Back to Details

manuscript-optimizer

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Manuscript Optimizer

Manuscript Optimizer（学术稿件优化器）

Overview

概述

Use this skill to treat a manuscript like a precision instrument: fix the top-level design first, then the evidence chain, then the figures, then the terminology, and only then the sentence-level polish.
This workflow is not tied to a single paper or field. Use it across manuscript projects whenever structure, evidence, figures, and prose need to be brought back into alignment.
Core rule: do not spend effort polishing prose that sits on top of an unstable claim, a broken evidence chain, or inconsistent figures.
使用本Skill将稿件视作精密仪器：先修复顶层设计，再梳理证据链，接着调整图表，统一术语，最后才进行语句层面的润色。
这个工作流不局限于单一论文或领域。每当稿件的结构、证据、图表和行文需要重新对齐时，均可在各类稿件项目中使用。
核心原则：不要在论点不稳定、证据链断裂或图表不一致的基础上浪费精力润色行文。

When To Use

适用场景

Use this skill when:
  • A paper is being drafted, revised, resubmitted, or journal-adapted
  • The abstract or introduction may be stronger than the downstream evidence
  • The storyline feels diffuse, repetitive, or hard to defend
  • Figures, legends, and main text may have drifted out of sync
  • Core terminology or abbreviations may be unstable
  • The writing needs to become clearer, tighter, and more reader-friendly without losing rigor
Do not use this skill as the primary workflow for:
  • Pure literature review generation
  • Citation-format-only cleanup
  • Methods-only statistical review
  • Journal peer review reports that focus mainly on acceptance recommendations
当出现以下情况时，可使用本Skill：
  • 论文处于起草、修订、重新投稿或适配期刊阶段
  • 摘要或引言的表述可能比后续证据更有力
  • 叙事线显得分散、重复或难以论证
  • 图表、图例与正文可能出现脱节
  • 核心术语或缩写的使用不稳定
  • 需要在保持严谨性的前提下，让写作更清晰、紧凑且易于阅读
以下场景不适合将本Skill作为主要工作流：
  • 纯文献综述生成
  • 仅清理引用格式
  • 仅针对方法部分的统计审阅
  • 主要聚焦录用建议的期刊同行评审报告

Operating Principle

操作原则

Always move in this order:
  1. Direction first
  2. Logic second
  3. Visual evidence third
  4. Terminology fourth
  5. Language last
If a higher-level problem is unresolved, do not present lower-level polish as a solution.
务必遵循以下顺序：
  1. 先明确方向
  2. 再梳理逻辑
  3. 接着处理可视化证据
  4. 然后统一术语
  5. 最后优化语言
若更高层级的问题未解决，切勿将低层级的润色作为解决方案。

Two Modes

两种模式

Review Mode

审阅模式

Use when the task is to diagnose weaknesses before editing.
Output priorities:
  • Findings first
  • Highest-level issues first
  • Explicitly separate unsupported claims, weak support, and cosmetic issues
  • Cite exact sections, figures, or sentences when possible
适用于编辑前诊断稿件缺陷的任务。
输出优先级：
  • 先呈现发现的问题
  • 先展示最高层级的问题
  • 明确区分无依据论点、薄弱支撑和表面问题
  • 尽可能引用具体章节、图表或语句

Optimization Mode

优化模式

Use when the task is to actually rewrite or tighten the manuscript.
Execution order:
  • Fix macro positioning and claim boundaries
  • Repair section logic and evidence chain
  • Sync figures, legends, and text
  • Canonicalize terminology
  • Polish prose, grammar, and format
适用于实际重写或精简稿件的任务。
执行顺序：
  • 修正宏观定位和论点边界
  • 修复章节逻辑和证据链
  • 同步图表、图例与正文
  • 统一术语规范
  • 润色行文、语法和格式

