fit-page-limit

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Fit Page Limit

适配页数限制

Two sides of the same problem: a paper that is over the limit and needs careful cuts, or a paper that is under and needs useful substance rather than filler. This skill maps the draft section by section, then gives the author a prioritized plan for whichever direction they need.

It coordinates with

polish-prose

for sentence-level tightening,

refactor-structure

for larger reorganization,

polish-tables-figures

for visual layout, and

preflight-check

when the page limit comes from a venue rule. Run it after the draft is roughly complete.

这是同一问题的两个方面：论文超出页数限制，需要谨慎删减；或者论文不足页数，需要补充有价值的实质内容而非冗余凑数。本技能会逐节梳理草稿内容，然后根据作者的需求方向，提供一份优先级明确的调整方案。

它可与

polish-prose

配合进行句子级精简，与

refactor-structure

配合进行大规模结构重组，与

polish-tables-figures

配合优化视觉排版；当页数限制来自会议/期刊规则时，可与

preflight-check

配合使用。请在草稿大致完成后运行本技能。

When to use

使用场景

The draft is over the limit and the author needs to know where the bulk is.
The draft is under the target length and the author wants to use space well.
The author asks for a length map: "where is all my length going?"

草稿超出页数限制，作者需要了解篇幅主要消耗在何处。
草稿未达到目标篇幅，作者希望合理利用剩余空间。
作者要求生成篇幅分布图谱：“我的篇幅都用在哪里了？”

Inputs

输入内容

The
```
.tex
```
source.
The real compiled page count, if available, to calibrate the estimate.
The target: a venue page limit or a length the author names.
The venue CFP or profile, if the target comes from a venue.

```
.tex
```
格式的论文源文件。
若有已编译好的实际页数，可提供用于校准篇幅估算结果。
目标篇幅：会议/期刊的页数限制，或作者指定的篇幅长度。
若目标篇幅来自会议/期刊，需提供该会议/期刊的Call for Papers（CFP）或相关说明文档。

Process

操作流程

Map the length. Run the analyzer from this skill directory; do not eyeball where the pages went.
bash
```
python3 scripts/section_budget.py paper.tex --target-pages 10 --current-pages 11
```
It reports per-section words, percentage of the paper, estimated pages, and the over/under gap.
```
--current-pages
```
calibrates words per page to the author's actual compile. Use
```
--json
```
for machine-readable output.
Confirm what counts. Re-verify the venue's limit and exclusions against the live CFP before relying on appendix moves or excluded sections. A stale page limit can desk-reject the paper.
Pick the right branch. Use references/resize-tactics.md to turn the map into a value-aware resize plan.

生成篇幅分布图谱。运行本技能目录下的分析工具；请勿仅凭肉眼判断篇幅去向。
bash
```
python3 scripts/section_budget.py paper.tex --target-pages 10 --current-pages 11
```
该工具会输出各章节的字数、占全文的百分比、估算页数，以及与目标篇幅的差值。
```
--current-pages
```
参数可根据作者实际编译的页数校准每页字数。使用
```
--json
```
参数可输出机器可读格式的结果。
确认计数规则。在决定将内容移至附录或利用不计入页数的部分之前，请对照最新的CFP重新确认会议/期刊的页数限制及不计入内容。过时的页数限制信息可能导致论文被直接拒稿。
选择合适的调整路径。使用references/resize-tactics.md文档，将篇幅分布图谱转化为兼顾内容价值的调整方案。

If over: compress value-aware, never blind

若超出篇幅：基于价值的精准压缩，而非盲目删减

Rank sections by compressibility x low impact, and cut there first:

Redundancy: the same point repeated in the intro, method, and conclusion.
Over-long related work: condense paragraph-per-paper prose into clusters that state only the delta that matters.
Verbose method/setup: tighten with
```
polish-prose
```
; cut walkthroughs a figure already shows.
Move, do not delete: push proofs, extra results, or implementation detail to an appendix only when the venue excludes it.
Figures/tables: resize, merge subfigures, or drop a redundant baseline column with
```
polish-tables-figures
```
.

