5writing
数学建模竞赛论文撰写阶段,支持 Typst 和 LaTeX 双引擎。仅在全自主模式下执行:根据 ANALYSIS_MODELING_REPORT.md、RESULTS_REPORT.md 和 figures/*.pdf 选择比赛模板、排版引擎、组织章节,并在论文正文中按章节直接插入图表。在辅助模式下不调用。
Skill by QianXiao233
Chalk Labs
Need help deploying 5writing?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code. Read the repository before you give any tool access to your data.
npx agentmarket install skill/qianxiao233-5writing
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/5writing
Tools it pre-approves 9
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash(*),Read,Write,Edit,Grep,Glob,Agent,WebSearch,WebFetch
What's inside
- Skill name
5writing- Description
- 数学建模竞赛论文撰写阶段,支持 Typst 和 LaTeX 双引擎。仅在全自主模式下执行:根据 ANALYSIS_MODELING_REPORT.md、RESULTS_REPORT.md 和 figures/*.pdf 选择比赛模板、排版引擎、组织章节,并在论文正文中按章节直接插入图表。在辅助模式下不调用。
- License
- MIT
- Allowed tools
- Bash(*),, Read,, Write,, Edit,, Grep,, Glob,, Agent,, WebSearch,, WebFetch
- Instructions
- 497 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (200)
- SKILL.md
- main.tex · templates/en/apmcm-latex/
- references.tex · templates/en/apmcm-latex/
- 1_introduction.tex · templates/en/apmcm-latex/sections/
- 2_assumptions.tex · templates/en/apmcm-latex/sections/
- 3_model_design.tex · templates/en/apmcm-latex/sections/
- 4_solution.tex · templates/en/apmcm-latex/sections/
- 5_sensitivity.tex · templates/en/apmcm-latex/sections/
- 6_strengths_weaknesses.tex · templates/en/apmcm-latex/sections/
- 7_conclusions.tex · templates/en/apmcm-latex/sections/
- A_code.tex · templates/en/apmcm-latex/sections/
- main.typ · templates/en/apmcm/
- references.typ · templates/en/apmcm/
- 1_introduction.typ · templates/en/apmcm/sections/
- 2_assumptions.typ · templates/en/apmcm/sections/
- 3_model_design.typ · templates/en/apmcm/sections/
- 4_solution.typ · templates/en/apmcm/sections/
- 5_sensitivity.typ · templates/en/apmcm/sections/
- 6_strengths_weaknesses.typ · templates/en/apmcm/sections/
- 7_conclusions.typ · templates/en/apmcm/sections/
- A_code.typ · templates/en/apmcm/sections/
- main.tex · templates/en/default-latex/
- references.tex · templates/en/default-latex/
- 1_introduction.tex · templates/en/default-latex/sections/
- 2_assumptions.tex · templates/en/default-latex/sections/
- 3_notations.tex · templates/en/default-latex/sections/
- 4_model.tex · templates/en/default-latex/sections/
- 5_results.tex · templates/en/default-latex/sections/
- 6_sensitivity.tex · templates/en/default-latex/sections/
- 7_evaluation.tex · templates/en/default-latex/sections/
- 8_conclusions.tex · templates/en/default-latex/sections/
- A_code.tex · templates/en/default-latex/sections/
- main.typ · templates/en/default/
- references.typ · templates/en/default/
- 1_introduction.typ · templates/en/default/sections/
- 2_assumptions.typ · templates/en/default/sections/
- 3_notations.typ · templates/en/default/sections/
- 4_model.typ · templates/en/default/sections/
- 5_results.typ · templates/en/default/sections/
- 6_sensitivity.typ · templates/en/default/sections/
- 7_evaluation.typ · templates/en/default/sections/
- 8_conclusions.typ · templates/en/default/sections/
- A_code.typ · templates/en/default/sections/
- main.tex · templates/en/mcm-latex/
- references.tex · templates/en/mcm-latex/
- 1_introduction.tex · templates/en/mcm-latex/sections/
