paperfit
Diagnose and repair LaTeX paper layout through PaperFit's structured visual closed loop over rendered pages, source-grounded…
PaperFit writing polish expertise for LaTeX paper layout.
Claude Code
$ npx -y skills add OpenRaiser/PaperFit --skill writing-polish --agent claude-code
Codex
$ npx skills add OpenRaiser/PaperFit --skill writing-polish -a codex -y
Cursor
$ npx skills add OpenRaiser/PaperFit --skill writing-polish -a cursor -y
Gemini CLI
$ npx skills add OpenRaiser/PaperFit --skill writing-polish -a gemini-cli -y
GitHub Copilot
$ npx skills add OpenRaiser/PaperFit --skill writing-polish -a github-copilot -y
OpenCode
$ npx skills add OpenRaiser/PaperFit --skill writing-polish -a opencode -y
Windsurf
$ npx skills add OpenRaiser/PaperFit --skill writing-polish -a windsurf -y
name: writing-polish description: "PaperFit writing polish expertise for LaTeX paper layout."
本技能为 **Semantic Polish Agent** 提供具体、可执行的语义微调策略与禁区规则。它定义了在排版手段用尽后,如何通过最小化文字增删来消除孤行寡行、控制页数预算或优化末页留白,同时严格保持学术内容的原意、数据和结论不变。
该技能不直接被 `orchestrator-agent` 调用,而是作为 `semantic-polish-agent` 的知识库和行为规范。所有语义级改写必须遵循本技能中定义的技巧和约束。
Source-changing 边界:语义级改写是高风险 source mutation。默认只能生成候选改写、风险和 approval 状态;只有显式 `--apply` 或宿主等价授权存在时才允许写回。多轮语义改写必须同时显式启用 `--apply --max-rounds N`,并且每轮都通过 approval carry-forward、artifact freshness、candidate approval scope gate 和 gatekeeper `CONTINUE`;超出既有 approval scope 的语义修改必须重新获批。
| 触发缺陷 | 操作方向 | 允许的改写幅度 | |----------|----------|---------------| | A1(孤行寡行) | 缩短 1-2 行 | 增删 3-8 词 | | A2(末页留白) | 扩展 2-4 行 | 增加 20-50 词 | | A3(页数预算) | 缩短或扩展多行 | 按需,但需分段执行 | | 用户主动请求 | 精炼或扩写特定段落 | 用户指定 |
| 输入项 | 来源 | 说明 | |--------|------|------| | 目标段落源码 | `semantic-polish-agent` 提取 | 需改写的一个或多个完整段落 | | 改写目标 | 调用方请求 | `shorten` 或 `expand`,及期望行数变化 | | 写作规范 | `config/writing_rules.yaml` | 时态、术语、禁用词等约束 | | 上下文段落 | `semantic-polish-agent` 提取 | 前后各一段,用于保证语义连贯 |
本技能输出改写后的文本及变更元数据,供 `semantic-polish-agent` 整合为最终报告。
{
"skill": "writing-polish",
"changes": [
{
"paragraph_id": 3,
"action": "shorten",
"net_word_change": -6,
"before_snippet": "It is worth noting that our method achieves state-of-the-art performance on several benchmark datasets.",
"after_snippet": "Our method achieves state-of-the-art results on several benchmarks.",
"techniques_used": ["remove_redundant", "phrase_to_word"],
"rationale": "移除冗余修饰词,将 'achieves state-of-the-art performance on several benchmark datasets' 压缩为 'achieves state-of-the-art results on several benchmarks'。语义等价,数据未变。"
}
],
"warnings": []
}1. **最小修改优先**:能改一词不改一句,能改一句不改一段。 2. **保持学术严谨**:绝不改变数据值、引用标记、专有名词、核心声明。 3. **局部影响评估**:每次改写后需编译验证,确保不引入新的孤行或溢出。 4. **可逆性**:保留改写前文本,便于人工审查或回滚。
---
目标:在不损失信息的前提下减少字数/行数。
移除对学术内容无实质贡献的修饰语。
示例:
修改前:It is worth noting that our method achieves very competitive performance. 修改后:Our method achieves competitive performance. 减少:5 词
用更简洁的单词或缩写替代多词短语。
| 原短语 | 替换为 | |--------|--------| | `in order to` | `to` | | `a large number of` | `many` | | `due to the fact that` | `because` | | `at the present time` | `now` | | `state-of-the-art methods` | `SOTA methods`(需已定义) | | `with respect to` | `regarding` 或 `on` |
示例:
修改前:We conduct experiments in order to evaluate the performance of the proposed approach. 修改后:We conduct experiments to evaluate our approach. 减少:5 词
主动语态通常更简短且更有力。
