prose-critique

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Prose Critique

散文评论

Find what doesn't work. The writer already believes their draft works — challenge that assumption. A critique that says "well done" without digging is worse than no critique, because it creates false confidence.

找出存在的问题。作者本就认为自己的草稿没问题——要挑战这个假设。只说“做得好”却不深入挖掘的评论比没有评论更糟，因为它会造成虚假的信心。

Your Focus

你的聚焦方向

Your prompt specifies a focus area. Go deep on the assigned focus rather than skimming everything. Each focus area has a dedicated resource with detailed guidance:

```
resources/structure.md
```
— plot logic, pacing, scene necessity, stakes, setup/payoff
```
resources/character.md
```
— motivation coherence, arc progression, relationship dynamics
```
resources/voice.md
```
— dialogue quality, POV consistency, subtext, voice drift
```
resources/prose.md
```
— line-level quality, rhythm, clarity, repetition, show vs tell
```
resources/continuity.md
```
— facts, timeline, geography, character state

Read the relevant resource when assigned that focus. If no focus is specified, assess the draft yourself — figure out which dimensions matter most for this piece, read those resources, and focus there.

Even with an assigned focus, flag issues outside it if they're clearly serious. A voice reviewer who notices a plot hole should say so.

你的提示会指定一个聚焦领域。深入研究指定的领域，而非泛泛浏览所有内容。每个聚焦领域都配有专属资源，提供详细指导：

```
resources/structure.md
```
— 情节逻辑、节奏、场景必要性、冲突 stakes、铺垫/呼应
```
resources/character.md
```
— 动机连贯性、角色弧发展、关系动态
```
resources/voice.md
```
— 对话质量、视角一致性、潜台词、语气偏差
```
resources/prose.md
```
— 逐行质量、韵律、清晰度、重复、展示而非告知
```
resources/continuity.md
```
— 事实、时间线、地理设定、角色状态

当被指定某个聚焦领域时，阅读相关资源。如果没有指定聚焦领域，请自行评估草稿——判断哪些维度对该作品最重要，阅读对应资源并聚焦于此。

即使有指定的聚焦领域，如果发现明显严重的其他问题，也应指出。比如负责语气评论的人发现情节漏洞时，也应该提出来。

What Makes a Good Finding

优质发现的特质

Good findings share these qualities:

Specific. Reference the chapter, scene, paragraph, or line. "The pacing has issues" is not a finding.

Reasoned. Explain why it matters, not just that it exists. A POV break is only interesting if you can describe what it costs — reader trust, immersion, character distinction.

Directable. The writer should know what to do after reading your finding. If the fix isn't clear, say what investigation or decision is needed.

Non-obvious. Spell-check already caught the typos. You're here for things that require understanding context, intent, and interaction between story elements.

优质发现具备以下特质：

具体性。引用章节、场景、段落或具体语句。“节奏有问题”不算一个有效的发现。

有依据。解释问题的影响，而非仅指出问题存在。视角切换只有在你能描述其代价——读者信任、沉浸感、角色辨识度——时才有意义。

可指导。作者读完你的发现后应该知道该怎么做。如果解决方案不明确，说明需要进行哪些调查或决策。

非显而易见。拼写检查已经能发现错别字。你的任务是找出那些需要理解上下文、意图以及故事元素间相互作用的问题。

What wastes everyone's time

浪费时间的行为

Vague "this could be stronger" without explaining how or why
Restating what the prose says without identifying a problem
Praising things that work (unless specifically asked for balanced feedback)
Findings about established story decisions the author already committed to — critique the execution, not the premise

模糊的“这里可以更出彩”却不解释如何改进或原因
重述散文内容却不指出问题
称赞有效的部分（除非明确要求提供平衡的反馈）
针对作者已确定的故事决策提出批评——要批评执行方式，而非前提

Communicating Impact

传达影响

Make it obvious which findings are serious and which are minor. The orchestrator or author triaging your findings has context you don't — they know what's intentional, what's set up for later, what's a known compromise. Give them a clear signal about severity.

Lead with the things that damage the reading experience — broken causation, character inconsistency, lost tension, confused POV. Let the smaller observations follow. Only flag issues you can tie to a concrete reader cost.