- 2_assumptions.tex · templates/en/mcm-latex/sections/
- 3_model_design.tex · templates/en/mcm-latex/sections/
- 4_solution.tex · templates/en/mcm-latex/sections/
- 5_sensitivity.tex · templates/en/mcm-latex/sections/
- 6_strengths_weaknesses.tex · templates/en/mcm-latex/sections/
- 7_conclusions.tex · templates/en/mcm-latex/sections/
- A_code.tex · templates/en/mcm-latex/sections/
- main.typ · templates/en/mcm/
- references.typ · templates/en/mcm/
- 1_introduction.typ · templates/en/mcm/sections/
- 2_assumptions.typ · templates/en/mcm/sections/
- 3_model_design.typ · templates/en/mcm/sections/
- 4_solution.typ · templates/en/mcm/sections/
- 5_sensitivity.typ · templates/en/mcm/sections/
- …and 140 more
SKILL.md (first lines)
# 竞赛论文撰写(Typst / LaTeX)
> **⚠️ 模式约束:本 skill 仅在全自主模式下执行。**
> 在辅助模式下,`1start-mathmodel` 不会调用本 skill。如果用户在辅助模式下要求"生成论文模板",只复制空模板框架到 `paper/`,不写入任何正文内容。
本 skill 承接 `3coding-visual` 和 `4drawio`。前序阶段只提供真实数据、图表 PDF 和记录文件;本阶段负责选择比赛模板和排版引擎、组织论文结构,并决定每张图表放入哪个章节。
**Typst 引擎**下可调用 typst-author skill 学习 typst 写法;**LaTeX 引擎**参考本文件末尾的"LaTeX 写作要点"小节。
**⚠️ 编译注意事项**:生成任何 `.typ` 文件前,先读 `../_references/typst_compile_notes.md`(Typst 编译踩坑实录:表格必须用 `#table` 而非 Markdown `|`、数学模式多字母变量加引号、`//` 是注释符、`#enum` 内容块写法、`table.header` 子元素、图片路径不越界等);写完必须 `typst compile` 验证通过再进入下一环节。
## 数学建模规范参考
如需领域判断,读取 `../_references/math_modeling_norms.md` 中的“论文写作”“图表与可视化”和“非数据图工具选择”小节。该文件只作为规范知识库,论文结构仍按比赛模板和当前赛题内容决定。
## 模板族
本技能内捆绑的模板位于:
```text
templates/zh/<竞赛>/main.typ # Typst 模板
templates/zh/<竞赛>-latex/main.tex # LaTeX 模板
templates/en/<竞赛>/main.typ # Typst 模板
templates/en/<竞赛>-latex/main.tex # LaTeX 模板
```
**LaTeX 模板覆盖范围**:所有中文模板和英文模板均已提供 LaTeX 版本(`-latex` 后缀),使用 xelatex 编译。
支持的中文模板(Typst + LaTeX 双版本):
```text
apmcm, changsanjiao, cumcm, default, diangongbei, dongsansheng,
huashubei, huaweibei, huazhongbei, mathorcup, mcm, shuweibei, stats, wuyibei
```
华为杯、华中杯、五一杯统一使用 `huaweibei`、`huazhongbei`、`wuyibei` 作为模板。
支持的英文模板(Typst + LaTeX 双版本):
```text
apmcm, default, mcm
```
论文中的所有数值图表结论必须来自 `reports/RESULTS_REPORT.md` 或 `figures/*`。不得编造、估算或使用不同的四舍五入方式。
## 排版硬规则(强制,违反即验收 FAIL)
1. **不设目录页**。竞赛论文不写目录,也不写"表格与插图清单""List of Figures"等前置清单页。本 skill 的 34 套模板(Typst + LaTeX 双引擎)已全部移除目录页——即 Typst 的 `outline()` 与 LaTeX 的 `\tableofcontents` / `\listoffigures` / `\listoftables`——**禁止再把目录加回来**。论文从摘要页直接进入正文。
2. **表上图下**。**表题(表 x 标题)位于表格上方**,**图题(图 x 标题)位于图形下方**:
- **Typst**:各模板导言区已内置
```typ
#show figure.where(kind: table): set figure.caption(position: top)
```
图题沿用 Typst 默认的"下方",无需额外设置。表格必须写成 `#figure(table(...), caption: [...])`(Typst 会自动识别 `kind: table`),**不要用裸 `#table(...)` 丢掉表题**。
- **LaTeX**:`\caption{}` 必须写在 `\begin{tabular}` / `\begin{longtable}` **之前**;图环境中 `\caption{}` 必须写在 `\includegraphics` **之后**。
3. 表题/图题的语言随论文语言(中文论文用"表 x / 图 x",英文论文用 Table x / Figure x),全文编号连续,并与正文引用一致。
4. **自检**:写完或改完论文后运行版面门禁,出现 FAIL 必须修好再继续:
```bash
python3 "<6verity skill 目录>/scripts/layout_check.py" --paper-dir paper --main paper/main.typ --pdf paper/main.pdf
```
## 工作流
### 步骤 0:确定排版引擎
**撰写论文前必须让用户选择排版引擎。** 引擎决定后续所有步骤(模板路径、章节文件扩展名、图片插入语法、编译命令),选错会导致整篇论文格式错误。
使用 AskUserQuestion 工具向用户询问:"撰写论文使用哪种排版引擎?"
- 选项 1:LaTeX(xelatex 编译,数学建模竞赛主流,模板已全部就绪)— 推荐选项放第一位
- 选项 2:Typst(typst 编译,调用 typst-author skill 辅助写作)
询问前先读取 `plan.md` 的"用户偏好 → 排版引擎"字段作为预选项:
- 若 plan.md 已记录引擎选择,向用户确认:"检测到之前选择的引擎是 <LaTeX/Typst>,是否沿用?"
