migrating-latex-templates
当用户明确要求"迁移标书""升级模板""跨版本迁移""旧标书转新模板"时使用。智能迁移NSFC LaTeX标书到新版模板，基于五阶段工作流（分析→映射→规划→执行→验证），自动处理结构变化、内容重组、引用更新；支持AI驱动语义匹配与启发式回退，并提供 runs 输出隔离与一键迁移脚本。
Best use case
migrating-latex-templates is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
当用户明确要求"迁移标书""升级模板""跨版本迁移""旧标书转新模板"时使用。智能迁移NSFC LaTeX标书到新版模板，基于五阶段工作流（分析→映射→规划→执行→验证），自动处理结构变化、内容重组、引用更新；支持AI驱动语义匹配与启发式回退，并提供 runs 输出隔离与一键迁移脚本。
Teams using migrating-latex-templates should expect a more consistent output, faster repeated execution, less prompt rewriting, better workflow continuity with your supporting tools.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
- You already have the supporting tools or dependencies needed by this skill.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/transfer_old_latex_to_new/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How migrating-latex-templates Compares
| Feature / Agent | migrating-latex-templates | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
当用户明确要求"迁移标书""升级模板""跨版本迁移""旧标书转新模板"时使用。智能迁移NSFC LaTeX标书到新版模板，基于五阶段工作流（分析→映射→规划→执行→验证），自动处理结构变化、内容重组、引用更新；支持AI驱动语义匹配与启发式回退，并提供 runs 输出隔离与一键迁移脚本。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# LaTeX 标书智能迁移器 > **核心入口**：`python skills/transfer_old_latex_to_new/scripts/run.py --help` > > **一键迁移**：`bash skills/transfer_old_latex_to_new/scripts/migrate.sh --old ... --new ...` > > **配置中心**：[config.yaml](config.yaml) > > **参考文档**：[references/](references/) > > **拆分文档**： > [references/quickstart.md](references/quickstart.md) / > [references/config_guide.md](references/config_guide.md) / > [references/api_reference.md](references/api_reference.md) / > [references/troubleshooting.md](references/troubleshooting.md) / > [references/faq.md](references/faq.md) / > [references/case_study_2025_to_2026.md](references/case_study_2025_to_2026.md) --- ## 快速开始 ```bash # 一键分析（生成结构差异报告） python skills/transfer_old_latex_to_new/scripts/run.py analyze \ --old /path/to/NSFC_2025 \ --new /path/to/NSFC_2026 # 一键应用（执行迁移，apply前自动快照） python skills/transfer_old_latex_to_new/scripts/run.py apply \ --old /path/to/NSFC_2025 \ --new /path/to/NSFC_2026 \ --run-id <上一步输出的run_id> # 一键编译（验证迁移结果） python skills/transfer_old_latex_to_new/scripts/run.py compile \ --run-id <run_id> \ --new /path/to/NSFC_2026 # 一键恢复（回滚到apply前状态） python skills/transfer_old_latex_to_new/scripts/run.py restore \ --run-id <run_id> \ --new /path/to/NSFC_2026 ``` ### 一键迁移（推荐） ```bash bash skills/transfer_old_latex_to_new/scripts/migrate.sh \ --old /path/to/NSFC_2025 \ --new /path/to/NSFC_2026 ``` ### runs 输出隔离（强烈建议：测试/批处理） ```bash python skills/transfer_old_latex_to_new/scripts/run.py analyze \ --old /path/to/NSFC_2025 \ --new /path/to/NSFC_2026 \ --runs-root /path/to/runs ``` **输出目录**：默认 `skills/transfer_old_latex_to_new/runs/<run_id>/`；指定 `--runs-root` 则输出到该目录。 ``` runs/<run_id>/ ├── input_snapshot/ # 旧新项目输入快照 ├── analysis/ # 结构分析JSON（sections_map_*.json, structure_diff.json） ├── plan/ # 迁移计划（migration_plan.json） ├── backup/ # Apply前新项目快照（用于restore） ├── logs/ # 执行日志与编译输出 │ ├── apply_result.json # 迁移执行结果 │ ├── compile_summary.json # 编译摘要 │ ├── compile_*_*.out.txt # 编译标准输出 │ ├── compile_*_*.err.txt # 编译标准错误 │ └── latex_aux/ # LaTeX 中间文件隔离目录 │ ├── main.aux # 辅助文件 │ ├── main.log # 编译日志 │ ├── main.bbl # BibTeX 输出 │ ├── main.blg # BibTeX 日志 │ ├── main.out # hyperref 输出 │ ├── main.toc # 目录文件 │ └── *.aux # 其他辅助文件 └── deliverables/ # 交付物（PDF、报告、指南） ``` **中间文件隔离**: 所有 LaTeX 编译中间文件(.aux/.log/.bbl等)自动保存在 `logs/latex_aux/` 目录,避免在项目目录产生"垃圾"文件。最终 PDF 自动复制回项目根目录。 --- ## 前置约束（铁律） ### 修改范围白名单 **✅ 可修改**: - `extraTex/*.tex` 内容文件（**排除** `@config.tex`） - 新项目 `references/*.bib`（如需更新引用格式） - 本技能运行产物：`runs/<run_id>/`（日志、分析、备份、交付物） **❌ 禁止修改**: - `main.tex` 模板结构文件 - `extraTex/@config.tex` 配置文件 - `.cls`、`.sty` 样式文件 - 任何影响编译环境的系统文件 更完整的流程说明、配置与排障文档已拆分到 `references/`： - [references/quickstart.md](references/quickstart.md) - [references/config_guide.md](references/config_guide.md) - [references/api_reference.md](references/api_reference.md) - [references/troubleshooting.md](references/troubleshooting.md) ## 📋 版本与变更 **当前版本**: v1.4.0（与 [config.yaml](config.yaml) 同步） **变更记录**: 见根级 [CHANGELOG.md](../../../CHANGELOG.md) **优化计划**: 质量评估与优化计划见 `plans/v202601081355.md`（仓库根级） --- **最后更新**: 2026-01-08 **维护者**: Bensz Conan **许可证**: MIT