The Five-Level Audit

五层审核

1. Top-Level Design And Core Contribution

1. 顶层设计与核心贡献

Check the manuscript's top story before touching paragraph style.
Audit:
  • What is the central problem?
  • Why does it matter now?
  • What is the single-sentence take-home message?
  • Is the main contribution a method, framework, benchmark, resource, biological finding, or something else?
  • Is the claim ambitious enough to matter but narrow enough to defend?
  • After reading the abstract and introduction, can a broad scientific reader understand why this work is not interchangeable with prior work?
Guardrails:
  • Do not let the paper sound like it contributes three equally important things unless that structure is deliberate and defensible
  • Do not let examples, intuitions, or motivating cases masquerade as experimental evidence
  • If the real contribution is a reformulation or evaluation framework, do not accidentally rewrite it as "a new model"
在调整段落风格前，先检查稿件的核心叙事。
审核要点：
  • 核心问题是什么？
  • 为何该问题在当下至关重要？
  • 用一句话概括核心结论是什么？
  • 主要贡献是方法、框架、基准、资源、生物学发现还是其他类型？
  • 论点的野心是否足够重要，同时又足够具体可论证？
  • 阅读摘要和引言后，广泛的科学读者能否理解这项工作与先前研究的本质区别？
注意事项：
  • 除非结构经过深思熟虑且合理，否则不要让论文听起来有三个同等重要的贡献
  • 不要让示例、直觉或动机案例伪装成实验证据
  • 如果实际贡献是重构或评估框架，切勿误将其改写为“一种新模型”

2. Logic Architecture And Evidence Chain

2. 逻辑架构与证据链

This is the main structural check.
Build a claim-to-evidence map:
  • Extract every substantive claim from the abstract
  • Extract every substantive claim from the introduction and discussion
  • For each claim, point to the exact supporting result, figure, table, or supplementary item
  • Mark each claim as:
    • fully supported
    • partially supported
    • not supported by current evidence
Then run a reverse outline on the current section structure:
  • Write the section thesis in one sentence.
  • Write one line for each paragraph:
    • paragraph job
    • key evidence or reasoning inside it
    • the transition relation to the previous paragraph
  • Merge, move, or remove any paragraph that cannot be mapped cleanly to the section thesis.
When a claim is not fully supported, only three acceptable actions exist:
  • weaken the claim
  • add the missing evidence
  • reframe the claim as intuition, hypothesis, or motivation
Questions to ask:
  • Does each Results subsection answer a clear question?
  • Does each module in the method or framework have a corresponding validation experiment?
  • If the manuscript claims OOD generalization, cross-domain transfer, causal disentanglement, or clinical relevance, is there direct evidence for that exact statement?
  • Are surprising or paradoxical findings explained, not merely reported?
Never leave the abstract or introduction stronger than the Results.
这是主要的结构检查环节。
构建论点-证据映射：
  • 从摘要中提取所有实质性论点
  • 从引言和讨论中提取所有实质性论点
  • 针对每个论点，指向确切的支撑结果、图表、表格或补充材料
  • 将每个论点标记为：
    • 完全支撑
    • 部分支撑
    • 当前证据无法支撑
随后对现有章节结构进行反向大纲梳理：
  • 用一句话概括章节主旨。
  • 为每个段落写一行内容：
    • 段落作用
    • 段落内的关键证据或推理
    • 与前一段的过渡关系
  • 合并、移动或删除任何无法清晰映射到章节主旨的段落。
当论点未得到完全支撑时，仅存在三种可行操作：
  • 弱化论点
  • 添加缺失的证据
  • 将论点重新表述为直觉、假设或动机
需思考的问题：
  • 每个结果子章节是否回答了明确的问题？
  • 方法或框架中的每个模块是否有对应的验证实验？
  • 如果稿件声称分布外泛化、跨域迁移、因果解耦或临床相关性，是否有直接证据支持该确切表述？
  • 意外或矛盾的发现是否已得到解释，而非仅被报告？
切勿让摘要或引言的表述比结果部分更有力。

