ChineseResearchLaTeX is a collection of LaTeX templates and an AI-assisted workflow for preparing Chinese research documents such as grant proposals, papers, theses, and academic CVs. Researchers use it to plan, format, review, compile, and revise these documents with human oversight. The catalogue skills and instructions support its agent-based research-writing workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add huangwb8/ChineseResearchLaTeX --skill transfer-old-latex-to-newgit clone --depth 1 https://github.com/huangwb8/ChineseResearchLaTeXWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/huangwb8/chineseresearchlatex/transfer-old-latex-to-new)<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/transfer-old-latex-to-new"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/transfer-old-latex-to-new/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/transfer-old-latex-to-new"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/transfer-old-latex-to-new.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00161 | $0.02304 |
| Opus 5 | $0.00081 | $0.01152 |
| Sonnet 5 | $0.00032 | $0.00461 |
| Haiku 4.5 | $0.00016 | $0.00230 |
Grade A, and why
transfer-old-latex-to-new scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChineseResearchLaTeX 内容迁移技能
输入原则
不要要求用户先整理成固定输入协议。默认接受并消化任意合理输入，例如：
- 一个完整旧项目目录
- 若干
.tex/.bib/.docx/.md/.txt - PDF、截图、图片
- 一份已有模板项目路径，加上一些迁移目标说明
- 多种输入混合出现
如果材料不完整，不要先追问“标准输入”；先判断目标产品线、合适承载项目、哪些内容能直接落入 extraTex/*.tex 或 references/*.bib，以及哪些诉求已经超出内容迁移边界。只有缺失信息会导致把正文放错位置时，才请求补充。
输出原则
不要把输出理解成“任意重构仓库”。本 skill 的有效输出通常只有：
- 把正文迁移到目标项目的
extraTex/*.tex - 把参考文献迁移到目标项目的
references/*.bib - 生成必要的迁移说明、风险提示、未落位清单
- 在构建成功后给出验证结果
以下动作都超出本 skill 的边界：模板源码改动、样式修复、wrapper / main.tex / template.json / README 的结构重写，以及公共包抽取或包级能力沉淀。默认把用户原始材料视为只读，目标模板视为只读骨架；样式差异只报告，不偷改。
Legacy CLI 的定位
scripts/run.py、scripts/migrate.sh 仍然保留，但只作为经典 old/new 目录迁移的后备入口。即使使用 legacy CLI，也必须继续遵守本文件的硬性边界：旧项目可以读，新项目只能写内容层，不能借 CLI 绕过模板保护。
不适用场景
以下场景不要继续使用本 skill 直接落地：
- 用户要“做一个新模板”
- 用户要“把旧样式 1:1 复刻到当前仓库”
- 用户要改
packages/bensz-*、projects/*里的模板入口或样式文件 - 用户要新增模板承载位点、封面结构、目录结构、profile、class、style
这些都应转交模板开发链路。
流程
输入
按用户请求和配置文件提供必要输入；缺失信息应明确列出并停止依赖该输入的步骤。
执行步骤
这个 skill 仍然要识别目标产品线，但目的只是选对承载项目，而不是判断“该不该改 packages/”。
- NSFC：选择合适的
projects/NSFC_* - SCI 论文：选择
projects/paper-sci-01/ - 毕业论文：选择最接近的
projects/thesis-* - 简历：选择
projects/cv-01/
然后把旧材料中的正文内容映射到这些现成项目的内容文件里；默认优先选择最接近的现有项目，而不是新建或重组模板结构。
识别目标产品线与承载项目
先回答三个问题：用户最终要落到哪条产品线、当前仓库哪个现有项目最适合作为承载容器、这次任务是“内容迁移”还是已经变成“模板开发”。如果已经变成模板开发，立即转交，不要继续伪装成内容迁移任务。
清点可迁移内容
从输入中提炼可直接复用的正文段落、BibTeX、需要人工确认的缺口，以及会触发模板改动需求的超界诉求。
做内容层映射
只在内容层做映射：
- 旧正文 →
extraTex/*.tex - 旧参考文献 →
references/*.bib
不要把“映射”理解成：
- 改章节命令
- 改模板标题样式
- 改目录/封面/页眉页脚
- 改公共包接口
执行迁移
执行时只允许覆盖目标内容文件、新建目标内容文件（若模板已有对应承载位点）、以及写入或补齐 .bib。
如果某项需求必须改模板骨架才能完成，不要继续自动修改；应明确标出受阻位置和原因，并建议改用 make-latex-model。
官方入口验证
迁移完成后，尽量用对应产品线的官方入口验证：
- NSFC：
python packages/bensz-nsfc/scripts/nsfc_project_tool.py build --project-dir <项目路径> - SCI：
python packages/bensz-paper/scripts/paper_project_tool.py build --project-dir <项目路径> - Thesis：
python packages/bensz-thesis/scripts/thesis_project_tool.py build --project-dir <项目路径> - CV：
python packages/bensz-cv/scripts/cv_project_tool.py build --project-dir <项目路径> --variant all
What ships with it
45 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- CHANGELOG.md 2.5 KB
- config.yaml 21 KB
- README.md 6.3 KB
- references/api_reference.md 2.1 KB
- references/case_study_2025_to_2026.md 2.0 KB
- references/compliance_check.md 1.7 KB
- references/config_guide.md 1.9 KB