- 若 plan.md 不存在或未记录引擎选择,直接询问用户选择。
- 若用户未明确指定或跳过,**默认使用 LaTeX**。
根据确定的引擎选择对应模板族:
- **Typst 引擎**:使用 `templates/<lang>/<竞赛>/main.typ`,调用 typst-author skill。编译命令 `typst compile main.typ`。
- **LaTeX 引擎**:使用 `templates/<lang>/<竞赛>-latex/main.tex`,xelatex 编译(中文和英文均需跑两遍解决交叉引用)。编译命令 `xelatex -interaction=nonstopmode main.tex`(执行两次)。
**后续步骤中的所有代码示例、文件扩展名、图片插入语法都必须按所选引擎选择对应版本,不要混用。**
### 步骤 1:选择语言和模板
除非用户明确要求中文,否则 MCM/ICM/COMAP 一律使用英文。所有中文竞赛名称使用中文。
模板键示例(Typst 引擎):
```text
长三角 -> zh/changsanjiao
APMCM 英文版 -> en/apmcm
全国赛/国赛/CUMCM -> zh/cumcm
统计建模 -> zh/stats
MCM/ICM/COMAP -> en/mcm
```
模板键示例(LaTeX 引擎):
```text
全国赛/国赛/CUMCM -> zh/cumcm-latex
MCM/ICM/COMAP -> en/mcm-latex
```
### 步骤 2:准备模板
用以下命令检查捆绑模板是否可访问(`SKILL_DIR` 为本 skill 所在目录):
**Typst 模板**:
```bash
ls "$SKILL_DIR/templates/zh/<竞赛>/main.typ" 2>/dev/null && echo "OK" || echo "MISSING"
```
```powershell
# Windows (PowerShell)
if (Test-Path "$env:SKILL_DIR/templates/zh/<竞赛>/main.typ") { "OK" } else { "MISSING" }
```From QianXiao233/mathmodel-assistant, MIT.
More from QianXiao233/mathmodel-assistant
- 0.563score
bzd-modeling-ideas
QianXiao233
Generate a coherent, whole-paper mathematical modeling solution framework from a complete contest problem.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
bzd-problem-analysis-checker
QianXiao233
Review a Chinese mathematical-modeling problem-analysis section against the original problem, checking task classification, data reasoning, cross-problem…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
bzd-paper-format-checker
QianXiao233
Review a complete mathematical-modeling competition paper with an atomic checklist covering abstract readability, page structure, typography, headings…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
bzd-modeling-workflow
QianXiao233
Orchestrate the BZD mathematical-modeling Skills across problem reading, idea generation, model selection, paper drafting, section checks, final format/AIGC…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
bzd-abstract-checker
QianXiao233
Review a user-provided Chinese mathematical-modeling abstract without requiring the problem statement or full paper, identify concrete writing defects, and…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
bzd-ai-usage-disclosure
QianXiao233
Generate or review mathematical-modeling competition AI tool usage statements and the anonymous AI工具使用详情.pdf.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
bzd-model-assumption-checker
QianXiao233
Review a mathematical-modeling paper's model-assumption section against the complete problem statement.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
bzd-model-dictionary
QianXiao233
Query the bundled BZD mathematical-modeling dictionary for a user-selected model, explain its assumptions, inputs, outputs, limitations and validation, then…
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
bzd-paper-aigc-auditor
QianXiao233
对数学建模竞赛论文进行两层AI痕迹审计——第一层9维检测(语言层面60%:连接词/排比/拔高词/被动句/段落规律/文本复杂度;事实层面40%:引文验证/数值一致性/术语一致性),第二层模型合理性深度审查。严格判分+一票否决+问题标红。输出分层HTML报告。
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
bzd-problem-restatement
QianXiao233
Generate a compliant Chinese mathematical-modeling problem-restatement chapter from a complete problem statement, or review a user's restatement against the…
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
bzd-cumcm-school-awards
QianXiao233
Query 2021-2025 CUMCM school awards and 2026 forecasts, or assess a student's preparation distance from provincial and national awards using school history…
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
bzd-model-solution-checker
QianXiao233
Review the model establishment, numerical solution, result analysis, model validation, and sensitivity or robustness sections of a mathematical-modeling paper…
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 10, 2026 (1 month 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 QianXiao233
- 0.563score
bzd-modeling-ideas
QianXiao233
Generate a coherent, whole-paper mathematical modeling solution framework from a complete contest problem.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
bzd-model-dictionary
QianXiao233
Query the bundled BZD mathematical-modeling dictionary for a user-selected model, explain its assumptions, inputs, outputs, limitations and validation, then…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
bzd-model-assumption-checker
QianXiao233
Review a mathematical-modeling paper's model-assumption section against the complete problem statement.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
bzd-abstract-checker
QianXiao233
Review a user-provided Chinese mathematical-modeling abstract without requiring the problem statement or full paper, identify concrete writing defects, and…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
bzd-ai-usage-disclosure
QianXiao233
Generate or review mathematical-modeling competition AI tool usage statements and the anonymous AI工具使用详情.pdf.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
bzd-modeling-workflow
QianXiao233
Orchestrate the BZD mathematical-modeling Skills across problem reading, idea generation, model selection, paper drafting, section checks, final format/AIGC…
SkillBFreshness: B★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get 5writing running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
5writing skill. Agent Mart. https://agentmart.dev/skills/qianxiao233-5writing (last updated 2026-10-24)