Skip to content

brycewang-stanford/Auto-Empirical-Research-Skills / skills/35-bahayonghang-academic-writing-skills/skills/latex-thesis-zh

latex-thesis-zh

Verified

Chinese LaTeX thesis assistant for existing .tex degree thesis projects (XeLaTeX/LuaLaTeX/latexmk). Use this skill whenever a user works on a Chinese master's or doctoral thesis needing compilation, GB/T 7714 bibliography checks, chapter structure mapping, template detection (thuthesis, pkuthss), terminology consistency, logic coherence review, heading lead-in checks, title optimization, de-AI editing, experiment chapter review, three-line table validation, or abstract structure diagnosis. Trigger even for single issues like "帮我编译论文", "检查国标格式", "看看绪论逻辑", "毕业论文", "学位论文", "硕士/博士论文", "三线表", "检查摘要", or "摘要结构".

FileKindSize
SKILL.mdskill md7.8 KB
agents/openai.yamlconfig348 B
evals/evals.jsonconfig7.1 KB
examples/bibliography-and-deai.mdmarkdown525 B
examples/compile-and-template.mdmarkdown463 B
examples/structure-and-consistency.mdmarkdown544 B
references/ABSTRACT_STRUCTURE.mdmarkdown4.9 KB
references/ACADEMIC_STYLE_ZH.mdmarkdown3.8 KB
references/CAPTION_GUIDE.mdmarkdown2.2 KB
references/COMPILATION.mdmarkdown2.0 KB
references/DEAI_GUIDE.mdmarkdown17.8 KB
references/FORBIDDEN_TERMS.mdmarkdown1.3 KB
references/GB_STANDARD.mdmarkdown3.8 KB
references/LOGIC_COHERENCE.mdmarkdown7.4 KB
references/STRUCTURE_GUIDE.mdmarkdown4.2 KB
references/TABLE_GUIDE.mdmarkdown2.6 KB
references/TITLE_OPTIMIZATION.mdmarkdown7.1 KB
references/UNIVERSITIES/generic.mdmarkdown2.1 KB
references/UNIVERSITIES/pku.mdmarkdown1.5 KB
references/UNIVERSITIES/tsinghua.mdmarkdown1.3 KB
references/UNIVERSITIES/yanshan.mdmarkdown1.2 KB
references/WRITING_PHILOSOPHY_ZH.mdmarkdown4.9 KB
references/modules/ABSTRACT.mdmarkdown1.2 KB
references/modules/BIBLIOGRAPHY.mdmarkdown1.3 KB
references/modules/COMPILE.mdmarkdown1.1 KB
references/modules/CONSISTENCY.mdmarkdown2.1 KB
references/modules/DEAI.mdmarkdown1.6 KB
references/modules/EXPERIMENT.mdmarkdown4.9 KB
references/modules/FORMAT.mdmarkdown988 B
references/modules/LOGIC.mdmarkdown2.3 KB
references/modules/TABLES.mdmarkdown1.3 KB
references/modules/TEMPLATE.mdmarkdown1.3 KB
references/modules/TITLE.mdmarkdown1.5 KB
scripts/analyze_abstract.pyscript17.3 KB
scripts/analyze_experiment.pyscript10.3 KB
scripts/analyze_logic.pyscript24.2 KB
scripts/check_consistency.pyscript12.1 KB
scripts/check_format.pyscript7.0 KB
scripts/check_references.pyscript17.6 KB
scripts/check_tables.pyscript16.3 KB
scripts/compile.pyscript15.8 KB
scripts/deai_batch.pyscript10.0 KB
scripts/deai_check.pyscript18.1 KB
scripts/detect_template.pyscript3.7 KB
scripts/generate_table.pyscript8.8 KB
scripts/map_structure.pyscript11.3 KB
scripts/online_bib_verify.pyscript11.9 KB
scripts/optimize_title.pyscript12.5 KB
scripts/parsers.pyscript10.7 KB
scripts/verify_bib.pyscript9.7 KB

references/modules/EXPERIMENT.md

View on GitHub
# Role
你是一位资深的计算机科学领域中文学术专家和顶级中文期刊/双盲评审组长(如《计算机学报》、《软件学报》、《自动化学报》)。你擅长处理实验数据,并能够将其提炼撰写为符合中文核心期刊与高标准学位论文要求的、严谨流畅的学术分析段落。

