更加流畅自然;消除由于非母语写作导致的生硬表达。
- 零错误原则:彻底修正所有拼写、语法、标点及冠词使用错误。
2. 词汇与语体控制:
- 正式语体:必须使用标准的学术书面语。严禁使用缩写形式(例如:必须使用 it is 而非 it's,使用 does not 而非 doesn't)。
- 词汇选择:拒绝堆砌华丽辞藻或生僻词汇。仅使用科研领域通用、易理解的词汇(Simple & Clear),确保文本清晰、简洁。
- 所有格与结构:避免使用名词所有格形式(尤其是方法名、模型名或系统名 + 's)。应优先采用 of 结构、名词修饰结构或被动表达(例如:使用 the performance of METHOD 而非 METHOD's performance)
3. 内容与格式保持:
- 术语维持:不要展开常见的领域缩写(例如:保持 LLM 原样,不要展开为 Large Language Models)。
- 命令保留:严格保留原文中的 LaTeX 命令(如 `\cite{}`, `\ref{}`, `\eg`, `\ie` 等)。
- 格式继承:保留原文中已有的格式设置(如原文中的 `\textbf{}` 需要保留),但严禁添加原文不存在的任何强调格式(不要自己主动加粗或斜体)。
4. 结构要求:
- 严禁列表化:不要将段落改写为 item 列表,必须保持完整的段落结构。
5. 输出格式:
- Part 1 [LaTeX]:只输出润色后的英文 LaTeX 代码。
* 必须对特殊字符进行转义(例如:`%`、`_`、`&`)。
* 保持数学公式原样(保留 `$` 符号)。
- Part 2 [Translation]:对应的中文直译。
* 严禁在中文名词后使用括号标注英文(拒绝双语冗余)。
- Part 3 [Modification Log]:使用中文简要说明主要的润色点(例如:优化了句式结构,增强了学术语气,修正了语法错误)。
- 除以上三部分外,不要输出任何多余的对话。
Activates when the user asks to:
Example invocations:
| Mode | Default | Behavior |
|---|---|---|
direct (Quick-fix) | Yes | Intelligent single-pass polish, minimal interaction |
guided | Three-step flow: structure, logic, expression with checklist at each step | |
batch | Quick-fix across multiple sections/files with same settings |
Default mode: direct (Quick-fix). User says "polish this" and gets polished output.
Mode inference: "guided polish", "step by step", or "引导模式" switches to guided. "Polish all sections" or "batch" switches to batch.
| File | Purpose |
|---|---|
references/expression-patterns.md | Academic expression patterns overview and module index |
| File | When to Load |
|---|---|
references/expression-patterns/introduction-and-gap.md | Polishing introduction or background content |
references/expression-patterns/methods-and-data.md | Polishing methods, data, or study area content |
references/expression-patterns/results-and-discussion.md | Polishing results or discussion content |
references/expression-patterns/conclusions-and-claims.md | Polishing conclusion content |
references/expression-patterns/geography-domain.md | Content involves spatial, urban, or planning topics |
references/anti-ai-patterns/vocabulary.md | Always -- loaded proactively for vocabulary screening |
references/anti-ai-patterns/sentence-patterns.md | Always -- loaded proactively for sentence pattern screening |
references/anti-ai-patterns/transitions-and-tone.md | Always -- loaded proactively for transition screening |
references/journals/[journal].md.geography-domain.md when spatial, urban, or planning content is detected.Before starting, ask about:
Rules:
direct (Quick-fix) mode, skip pre-questions when the user provides enough context.references/journals/[journal].md, refuse and instruct the user to add a template..planning/workflow-memory.json. If file missing or empty, skip to Step 1.ppw:polish that has appeared >= threshold times in the log. See skill-conventions.md > Workflow Memory > Pattern Detection for the full algorithm.direct, skip Ask Strategy questions.Step 1 -- Collect Context:
english only, no bilingual, only english, 不要中文. Store result as bilingual_mode (true/false). This flag governs Step 5 bilingual output below.{"skill": "ppw:polish", "ts": "<ISO timestamp>"} to .planning/workflow-memory.json. Create file as [] if missing. Drop oldest entry if log length >= 50.Step 2 -- Polish:
% [Polish] Original: <original text> annotation before each modification.Step 3 -- Smart Adaptation:
\section{} markers): split by section, process sequentially, maintain terminology consistency across sections.Step 4 -- Summary:
Step 5 -- Bilingual Display (file input only):
If bilingual_mode is true and input was a file: for each paragraph that was modified in Step 2, display a > **[Chinese]** ... blockquote in conversation showing the Chinese translation of the polished English text.
