Install
$ agentstack add skill-mrsgsa-math-modeling-skill-dify-docx ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ● Filesystem access Used
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
DOCX 工具
路径与写入
- 当前目录为本工具根目录,只读。
- 模板和脚本从本目录读取。
- 生成或修改后的 DOCX 必须写入用户
PROJECT_ROOT。 - 默认不覆盖输入文件或 Skill 文件。
数学建模论文推荐流程
采用“当届官方参考模板 + python-docx 构建 + OMML 公式 + OOXML 校验 + 渲染抽检”。官方模板控制页面、样式、分节、页眉页脚和编号;代码负责稳定写入内容。
from pathlib import Path
import sys
scripts = Path("") / "tools" / "docx" / "scripts"
sys.path.insert(0, str(scripts))
import paper_format as pf
doc = pf.new_document(
contest="cumcm",
template_path=Path("") / "当届官方模板.docx",
preserve_template_content=False,
)
# 此示例只借用模板样式后追加正文。
# 若官方模板包含固定摘要页或编号页,应改为 True 并在原位置填充。
pf.title(doc, "论文题目")
pf.abstract_title(doc)
pf.body(doc, "摘要正文。")
pf.keywords(doc, "优化;预测")
pf.equation(doc, r"\min f(x)=\sum_{i=1}^{n}x_i^2")
pf.three_line_table(doc, [["符号", "说明"], ["x", "决策变量"]])
pf.save_document(doc, Path(""), contest="cumcm")
公式
直接写入
scripts/equations.py 把常用 LaTeX 子集转成 Word 原生 OMML。未知命令、未闭合分组和不支持环境会报错,不会静默生成错误文本。
python scripts/equations.py replace "输入.docx" `
--replace "EQ_OBJECTIVE" "\min f(x)=\sum_{i=1}^{n}x_i^2" `
--output "/输出.docx"
同一占位符出现多次时会全部替换。支持分式、上下标、根式、n 次根、常用希腊字母与关系符号、反三角函数和常见矩阵,包括 \nu、\mu、\approx、\arcsin、\arccos、\arctan。
复杂公式
复杂 LaTeX 优先使用 Pandoc 的成熟转换:
python scripts/equations.py generate "论文.md" `
--output "/论文.docx" `
--template "官方模板.docx"
转换后仍须校验和渲染抽检。
解包、校验与重打包
DOCX/XLSX 共用的 OOXML 基础工具只保留在 scripts/office/:
python scripts/office/unpack.py "输入.docx" "/unpacked"
python scripts/office/validate.py "/输出.docx"
python scripts/office/pack.py "/unpacked" "/输出.docx" --original "输入.docx"
不要在不理解 OOXML 关系和内容类型的情况下直接修改压缩包。
修订
python scripts/accept_changes.py "输入.docx" "/已接受修订.docx"
工具使用隔离的 LibreOffice 配置。超时、非零退出或残留修订标记都会失败,失败时不发布输出文件。
批注
先解包,再添加批注元数据和文档标记。父批注不存在或批注 ID 重复时,工具会在写入前失败。
python scripts/comment.py "/unpacked" 0 "批注意见"
python scripts/comment.py "/unpacked" 1 "回复意见" --parent 0
必做验证
python scripts/check_env.py
python scripts/self_check.py
python scripts/office/validate.py "/完整论文.docx"
调用 validate_paper_structure() 检查官方前置结构、摘要页渲染填充率、正文篇幅质量目标、公式/图/表数量、图表编号与正文引用、参考文献双向对应,并分别传入PDF总页数、正文页数、摘要有效区域填充率和电子文件大小。CUMCM默认以摘要充实且不溢出一页、正文恰好30页为优选质量目标;以2026年官方规范为例,正文不超过30页、电子论文不超过20MB才是硬约束,附录和PDF总页数不限。一级标题默认连续排版,不得逐章强制分页制造空白。结构校验后,把DOCX渲染成PDF或图片抽检分页、公式、表格、图片、页眉页脚和字体替换。
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: MrSGSA
- Source: MrSGSA/math-modeling-skill-dify
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.