Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →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. Trigg
.claude/skills/brycewang-stanford-latex-thesis-zh/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 163% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 64% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 623% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 194% | 0% |
使用此 skill 处理已有中文 LaTeX 学位论文项目中的定向问题。保持低摩擦：先判断最小匹配模块，再运行对应脚本，最后以论文审阅友好的格式返回问题和建议。
当用户拥有一个现有中文 .tex 学位论文项目，并希望你帮助处理以下任务时使用本 skill：
即使用户只提到单一问题，例如“帮我判断是不是 thuthesis”“检查绪论逻辑”或“按 GB/T 7714 看参考文献”，也应触发本 skill。
不要将此 skill 用于：
paper-audit）latex-paper-en）| Module | Use when | Primary command | Read next | | --- | --- | --- | --- | | compile | Thesis build fails or toolchain is unclear | uv run python $SKILL_DIR/scripts/compile.py main.tex | references/modules/COMPILE.md | | format | User asks about thesis formatting or GB/T 7714 layout | uv run python $SKILL_DIR/scripts/check_format.py main.tex | references/modules/FORMAT.md | | structure | Need chapter/section map or thesis skeleton overview | uv run python $SKILL_DIR/scripts/map_structure.py main.tex | references/STRUCTURE_GUIDE.md | | consistency | Terms, abbreviations, or naming drift across chapters | uv run python $SKILL_DIR/scripts/check_consistency.py main.tex --terms | references/modules/CONSISTENCY.md | | template | Need to identify or validate thesis class/template | uv run python $SKILL_DIR/scripts/detect_template.py main.tex | references/modules/TEMPLATE.md | | bibliography | GB/T 7714 or BibTeX validation | uv run python $SKILL_DIR/scripts/verify_bib.py references.bib --standard gb7714 | references/modules/BIBLIOGRAPHY.md | | title | Optimize Chinese thesis titles and chapter titles | uv run python $SKILL_DIR/scripts/optimize_title.py main.tex --check | references/modules/TITLE.md | | deai | Reduce AI-writing traces in visible Chinese prose | uv run python $SKILL_DIR/scripts/deai_check.py main.tex --section introduction | references/modules/DEAI.md | | logic | Check logical coherence, introduction funnel, heading lead-ins, lit review quality, chapter mainline, and cross-section closure | uv run python $SKILL_DIR/scripts/analyze_logic.py main.tex --section related | references/modules/LOGIC.md | | experiment | Review experiment chapter language, discussion layering, and conclusion completeness | uv run python $SKILL_DIR/scripts/analyze_experiment.py main.tex --section experiments | references/modules/EXPERIMENT.md | | tables | 表格结构校验、三线表生成、booktabs 检查 | uv run python $SKILL_DIR/scripts/check_tables.py main.tex | references/modules/TABLES.md | | abstract | 摘要五要素结构诊断与字数校验 | uv run python $SKILL_DIR/scripts/analyze_abstract.py main.tex --lang zh | references/modules/ABSTRACT.md |
main.tex。--section SECTION，当用户只关注某一章或某一节。thuthesis、pkuthss 或特定高校要求。如果参数不完整，只追问入口 .tex 文件和目标模块，不额外扩展问题。