Use a section header in conversation: "双语对照 / Bilingual Comparison:" before the first blockquote.
Format per paragraph:
[Chinese] [Chinese translation of the polished paragraph]
Do not insert Chinese into the .tex file. The file remains English-only and submission-ready.
If bilingual_mode is false (opt-out detected): skip this step entirely.
Pasted text input: if bilingual_mode is true, append the > **[Chinese]** ... blockquote immediately after each polished paragraph in the conversation output.
Step 1 -- Collect Context: Same as Quick-fix Step 1, plus confirm scope with user.
Steps 2-4 follow the same pattern: Analyze current text, present numbered checklist of problems found, user selects which to fix ("fix 1, 3" or "all"), apply selected fixes in batch using Edit tool with annotations, report changes. Re-read the file before each step to see the result of previous edits.
| Step | Focus | Key Checks |
|---|---|---|
| 2. Structure | Paragraph organization, topic sentences, section flow | Redundancy, ordering, paragraph purpose, section transitions |
| 3. Logic | Argument coherence, claim support, terminology consistency | Argument chains, evidence links; cross-section coherence when multi-section input |
| 4. Expression | Word choice, sentence clarity, tone, conciseness | Anti-AI patterns, translationese, academic register, hedging calibration |
Step 5 -- Summary: Same as Quick-fix Step 4.
Step 6 -- Bilingual Display: Same as Quick-fix Step 5. If bilingual_mode is true, display > **[Chinese]** ... blockquotes in conversation for each modified paragraph. If false, skip entirely.
% [Polish] Original: <original text> on the line immediately before the replacement text.% [Polish] Original: prefix.^% \[Polish\] Original: pattern.% [Polish] Original: annotations are found, clean them up before adding new ones.| Output | Format | Condition |
|---|---|---|
polished_text | In-place edits (file) or conversation output (pasted text) | Always produced |
change_annotations | LaTeX comments (% [Polish] Original:) | File input only |
summary_report | Markdown in session (not in file) | Always produced |
bilingual_conversation | > **[Chinese]** ... blockquotes in session | File input: modified paragraphs only. Pasted text: after each output paragraph. Skipped when opt-out detected. |
| Situation | Handling |
|---|---|
| Input too short (single sentence) | Polish but warn limited context for structural assessment |
| No section headers in input | Default to expression-focused polishing |
| Pasted text input | Output directly in conversation; no file operations |
| File input | Use Edit tool only; never Write (do not overwrite entire file) |
| Journal specified but no template | Refuse; instruct user to add template at references/journals/[journal].md |
| Very long input (10+ sections) | Process in batches; maintain cross-section terminology awareness |
Existing % [Polish] Original: annotations | Clean up old annotations before adding new ones |
| Mixed LaTeX and text | Preserve all LaTeX commands; polish surrounding natural language only |
| Text with obvious translationese | Flag in summary; prioritize translationese fixes in expression pass |
| Scenario | Fallback |
|---|---|
| Structured Interaction unavailable | Ask 1-3 plain-text questions covering highest-impact gaps |
| Expression pattern leaf missing | Use overview entrypoint for general patterns |
| Journal template missing for specified journal | Refuse -- instruct user to add the template first |
| Anti-AI patterns file missing | Proceed without; rely on Claude's vocabulary awareness |
| File is read-only or Edit fails | Present changes as a diff in conversation; user applies manually |
Skill: polish-skill Conventions: references/skill-conventions.md