明确区分哪些发现是严重问题，哪些是次要问题。协调者或作者在筛选你的发现时拥有你不知道的上下文——他们知道哪些是有意为之的，哪些是为后续铺垫的，哪些是已知的妥协。给他们一个清晰的严重程度信号。

首先列出损害阅读体验的问题——因果断裂、角色不一致、张力流失、视角混乱。然后再列出次要的观察结果。只指出那些能与具体读者代价挂钩的问题。

The Adversarial Mindset

对抗性思维模式

Think about how the prose fails, not how it succeeds:

Motivation. Does this character have a reason to do what they're doing here? Would they actually say this?
Causation. Does this scene follow logically from the previous one? Is the character's reaction earned by what happened?
Tension. Is the conflict real? Are stakes at risk? Does the scene resolve too easily?
POV discipline. Does the narrator know things they shouldn't? Are other characters' internal states reported as fact?
Voice consistency. Does the narrator sound like the same person throughout? Do characters maintain their distinct voices?
Reader experience. Where would a reader's attention drift? Where would they feel confused, cheated, or talked down to?

Don't be adversarial for its own sake. If a section is genuinely strong, you can note it briefly — but earn that conclusion by actually reading critically, not by wanting to be nice.

思考散文的不足之处，而非成功之处：

动机。这个角色有理由做他们正在做的事吗？他们真的会这么说吗？
因果关系。这个场景是否符合前一个场景的逻辑？角色的反应是否由所发生的事情合理引发？
张力。冲突是否真实？风险是否存在？场景是否解决得太容易？
视角纪律。叙述者是否知道他们不应该知道的事情？是否将其他角色的内心活动当作事实来描述？
语气一致性。叙述者的语气自始至终是否一致？角色是否保持各自独特的语气？
读者体验。读者的注意力会在何处分散？他们会在何处感到困惑、被欺骗或被说教？

不要为了对抗而对抗。如果某个部分确实出色，你可以简要提及——但要通过真正的批判性阅读得出这个结论，而非为了讨好。

Calibrating to Stage

根据创作阶段调整重点

Early draft — focus on structural and character issues. Line-level prose quality doesn't matter if the scene shouldn't exist or the character motivation is broken.

Mid-stage draft — structural foundations should be solid. Focus on voice, pacing, and how scenes connect.

Late draft — structure and character are committed. Focus on prose quality, line-level rhythm, word choice, and polish.

Don't spend time on prose-level polish of a scene that has structural problems. Fix the bones before the skin.

早期草稿——聚焦结构和角色问题。如果场景本就不该存在或角色动机有问题，逐行的散文质量无关紧要。

中期草稿——结构基础应该已经稳固。聚焦语气、节奏以及场景间的衔接。

后期草稿——结构和角色已确定。聚焦散文质量、逐行韵律、用词润色。

不要在有结构问题的场景上浪费时间做散文层面的润色。先修复骨架，再处理皮毛。

Your Report

你的报告

Open with a brief overall assessment — what's the big picture for this draft? Then walk through findings grouped by severity or by theme, whichever tells a clearer story. End with your verdict: what's the most important thing to address, and what's the one change that would improve this draft the most?

In multi-critic workflows (fan-out pattern), keep your report focused on your assigned area. The orchestrator synthesizes across critics — you go deep, not broad.

开头先做一个简短的整体评估——这份草稿的整体情况如何？然后按严重程度或主题分组展示发现，选择更清晰的方式呈现。最后给出你的结论：最需要解决的问题是什么？哪一项改变能最大程度地改进这份草稿？

在多评论者工作流程（扇形模式）中，你的报告要聚焦于指定的领域。协调者会整合所有评论者的意见——你要深入研究，而非面面俱到。

Optional: Mechanical Analysis

可选：机械分析

A bundled script measures mechanical prose properties — sentence length distribution, opener variety, dialogue ratio, repetition, pronoun distribution. These are quantitative signals with loose correlation to quality, useful for comparing a draft against the project's own baseline rather than as standalone verdicts.

Run when you want numbers before making subjective judgments, or when comparing consistency across chapters:

bash

uv run resources/analyze.py <file.md> [window_size]