Related Skills
make_latex_model
当用户明确要求"LaTeX 模板优化""样式参数对齐""make_latex_model"时使用。支持任意 LaTeX 模板的样式参数对齐、标题文字对齐、标题格式对比（加粗）、HTML 可视化报告、LaTeX 自动修复建议和像素级 PDF 对比验证。
acpx
Use the ACPX CLI through DrClaw's existing exec/long_exec tools to run Codex in the current project workspace.
ui-ux-pro-max
[Frontend] Frontend UI/UX design intelligence - activate FIRST when user requests beautiful, stunning, gorgeous, or aesthetic interfaces. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks. Triggers on ui design, ux design, design system, color palette, typography, glassmorphism, claymorphism, neumorphism, bento grid, font pairing, ui-ux-pro-max, stunning interface, beautiful ui.
fetch
Fetch metadata and links from arXiv for a given query.
web_literature_mining
Scientific Literature Mining - Mine scientific literature: PubMed search, arXiv search, web search, and Tavily deep search. Use this skill for scientific informatics tasks involving pubmed search search literature search web tavily search. Combines 4 tools from 2 SCP server(s).
uniprot_deep_analysis
UniProt Deep Protein Analysis - Deep UniProt analysis: entry data, UniRef clusters, UniParc cross-references, and gene-centric view. Use this skill for protein science tasks involving get uniprotkb entry by accession get uniref cluster by id get uniparc entry by upi get gene centric by accession. Combines 4 tools from 1 SCP server(s).
synthetic_biology_design
Synthetic Biology Design - Design synthetic biology construct: gene lookup, codon optimization, protein property prediction, and structure prediction. Use this skill for synthetic biology tasks involving get sequence id DegenerateCodonCalculatorbyAminoAcid calculate protein sequence properties pred protein structure esmfold. Combines 4 tools from 4 SCP server(s).
structural_homology_modeling
Structural Homology & Evolution Analysis - Analyze protein evolution: get gene tree from Ensembl, find homologs, compare sequences, and predict structure. Use this skill for evolutionary biology tasks involving get homology symbol get genetree member symbol calculate protein sequence properties pred protein structure esmfold. Combines 4 tools from 3 SCP server(s).
proteome_analysis
Proteome-Level Analysis - Analyze at proteome level: get proteome from UniProt, gene-centric view, functional annotation from STRING. Use this skill for proteomics tasks involving get proteome by id get gene centric by proteome get functional annotation. Combines 3 tools from 2 SCP server(s).
protein_structure_analysis
Protein Structure Comprehensive Analysis - Comprehensive structure analysis: download PDB, extract chains, calculate geometry, quality metrics, and composition. Use this skill for structural biology tasks involving retrieve protein data by pdbcode extract pdb chains calculate pdb structural geometry calculate pdb quality metrics calculate pdb composition info. Combines 5 tools from 1 SCP server(s).
protein_solubility_optimization
Protein Solubility Optimization - Optimize protein solubility: calculate properties, predict solubility, predict hydrophilicity, and suggest mutations. Use this skill for protein engineering tasks involving calculate protein sequence properties predict protein function ComputeHydrophilicity zero shot sequence prediction. Combines 4 tools from 3 SCP server(s).
protein_similarity_search
Protein Similarity Search - Search for similar proteins: extract sequence from PDB, search structures with FoldSeek, find homologs with STRING, and check UniProt. Use this skill for bioinformatics tasks involving extract pdb sequence foldseek search get best similarity hits between species search uniprotkb entries. Combines 4 tools from 3 SCP server(s).