# Task
请仔细阅读并分析提供的 **[实验数据或说明草稿]**,提取核心特征、趋势与对比结论,将其扩写为符合中文顶刊规范的 LaTeX 实验分析段落。

# Constraints
1. **数据真实性约束**:
   - 所有的推演和结论**必须**严格基于输入数据,禁止无中生有、夸大提升幅度或虚构数据。
   - 若数据未表现出显著优势,应客陈述表现一致或具竞争力,切勿强行声称“显著提升”。

2. **分析深度要求(拒绝流水账)**:
   - 绝不仅仅进行数值的列表式报告(如“方法A是0.5,方法B是0.6”),必须强调各个基线模型前后的**对比趋势**。
   - 分析需涵盖:有效性(基线对比)、参数敏感性、性能与效率的权衡、或消融实验中各组件的贡献度。
   - 统计严谨性:如有标准差、方差或多次实验设置信息,应当在分析中强调其统计意义上的稳定性。

3. **格式与排版严苛准则**:
   - **正文禁用一切粗体/斜体强调**:禁止使用 `\textbf{}`、`\emph{}` 来框选数据或模型名,纯学术文本需靠逻辑本身突显重点。
   - **禁止列表**:严禁使用 `\begin{itemize}` 乃至其变体环境。必须以流畅清晰的中文学术段落呈现。
   - **强制段落结构**:段首强制使用 `\paragraph{核心论点结论}`(例如 `\paragraph{所提方法在各类基准上具有显著优越性}`)。紧随其后在同一段落内展开详细的数据引证和逻辑分析。
   - **公式排版**:所有字母变量、算法缩写(如 $K$, $N$)、指标(如 $F_1$)需使用 LaTeX 内联数学模式 `$ ... $` 包裹。

4. **语言与语气规范**:
   - **极端客观学术化**:彻底剔除口语与夸张表达(如“效果很好”、“碾压”、“毫无保留地领先”)。统一使用规范学术语:“相比于...基线模型,该方法在...指标上相对提高了 X%”、“展现了更强的鲁棒性”等。
   - 用词统一标准:将“我们”替换为默认的被动语态或主语省略(如“实验结果表明”、“数据证实”)。

5. **输出格式规定**:
   - 输出**且仅输出**一段包含完整排版语法的 LaTeX 代码片段。
   - 务必转义 LaTeX 特殊字符(如 `%`,`_` 等)。
   - 绝不要添加类似于 "好的,以下是为您生成的分析..." 等任何对话语气词!

# Input
[Provided by the user or the analyze_experiment.py script]

---

# 讨论与文献回溯 (B3-B4)

## B3: 讨论深度 — 归因分析而非数据重复

**规则**:讨论章节不能仅仅重复实验数据。应使用因果/归因语言解释结果背后的*原因*。仅复述表格数字而不加解读的讨论是浅层的。

**检测启发式**(脚本自动化):
- 扫描 `discussion` 章节所有可见行
- 统计包含归因标记的行数:`原因|机制|表明|解释为|归因于|导致|由于|之所以|这是因为|根本原因|本质上|究其原因|可能是因为`
- 若比例 < 总可见行数的15%(最少5行) → Major/P1

| 模式 | 判定 |
|------|------|
| "模型A准确率为95%。模型B准确率为90%。" | 浅层重复(标记) |
| "模型A优于模型B,这可能是因为其能够捕获长程依赖关系。" | 归因分析(通过) |

## B4: 结果-文献回溯

**规则**:讨论应引用相关工作中的文献来对比发现。相关工作中的引用键应在讨论中重现,表明作者已将结果置于文献语境中。

**检测启发式**(脚本自动化):
- 从 `related` 章节范围提取引用键(`\cite{...}`)
- 从 `discussion` 章节范围提取引用键
- 若交集为零 → Major/P1

**修正**:添加如"与张三等\cite{zhang2020}的发现一致,本文结果证实..."或"与李四\cite{li2019}的方法不同,本文方法展现了..."的语句。

---

# 结论完整性检查 (B5)

**规则**:完整的结论必须包含三个要素:
1. **核心发现总结** — 明确重述研究所证明的内容
2. **启示/意义** — 更广泛的影响或实践价值
3. **局限/未来工作** — 承认研究边界与后续方向

**检测启发式**(脚本自动化):
- 扫描 `conclusion` 章节的三类关键词:
  - 发现:`本文证明了|实验表明|结果表明|本文提出了|研究发现|关键发现|主要结果`
  - 启示:`启示|应用价值|实际意义|使.*成为可能|推动|促进|有助于|实践意义`
  - 局限:`局限|不足|展望|未来工作|有待|进一步研究|改进方向|后续工作`
- 缺少局限 → Major/P1
- 缺少启示 → Minor/P2
- 缺少发现总结 → Minor/P2
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall