Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hongdotien10-hash-4daf8d
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/mrite-compile
What's inside
- Skill name
编译论文- Description
- 使用xelatex编译LaTeX论文,自动修复编译错误,执行排版优化
- License
- MIT
- Instructions
- 102 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "编译论文" does not match folder "mrite-compile"
Files (1)
- SKILL.md
SKILL.md (first lines)
# 编译论文
## 目的
使用 xelatex 编译论文 LaTeX 文件为 PDF,自动修复错误,直到编译成功且无任何问题。
## 编译流程
### Step 1:首次编译
```bash
cd 论文
xelatex -interaction=nonstopmode 论文.tex
xelatex -interaction=nonstopmode 论文.tex
```
### Step 2:检查错误
```bash
# 检查编译错误(必须为0)
grep -c 'Error' 论文.log
# 检查警告
grep -c 'Warning' 论文.log
# 检查溢出
grep 'Overfull\|Underfull\|Float too large' 论文.log
```
### Step 3:错误修复
| 错误类型 | 常见原因 | 修复方法 |
|----------|----------|----------|
| `Undefined control sequence` | 命令拼写错误或缺少包 | 检查拼写,添加必要包 |
| `Missing \begin{document}` | 正文前有输出内容 | 将内容移到 `\begin{document}` 后 |
| `File not found` | 引用文件不存在 | 检查路径和文件名 |
| `Font not found` | 缺少字体 | 检查 fonts/ 目录 |
| `Misplaced \noalign` | 表格中 `\\` 前有 `\centering` 干扰 | 确保 `>{\centering\arraybackslash}` 不省略 |
| 中文渲染警告 | 字体缺少字形 | 调整字体配置 |
| `Overfull \hbox` | 表格/段落过宽 | 缩短内容或调整宽度 |
| `Float too large` | 图表过大 | 调整尺寸 |
### Step 4:重编译
修复后重新执行:
```bash
xelatex -interaction=nonstopmode 论文.tex
xelatex -interaction=nonstopmode 论文.tex
```
重复直到 `grep -c 'Error' 论文.log` = 0。
## 排版优化(编译成功后自动执行)
### 检查项
```bash
grep 'Overfull\|Underfull\|Float too large' 论文.log
```
### 修复策略
| 问题类型 | 修复方法 |
|----------|----------|
| Overfull hbox | 缩短表格文字、调整 `p{}` 宽度 |
| Underfull hbox | 适当拉宽、调整断行 |
| Float too large | `width=0.75\textwidth` 等比缩小 |
| 大面积空白 | 调整段落密度、图片位置参数 |
| 图表位置不当 | 调整 `[ht]` / `[htb]` 参数 |
### 摘要一页验证
```bash
PAGE=$(grep 'abstract:end' 论文/论文.aux | grep -oE '\{[0-9]+\}' | head -1 | tr -d '{}')
if [ "$PAGE" -gt 1 ]; then
echo "摘要超出一页(第${PAGE}页),需缩减"
fi
```
若 `PAGE > 1`:按比例缩减各问题段字数,重新编译直到 `PAGE=1`。
### 优化循环
```
修复 → xelatex ×2 → grep 检查 → 仍有问题则继续修复
直到日志干净:无 Error、无 Overfull、无 Underfull、排版紧密
```
## 最终验证清单
- [ ] `grep -c 'Error' 论文.log` = 0
- [ ] 摘要 ≤ 1 页
- [ ] 所有 `\cite{}` 对应 `\bibitem{}`
- [ ] 所有图表被正文引用
- [ ] 无 Overfull/Underfull
- [ ] 图表位置正常,无大面积空白
- [ ] 中文渲染正常
## 输出
编译成功的 `论文.pdf` 文件。全部自动执行,不询问用户。From hongdotien10-hash/mathmodel-toolkit, MIT.
More from hongdotien10-hash/mathmodel-toolkit
- 0.479score
systematic-debugging
hongdotien10-hash
Debug experiment code with structured error analysis.
SkillCFreshness: CClaude Code +9 - 0.458score
逐题求解
hongdotien10-hash
按求解计划逐题编写Python代码求解,包含数据预处理、建模、求解、画图、灵敏度分析
SkillCFreshness: CClaude Code +9 - 0.458score
画图
hongdotien10-hash
使用matplotlib生成论文级质量图表,支持柱状图、折线图、热力图、散点图、饼图、箱线图等
SkillCFreshness: CClaude Code +9 - 0.458score
读取题目
hongdotien10-hash
读取数学建模竞赛的题目文件(PDF/DOCX)和数据文件(xlsx/docx),输出数据总览
SkillCFreshness: CClaude Code +9 - 0.458score
写论文
hongdotien10-hash
根据求解结果自动生成LaTeX论文,包含摘要、引言、模型建立与求解、检验、评价等完整章节
SkillCFreshness: CClaude Code +9 - 0.458score
求解计划
hongdotien10-hash
根据题目和数据生成详细的求解计划,包含思路、方法、输出标准和操作步骤
SkillCFreshness: CClaude Code +9 - 0.458score
数据预处理
hongdotien10-hash
数学建模数据预处理,包含缺失值处理、异常值检测、标准化/归一化、特征工程
SkillCFreshness: CClaude Code +9 - 0.458score
代码检查
hongdotien10-hash
检查数学建模Python求解代码的规范性,包括绘图标准、执行顺序、依赖限制、统计输出
SkillCFreshness: CClaude Code +9 - 0.458score
全自动求解
hongdotien10-hash
数学建模竞赛全自动求解+论文生成,从读取题目到编译PDF一气呵成
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 22, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from hongdotien10-hash
- 0.479score
systematic-debugging
hongdotien10-hash
Debug experiment code with structured error analysis.
SkillCFreshness: CClaude Code +9 - 0.458score
逐题求解
hongdotien10-hash
按求解计划逐题编写Python代码求解,包含数据预处理、建模、求解、画图、灵敏度分析
SkillCFreshness: CClaude Code +9 - 0.458score
画图
hongdotien10-hash
使用matplotlib生成论文级质量图表,支持柱状图、折线图、热力图、散点图、饼图、箱线图等
SkillCFreshness: CClaude Code +9 - 0.458score
读取题目
hongdotien10-hash
读取数学建模竞赛的题目文件(PDF/DOCX)和数据文件(xlsx/docx),输出数据总览
SkillCFreshness: CClaude Code +9 - 0.458score
写论文
hongdotien10-hash
根据求解结果自动生成LaTeX论文,包含摘要、引言、模型建立与求解、检验、评价等完整章节
SkillCFreshness: CClaude Code +9 - 0.458score
求解计划
hongdotien10-hash
根据题目和数据生成详细的求解计划,包含思路、方法、输出标准和操作步骤
SkillCFreshness: CClaude Code +9
Cite this page
编译论文 skill. Agent Mart. https://agentmart.dev/skills/hongdotien10-hash-4daf8d (last updated 2026-10-24)