Adversarial Self-Review

对抗式自我审阅

Before calling the structure stable, pressure-test the manuscript like a skeptical reviewer in five dimensions:
  • contribution sufficiency
  • writing clarity and reproducibility
  • empirical strength
  • evaluation completeness
  • method or framework soundness
Do not answer these with intuition alone. Point to concrete sections, figures, tables, or supplementary items.
在确认结构稳定前，从五个维度像持怀疑态度的审稿人一样压力测试稿件：
  • 贡献充分性
  • 写作清晰度与可重复性
  • 实证强度
  • 评估完整性
  • 方法或框架合理性
不要仅凭直觉回答这些问题，需指向具体章节、图表、表格或补充材料。

3. Data Visualization And Figure Expression

3. 数据可视化与图表呈现

Treat figures as independent carriers of the paper's logic.
Audit each figure on its own:
  • Can the figure tell its own story without the main text?
  • Do panel labels, legends, and body text say the same thing?
  • Are metrics, baselines, datasets, and abbreviations defined consistently?
  • If a panel was removed or reordered, were the text and legend updated in the same pass?
  • Are the key comparisons visually obvious, not buried in clutter?
  • Does the figure support the exact claim made about it in the Results?
For high-impact-journal style manuscripts:
  • Prefer figures that communicate one main message each
  • Reduce decorative complexity
  • Make figure titles and legends carry real interpretive value
  • Do not let legends overclaim relative to the plotted data
将图表视为论文逻辑的独立载体。
单独审核每个图表：
  • 图表能否脱离正文独立讲述完整故事？
  • 面板标签、图例与正文表述是否一致？
  • 指标、基准、数据集和缩写的定义是否统一？
  • 如果面板被移除或重新排序，正文和图例是否同步更新？
  • 关键对比是否在视觉上清晰可见，而非被杂乱信息掩盖？
  • 图表是否支撑结果部分中对其的确切论点？
对于高影响力期刊风格的稿件：
  • 优先选择每个图表传达一个核心信息
  • 减少装饰性复杂度
  • 让图表标题和图例承载实际解释价值
  • 不要让图例的表述超出图表数据所呈现的内容

Results Compression And Figure-Legend Balance

结果压缩与图表-图例平衡

When a Results section feels overloaded, compress it by claim rather than by panel count.
Rules:
  • Prefer one main claim per figure.
  • If a figure needs internal subdivision, keep it to at most two Results subsections unless there is a strong reason otherwise.
  • Keep only 
    1-2
    hard numbers in the main-text paragraph that directly support the local claim.
  • Move panel-level values, method-by-method comparisons, and denser quantitative detail into figure legends or supplementary display items.
  • Treat figure legends as the second layer of result narration: they should define panel roles, preserve key quantitative anchors, and stay synchronized with the compressed main text.
Before rewriting figure-linked prose, identify each panel's real role:
  • claim-supporting evidence
  • methodological bridge or definition
  • validation under a new regime
  • translational or practical consequence
  • case illustration
Do not flatten a methodological bridge panel into generic motivation. If a panel explains where a metric or evaluation space comes from, say so explicitly in the main text.
When multiple metrics are shown:
  • keep the strongest metric as the primary evidence in the Results paragraph
  • demote weaker or more auxiliary metrics to complementary readouts
  • do not oversell a metric that is mainly included for completeness or secondary utility
当结果部分显得过载时，按论点而非面板数量进行压缩。
规则：
  • 优先每个图表对应一个核心论点。
  • 如果图表需要内部细分，除非有充分理由，否则最多对应两个结果子章节。
  • 在正文段落中仅保留1-2个直接支撑局部论点的关键数据。
  • 将面板级数值、逐方法对比和更密集的量化细节移至图例或补充展示材料中。
  • 将图例视为结果叙述的第二层：它们应明确面板作用、保留关键量化锚点，并与压缩后的正文保持同步。
在重写与图表相关的行文前，明确每个面板的实际作用：
  • 支撑论点的证据
  • 方法桥梁或定义
  • 新场景下的验证
  • 转化或实际应用价值
  • 案例说明
不要将方法桥梁面板简化为通用动机。如果某个面板解释了指标或评估空间的来源，需在正文中明确说明。
当展示多个指标时：
  • 将最强的指标作为结果段落中的主要证据
  • 将较弱或辅助性指标降级为补充读数
  • 不要过度推销主要为完整性或次要用途而包含的指标