% MODULE (L##) [Severity] [Priority]: ...\cite{}、\ref{}、\label{}、数学环境、参考文献键和模板宏命令。$ARGUMENTS for entry file and module. If missing, ask for the thesis .tex entry file and target module.uv run python ....% Module (L##) [Severity] [Priority]: .... Report exact command and exit code on failure.template first, then structure.\cite{}, \ref{}, \label{}, math blocks, or bibliography keys unless explicitly asked.references/COMPILATION.md: compilation strategy and toolchain diagnosis.references/GB_STANDARD.md: GB/T 7714 and bibliography-related checks.references/STRUCTURE_GUIDE.md: thesis structure expectations and chapter mapping.references/LOGIC_COHERENCE.md: logic, coherence, heading lead-ins, consistency, and literature-review expectations.references/TITLE_OPTIMIZATION.md: Chinese academic title heuristics.references/DEAI_GUIDE.md: de-AI review heuristics.references/modules/EXPERIMENT.md: experiment-chapter review criteria.references/UNIVERSITIES/: school/template-specific constraints after template detection.只读取当前模块所需的参考文件，避免一次加载整套指南。
main.tex 为什么 XeLaTeX 一直编译失败，并判断是不是 thuthesis 模板。”| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 4,994 | 2,647 | -47% | 1 | 1 | 0% | 869 | 2,289 | +163% | 0 | 0 | — |
case-02 | fail→pass | 9,339 | 5,182 | -45% | 1 | 1 | 0% | 1,731 | 2,845 | +64% | 0 | 0 | — |
case-03 | fail→pass | 3,206 | 7,745 | +142% | 1 | 1 | 0% | 429 | 3,100 | +623% | 0 | 0 | — |
case-04 | pass→pass | 33,801 | 7,833 | -77% | 1 | 1 | 0% | 6,179 | 3,149 | -49% | 0 | 0 | — |
case-05 | fail→pass | 11,742 | 4,748 | -60% | 1 | 1 | 0% | 2,087 | 2,645 | +27% | 0 | 0 | — |
case-14 | fail→pass | 4,749 | 2,458 | -48% | 1 | 1 | 0% | 760 | 2,238 | +194% | 0 | 0 | — |
case-06 | fail→pass | 14,790 | 5,160 | -65% | 1 | 1 | 0% | 2,439 | 2,805 | +15% | 0 | 0 | — |
case-07 | fail→pass | 9,756 | 3,884 | -60% | 1 | 1 | 0% | 1,818 | 2,399 | +32% | 0 | 0 | — |
case-08 | fail→pass | 14,343 | 4,488 | -69% | 1 | 1 | 0% | 2,465 | 2,537 | +3% | 0 | 0 | — |
case-09 | fail→pass | 11,754 | 3,133 | -73% | 1 | 1 | 0% | 1,931 | 2,351 | +22% | 0 | 0 | — |
case-10 | fail→pass | 10,530 | 3,210 | -70% | 1 | 1 | 0% | 1,608 | 2,312 | +44% | 0 | 0 | — |
case-11 | fail→pass | 10,806 | 2,870 | -73% | 1 | 1 | 0% | 1,841 | 2,345 | +27% | 0 | 0 | — |
case-12 | fail→pass | 13,845 | 3,832 | -72% | 1 | 1 | 0% | 2,951 | 2,536 | -14% | 0 | 0 | — |
case-13 | fail→pass | 11,284 | 4,159 | -63% | 1 | 1 | 0% | 2,205 | 2,473 | +12% | 0 | 0 | — |
case-15 | fail→pass | 8,862 | 4,591 | -48% | 1 | 1 | 0% | 1,618 | 2,647 | +64% | 0 | 0 | — |
case-16 | fail→pass | 12,196 | 8,071 | -34% | 1 | 1 | 0% | 2,143 | 3,230 | +51% | 0 | 0 | — |
case-17 | fail→pass | 10,226 | 2,461 | -76% | 1 | 1 | 0% | 1,709 | 2,228 | +30% | 0 | 0 | — |
case-18 | fail→pass | 6,229 | 2,278 | -63% | 1 | 1 | 0% | 1,040 | 2,211 | +113% | 0 | 0 | — |
case-19 | pass→fail | 8,309 | 3,532 | -57% | 1 | 1 | 0% | 1,511 | 2,392 | +58% | 0 | 0 | — |
case-20 | pass→fail | 11,948 | 3,858 | -68% | 1 | 1 | 0% | 1,855 | 2,367 | +28% | 0 | 0 | — |
case-21 | fail→pass | 15,164 | 2,850 | -81% | 1 | 1 | 0% | 2,619 | 2,393 | -9% | 0 | 0 | — |
case-22 | fail→pass | 6,921 | 2,188 | -68% | 1 | 1 | 0% | 1,241 | 2,218 | +79% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +77 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.