- references/faq.md 1.5 KB
- references/implementation_status.md 2.8 KB
- references/migration_patterns.md 3.2 KB
- references/optimization_summary.md 727 B
- references/quickstart.md 2.6 KB
- references/structure_mapping_guide.md 2.1 KB
- references/troubleshooting.md 1.3 KB
- references/version_differences_2025_2026.md 1.9 KB
- scripts/core/__init__.py 1.2 KB runs code
- scripts/core/ai_integration.py 9.2 KB runs code
- scripts/core/cache_manager.py 6.4 KB runs code
- scripts/core/compiler.py 7.0 KB runs code
- scripts/core/config_loader.py 7.0 KB runs code
- scripts/core/config_utils.py 5.7 KB runs code
- scripts/core/content_optimizer.py 9.5 KB runs code
- scripts/core/json_utils.py 9.4 KB runs code
- scripts/core/latex_utils.py 5.1 KB runs code
- scripts/core/mapping_engine.py 15 KB runs code
- scripts/core/migration_plan.py 3.4 KB runs code
- scripts/core/migrator.py 18 KB runs code
- scripts/core/progress_utils.py 8.3 KB runs code
- scripts/core/project_analyzer.py 4.1 KB runs code
- scripts/core/prompt_templates.py 3.8 KB runs code
- scripts/core/README.md 7.9 KB
- scripts/core/reference_guardian.py 5.8 KB runs code
- scripts/core/reference_validator.py 6.5 KB runs code
- scripts/core/reports.py 5.0 KB runs code
- scripts/core/resource_manager.py 9.2 KB runs code
- scripts/core/run_manager.py 2.2 KB runs code
- scripts/core/security_manager.py 3.7 KB runs code
- scripts/core/snapshot.py 1.8 KB runs code
- scripts/core/word_count_adapter.py 13 KB runs code
- scripts/demo.py 5.6 KB runs code
- scripts/migrate.sh 2.6 KB runs code
- scripts/quicktest.py 4.1 KB runs code
- scripts/README.md 2.5 KB
- scripts/run.py 16 KB runs code
- scripts/validate_config.py 8.9 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago Changed · +1 lines 47e7fb28be34
- 13d ago First seen · 161 lines · 161 tokens per session scan A 554c963a1a7a
transfer-old-latex-to-new is a skill published in the GitHub repository huangwb8/ChineseResearchLaTeX (2,726 stars, last pushed yesterday), licensed MIT. It adds 161 tokens to every session and 2,304 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
nature-data
Prepare, audit, or revise Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts. Use when the user asks about Nature data availability, research data sharing, repository selection, accession numbers, restricted or sensitive data, source data…
publication-chart-skill
This skill should be used when the user asks for a publication-quality scientific figure or table, wants help choosing the right chart for results, needs a paper-ready pubfig or pubtab workflow, wants a figure + companion table for a results section, wants an Excel sheet turned into publication-ready LaTeX, or wants…
obsidian-source-ingestion
Use this skill to ingest external materials into the current project-scoped Obsidian KB as source notes under Sources/Papers, Sources/Web, Sources/Docs, Sources/Data, Sources/Interviews, or Sources/Notes.
visual-html-renderer
A shared workflow for turning requested content into a final HTML document that can be checked and previewed in a browser. It chooses a document structure, renders it, validates the result, and returns a temporary preview link.
plain-report
Use this tool only when the user explicitly asks to create a plain report.
latex-conference-template-organizer
Organize messy conference LaTeX template .zip files into clean Overleaf-ready structure. Use when the user asks to "organize LaTeX template", "clean up .zip template", or "prepare Overleaf submission template".