Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hongdotien10-hash-c47812
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
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/mrite-code
What's inside
- Skill name
逐题求解- Description
- 按求解计划逐题编写Python代码求解,包含数据预处理、建模、求解、画图、灵敏度分析
- License
- MIT
- Instructions
- 243 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "逐题求解" does not match folder "mrite-code"
Files (1)
- SKILL.md
SKILL.md (first lines)
# 逐题求解
## 目的
为每个子问题编写Python求解脚本,先算后画,每题至少4-6张图,完成灵敏度分析。
## 代码结构(每个问题一个py文件)
### 文件命名与位置
```
求解/
├── 问题一/
│ ├── 问题一_<描述>.py
│ ├── 图片/
│ └── 结果/
├── 问题二/
│ ...
```
### 公共头部(每个脚本复制)
```python
import pandas as pd
import numpy as np
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
import os, warnings
warnings.filterwarnings('ignore')
# 中文字体(跨平台)
plt.rcParams['font.sans-serif'] = ['STHeiti', 'SimHei', 'Heiti TC',
'Arial Unicode MS', 'Hiragino Sans GB', 'PingFang SC',
'Microsoft YaHei', 'Songti SC', 'DejaVu Sans']
plt.rcParams['axes.unicode_minus'] = False
plt.rcParams['figure.dpi'] = 150
plt.rcParams['savefig.dpi'] = 150
plt.rcParams['savefig.bbox'] = 'tight'
def despine(ax):
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
FIG_DIR = os.path.join(BASE_DIR, '图片')
OUT_DIR = os.path.join(BASE_DIR, '结果')
os.makedirs(FIG_DIR, exist_ok=True)
os.makedirs(OUT_DIR, exist_ok=True)
def save_fig(fig, name_cn):
fig.savefig(os.path.join(FIG_DIR, name_cn))
plt.close(fig)
def save_csv(df, name_cn):
df.to_csv(os.path.join(OUT_DIR, name_cn), index=False, encoding='utf-8-sig')
```
## 两阶段执行(严格执行)
### 第一阶段:纯计算
```
数据加载 → 预处理 → 建模 → 求解 → 得到所有数值结果
```
**必须打印的统计量**(供论文引用):
```python
def print_stats(data, name):
print(f"\n=== {name} 统计 ===")
print(f"样本数: {len(data)}")
print(f"最小值: {data.min():.4f}")
print(f"最大值: {data.max():.4f}")
print(f"均值: {data.mean():.4f}")
print(f"标准差: {data.std():.4f}")
print(f"变异系数(CV): {data.std()/data.mean():.4f}")
print(f"振幅: {data.max()-data.min():.4f}")
```
### 第二阶段:检查 + 绘图
在确认所有计算结果正确后,再进行画图。
## 各类型问题的建模模板
### 优化类
```python
# 步骤1:目标函数的建立
# 步骤2:约束条件的建立(逐个约束编号)
# 步骤3:核心机理建模(子模型)
# 步骤4:求解算法实现
from scipy.optimize import minimize, differential_evolution
# 或使用遗传算法、粒子群等
```
### 评价类
```python
# 步骤1:评价指标体系构建
# 步骤2:指标权重确定(熵权法/AHP)
# 步骤3:综合评价(TOPSIS/模糊综合评价)
from sklearn.preprocessing import MinMaxScaler
# 熵权法计算权重
def entropy_weight(matrix):
# 归一化
p = matrix / matrix.sum(axis=0)
# 计算熵值
e = -np.sum(p * np.log(p + 1e-10), axis=0) / np.log(len(matrix))
# 计算权重
w = (1 - e) / np.sum(1 - e)
return w
```
### 分类/预测类
```python
# 步骤1:特征工程(相关性分析+降维+特征选择)
# 步骤2:模型构建(完整数学表达式)
# 步骤3:模型训练与评估(交叉验证+指标)From hongdotien10-hash/mathmodel-toolkit, MIT.
More from hongdotien10-hash/mathmodel-toolkit
- 0.479score
systematic-debugging
hongdotien10-hash
Debug experiment code with structured error analysis.
SkillCFreshness: CClaude Code +9 - 0.458score
画图
hongdotien10-hash
使用matplotlib生成论文级质量图表,支持柱状图、折线图、热力图、散点图、饼图、箱线图等
SkillCFreshness: CClaude Code +9 - 0.458score
读取题目
hongdotien10-hash
读取数学建模竞赛的题目文件(PDF/DOCX)和数据文件(xlsx/docx),输出数据总览
SkillCFreshness: CClaude Code +9 - 0.458score
写论文
hongdotien10-hash
根据求解结果自动生成LaTeX论文,包含摘要、引言、模型建立与求解、检验、评价等完整章节
SkillCFreshness: CClaude Code +9 - 0.458score
编译论文
hongdotien10-hash
使用xelatex编译LaTeX论文,自动修复编译错误,执行排版优化
SkillCFreshness: CClaude Code +9 - 0.458score
求解计划
hongdotien10-hash
根据题目和数据生成详细的求解计划,包含思路、方法、输出标准和操作步骤
SkillCFreshness: CClaude Code +9 - 0.458score
数据预处理
hongdotien10-hash
数学建模数据预处理,包含缺失值处理、异常值检测、标准化/归一化、特征工程
SkillCFreshness: CClaude Code +9 - 0.458score
代码检查
hongdotien10-hash
检查数学建模Python求解代码的规范性,包括绘图标准、执行顺序、依赖限制、统计输出
SkillCFreshness: CClaude Code +9 - 0.458score
全自动求解
hongdotien10-hash
数学建模竞赛全自动求解+论文生成,从读取题目到编译PDF一气呵成
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 22, 2026 (3 months 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 hongdotien10-hash
- 0.479score
systematic-debugging
hongdotien10-hash
Debug experiment code with structured error analysis.
SkillCFreshness: CClaude Code +9 - 0.458score
画图
hongdotien10-hash
使用matplotlib生成论文级质量图表,支持柱状图、折线图、热力图、散点图、饼图、箱线图等
SkillCFreshness: CClaude Code +9 - 0.458score
读取题目
hongdotien10-hash
读取数学建模竞赛的题目文件(PDF/DOCX)和数据文件(xlsx/docx),输出数据总览
SkillCFreshness: CClaude Code +9 - 0.458score
写论文
hongdotien10-hash
根据求解结果自动生成LaTeX论文,包含摘要、引言、模型建立与求解、检验、评价等完整章节
SkillCFreshness: CClaude Code +9 - 0.458score
编译论文
hongdotien10-hash
使用xelatex编译LaTeX论文,自动修复编译错误,执行排版优化
SkillCFreshness: CClaude Code +9 - 0.458score
求解计划
hongdotien10-hash
根据题目和数据生成详细的求解计划,包含思路、方法、输出标准和操作步骤
SkillCFreshness: CClaude Code +9
Cite this page
逐题求解 skill. Agent Mart. https://agentmart.dev/skills/hongdotien10-hash-c47812 (last updated 2026-10-24)