4. Terminology And Domain Language

4. 术语与领域语言

Scientific credibility depends on stable naming.
Create a canonical term list early:
  • core concepts
  • formal decomposition terms
  • benchmark names
  • task settings
  • baseline names
  • abbreviations
Then enforce it everywhere:
  • abstract
  • introduction
  • results
  • discussion
  • figure labels
  • legends
  • supplementary text
Audit:
  • Are old and new names mixed?
  • Are informal descriptions replacing formal terms in key places?
  • Are multiple near-synonyms being used for one concept?
  • Are any terms likely to create domain confusion because they already mean something else in the field?
If a term is formal, keep it stable. If a looser explanatory phrase is needed, make sure it does not compete with the formal term.
科学可信度依赖于稳定的命名。
尽早创建规范术语列表：
  • 核心概念
  • 正式分解术语
  • 基准名称
  • 任务设置
  • 基准模型名称
  • 缩写
然后在所有位置强制执行：
  • 摘要
  • 引言
  • 结果
  • 讨论
  • 图表标签
  • 图例
  • 补充文本
审核要点：
  • 是否新旧名称混用？
  • 是否在关键位置用非正式描述替代正式术语？
  • 是否对同一概念使用多个近义术语？
  • 是否存在因在该领域已有其他含义而可能造成混淆的术语？
如果是正式术语，保持其稳定性。 如果需要更宽松的解释性表述，确保其不会与正式术语产生冲突。

5. Micro-Level Polish

5. 微观层面润色

Only do this after the first four levels are stable.
Targets:
  • grammar
  • singular/plural consistency
  • tense consistency
  • punctuation
  • article usage
  • redundant phrases
  • repeated transitions
  • overlong sentences
  • vague intensifiers
  • empty summary lines
Preferred prose style:
  • professional but readable
  • specific rather than ornamental
  • short-to-medium sentences by default
  • one paragraph, one job
  • observations and interpretations clearly separated
Avoid:
  • bloated topic sentences
  • unnecessary jargon
  • unstable voice
  • repeated transition formulas
  • em dashes unless explicitly wanted
  • generic AI-sounding escalation words
仅在前四层均稳定后再进行此步骤。
优化目标：
  • 语法
  • 单复数一致性
  • 时态一致性
  • 标点
  • 冠词使用
  • 冗余短语
  • 重复过渡词
  • 过长句子
  • 模糊的强化词
  • 空洞的总结句
推荐行文风格：
  • 专业但易读
  • 具体而非华丽
  • 默认使用中短句
  • 一段一任务
  • 观察结果与解释明确区分
需避免：
  • 臃肿的主题句
  • 不必要的行话
  • 不稳定的语态
  • 重复的过渡句式
  • 破折号（除非明确需要）
  • 通用AI风格的夸张词汇

Default Workflow

默认工作流

When asked to improve a manuscript, follow this sequence:
  1. Identify venue, article type, and the paper's intended central contribution.
  2. Read abstract, introduction, results headings, and figure legends first.
  3. Write a short claim-to-evidence map.
  4. Reverse-outline the current section or subsection structure before rewriting.
  5. Flag any mismatch between front-half claims and downstream support.
  6. Check whether figures and legends independently support the stated claim.
  7. Run a compact skeptical-review pass across contribution, clarity, empirical support, evaluation completeness, and design soundness.
  8. Lock canonical terminology.
  9. Only after the above, rewrite for clarity and concision.
If the user asks for review only, stop after diagnosis. If the user asks for revision, edit in the same macro-to-micro order.
当被要求优化稿件时，遵循以下步骤：
  1. 确定目标期刊、文章类型及论文的预期核心贡献。
  2. 先阅读摘要、引言、结果标题和图例。
  3. 撰写简短的论点-证据映射。
  4. 在重写前对当前章节或子章节结构进行反向大纲梳理。
  5. 标记前半部分论点与后续支撑之间的任何不匹配。
  6. 检查图表和图例是否能独立支撑所述论点。
  7. 针对贡献充分性、清晰度、实证支撑、评估完整性和设计合理性进行一次简洁的怀疑式审阅。
  8. 锁定规范术语。
  9. 完成上述步骤后，才进行清晰度和简洁度的重写。
如果用户仅要求审阅，诊断完成后即可停止。 如果用户要求修订，按照从宏观到微观的顺序进行编辑。