修改前:The experiments were conducted by us on three datasets. 修改后:We conducted experiments on three datasets. 减少:3 词
将两个紧密相关的短句合并为一句。
修改前:We used the Adam optimizer. The learning rate was set to 1e-4. 修改后:We used Adam with a learning rate of 1e-4. 减少:6 词
在全文首次定义后,使用公认缩写。
| 原词 | 缩写 | |------|------| | `state-of-the-art` | `SOTA` | | `natural language processing` | `NLP` | | `mean average precision` | `mAP` |
修改前:Our method outperforms previous state-of-the-art approaches on the natural language processing benchmark. 修改后:Our method outperforms previous SOTA approaches on the NLP benchmark. 减少:5 词(假设 SOTA/NLP 已定义)
将定语从句压缩为分词短语或前置定语。
修改前:The model which is trained on ImageNet achieves high accuracy. 修改后:The ImageNet-trained model achieves high accuracy. 减少:3 词
---
目标:在不注水的前提下增加有实质内容的文字。
在结果陈述后补充简短的原因解释。
修改前:Our method outperforms the baseline by 3.2%. 修改后:Our method outperforms the baseline by 3.2%, likely because the attention mechanism better captures long-range dependencies. 增加:11 词
在表格或数据引用后,增加一句对关键发现的解读。
修改前:Table 2 shows the ablation results. 修改后:Table 2 summarizes the ablation study. Removing the temporal module causes a significant drop of 5.1%, confirming its importance for sequential modeling. 增加:18 词
在提及已有工作时,增加具体的差异说明。
修改前:Unlike previous work, we use a transformer-based architecture. 修改后:Unlike previous work that relied on recurrent networks with limited parallelization, we adopt a transformer architecture that scales more efficiently to long sequences. 增加:14 词
在结论或讨论部分,补充一句对当前方法局限性的客观陈述。
修改前:Future work will explore larger-scale datasets. 修改后:Future work will explore larger-scale datasets. A current limitation is the reliance on pre-trained word embeddings, which may not fully capture domain-specific terminology. 增加:17 词
通过增加句号拆分长句,可在不显著增加内容的情况下扩展行数。
修改前:Our method consists of three components: an encoder, a decoder, and a refinement module. 修改后:Our method consists of three components. First, the encoder extracts features from the input. Second, the decoder generates initial predictions. Finally, the refinement module iteratively improves the output. 增加:14 词,行数增加更多
在不泄露未公开信息的前提下,可适当补充已在论文其他部分出现过的技术细节。
修改前:We use a standard cross-entropy loss. 修改后:We use a standard cross-entropy loss with label smoothing of 0.1, following common practice in image classification. 增加:10 词
---
以下操作 **严禁** 进行,违反任何一条都不得输出修改。
Vision-in-the-Loop Academic Typesetting Agent System PaperFit 是面向 Claude Code、Codex、Cursor 的视觉闭环 LaTeX 排版系统。PaperFit 组织“渲染页图—视觉诊断—受约束源码修复—重新渲染与视觉复验”的结构化循环,由当前多模态宿主执行。实际页图反馈是诊断和每个修复候选验收的必要环节,每个完整候选重新渲染后都检查全部物理页面,再决定保留、修改或回滚;独立视觉 API
Diagnose and repair LaTeX paper layout through PaperFit's structured visual closed loop over rendered pages, source-grounded…
Inspect and repair local table, figure, and caption presentation while preserving content and venue formatting.
PaperFit advice for LaTeX figure/table placement, width, clustering and breakable-table flow, verified against current page…
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use…
AI-driven presentation workflow for generating editable PPTX decks and slides, reconstructing page visuals, creating reusable…
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style…
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to…