Protect contributions, headline results, and every citation. Present estimated savings per cut and let the author approve before editing. Never delete a result, claim, or reference to hit a number.

按照可压缩性 × 低影响度对章节排序，优先从以下部分入手删减：

冗余内容：引言、方法和结论中重复表述的同一观点。
过长的相关工作部分：将逐篇论文单独成段的叙述浓缩为聚类内容，仅阐述与本研究相关的差异点。
冗长的方法/实验设置：使用
```
polish-prose
```
进行精简；删减已有图表说明的操作步骤。
移至附录而非删除：仅当会议/期刊允许附录不计入页数时，才将证明过程、额外研究结果或实现细节移至附录。
图表：使用
```
polish-tables-figures
```
调整图表尺寸、合并子图，或删除冗余的基线列。

保护核心贡献、主要研究结果以及所有引用内容。需告知作者每一项删减预计节省的篇幅，待作者确认后再进行编辑。绝不能为了达标而删除研究结果、核心观点或引用文献。

If under: expand with substance

若篇幅不足：补充实质内容

A short, complete paper can be fine; say so. If there is real room to strengthen it, suggest substance: a missing ablation, deeper error analysis, limitations or threats to validity, clearer motivation, a worked example, or a related-work gap. Flag suggestions that would merely pad. Hand drafting to the writing skills.

篇幅较短但内容完整的论文是可以接受的，需如实告知作者。若确实有提升空间，建议补充以下实质内容：缺失的消融实验、更深入的误差分析、局限性或有效性威胁、更清晰的研究动机、实际案例，或相关研究中的空白点。需标注仅用于凑篇幅的建议。将草稿交由写作类技能处理。

Output

输出内容

A length map and prioritized resize plan:

Over: ranked cut list, estimated savings, and protected material.
Under: substantive additions ranked by value.

Write durable outputs to the user's local

paper-workspace/writing/

directory when a workspace exists. The skill recommends and explains; the author decides and edits.

篇幅分布图谱和优先级明确的调整方案：

超出篇幅：按优先级排序的删减清单、预计节省的篇幅，以及需保护的内容。
篇幅不足：按价值排序的实质补充内容建议。

若存在工作区，会将持久化输出内容写入用户本地的

paper-workspace/writing/

目录。本技能仅提供建议和说明；最终由作者决定并进行编辑。

Guardrails

约束规则

Never delete results, claims, or citations to fit.
Never pad to fill.
Page numbers are estimates; tell the author to compile and check the real count.
Re-verify venue limits and exclusions against the live CFP before advising appendix moves.
Copilot, not pilot: propose the plan; the author approves and edits.

绝不能为了达标而删除研究结果、核心观点或引用文献。
绝不能添加冗余内容凑篇幅。
页数仅为估算值；需告知作者编译并查看实际页数。
在建议将内容移至附录之前，需对照最新的CFP重新确认会议/期刊的页数限制及不计入内容。
仅作协作助手，而非主导者：提出方案；由作者确认并编辑。

Memory

记忆机制

Uses the shared

.paper-memory/

convention documented by

paper-profile

At start: read
```
lessons.md
```
for recurring overspend patterns, such as "related work always runs long".
At end: append `date - fit-page-limit - over/under - where the length went
- what was cut/added` after deduping.
Create
```
.paper-memory/
```
on demand in the user's paper directory. It is local only and should usually be ignored by git.

采用

paper-profile

文档中记录的共享

.paper-memory/

约定。

启动时：读取
```
lessons.md
```
文件，了解重复出现的篇幅超支模式，例如“相关工作部分总是过长”。

结束时：去重后，将

日期 - fit-page-limit - 超出/不足 - 篇幅去向 - 删减/补充内容

的记录追加到文件中。

根据需要在用户的论文目录中创建
```
.paper-memory/
```
目录。该目录仅存储在本地，通常应被git忽略。