Common Failure Modes

常见失效模式

Front Half Stronger Than Back Half

前半部分强于后半部分

Symptom:
  • Abstract or introduction promises more than the Results show
Fix:
  • downgrade the claim or add evidence
  • do not hide the gap with stronger prose
症状：
  • 摘要或引言承诺的内容多于结果部分展示的内容
修复方案：
  • 弱化论点或补充证据
  • 不要用更华丽的行文掩盖差距

Framework Turns Into Model

框架被误描述为模型

Symptom:
  • A benchmark, reformulation framework, or evaluation protocol gets described as if it were the predictive architecture itself
Fix:
  • restate the contribution type explicitly
  • distinguish the framework from the instantiated pipeline or baseline comparisons
症状：
  • 基准、重构框架或评估协议被描述成预测架构本身
修复方案：
  • 明确重述贡献类型
  • 将框架与实例化流程或基准模型区分开

Metric Drop Framed As Mechanism

指标下降被错误归因于机制

Symptom:
  • A harsher metric is described as causal proof of a deeper mechanism
Fix:
  • separate what the metric directly shows from the interpretation it suggests
  • use "suggests", "is consistent with", or "implicates" when direct mechanism evidence is absent
症状：
  • 更严苛的指标被描述为深层机制的因果证明
修复方案：
  • 区分指标直接展示的内容与它所暗示的解释
  • 当缺乏直接机制证据时，使用“表明”“与……一致”或“暗示”等表述

Figure Drift

图表脱节

Symptom:
  • Panel letters, metrics, datasets, baselines, or numbers changed in the figure but not in the text
Fix:
  • re-read the actual figure
  • update text, legend, and claims together
症状：
  • 图表中的面板编号、指标、数据集、基准或数值已更改，但正文未同步更新
修复方案：
  • 重新阅读实际图表
  • 同步更新正文、图例和论点

Terminology Drift

术语脱节

Symptom:
  • Several labels compete for the same concept
Fix:
  • choose one canonical term
  • allow looser explanatory phrases only when they do not function as competing formal labels
症状：
  • 多个标签指代同一概念
修复方案：
  • 选择一个规范术语
  • 仅当宽松解释性表述不充当竞争性正式标签时，才允许使用

Premature Sentence Polishing

过早润色语句

Symptom:
  • The prose becomes smoother but the argument remains unstable
Fix:
  • return to macro and structural levels first
症状：
  • 行文变得更流畅，但论证仍不稳定
修复方案：
  • 先回到宏观和结构层面解决问题

Output Standard

输出标准

When reporting findings, prefer this order:
  • macro contribution problem
  • evidence-chain problem
  • figure or legend inconsistency
  • terminology inconsistency
  • prose and formatting issues
When no major structural problems exist, say that explicitly and then move to lower-level optimization.
报告发现的问题时，优先遵循以下顺序：
  • 宏观贡献问题
  • 证据链问题
  • 图表或图例不一致
  • 术语不一致
  • 行文与格式问题
当不存在重大结构问题时，需明确说明，然后再进行低层级优化。

Minimal Review Template

极简审阅模板

Use this compact structure when reviewing a manuscript:
  • Central claim:
  • Claim | Evidence | Status:
  • Strongest supporting result:
  • Weakest or unsupported claim:
  • Reverse-outline break point:
  • Figure-text mismatch:
  • Terminology drift:
  • Recommended next revision step:
审阅稿件时可使用以下紧凑结构：
  • 核心论点：
  • 论点 | 证据 | 状态：
  • 最强支撑结果：
  • 最弱或无依据论点：
  • 反向大纲断点：
  • 图表-正文不匹配：
  • 术语脱节：
  • 推荐下一步修订步骤：