Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Jmsc Model Building

ASecurity

Use when building the formal model for a 《管理科学学报》 (Journal of Management Sciences in China) manuscript — making decision variables, parameters, constraints, objective function, and assumptions all explicit, and justifying each assumption against the modeling goal. Use after jmsc-problem-formulation and before jmsc-proofs.

1,052 stars
0 votes
0 copies
1 views
Added 6/5/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 6/5/2026

Install to Claude Code

$npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill jmsc-model-building --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Jmsc Model Building?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Jmsc Model Building
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-jmsc-model-building/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-jmsc-model-building)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: jmsc-model-building
description: Use when building the formal model for a 《管理科学学报》 (Journal of Management Sciences in China) manuscript — making decision variables, parameters, constraints, objective function, and assumptions all explicit, and justifying each assumption against the modeling goal. Use after jmsc-problem-formulation and before jmsc-proofs.
---

# 模型构建(jmsc-model-building)

## 触发时机

- 决策问题清楚了,要写出正式模型
- 审稿质疑"假设不合理 / 模型设定不完整"
- 模型有变量但约束或目标缺项
- 假设一堆,但说不清每条为什么需要

## 核心:模型设定必须完整且可辩护

本刊的模型设定要做到**完整(complete)+ 可辩护(defensible)**。完整指四要素无缺;可辩护指每条假设都有"为什么这样设"的理由,且与建模目标一致。

## 模型四要素(缺一不可)

1. **决策变量与参数**:列清符号、定义域、量纲;变量与参数分开声明。
2. **约束**:容量/预算/非负/可行性/激励相容(IC)/参与(IR)等,写成显式不等式或等式。
3. **目标函数**:期望利润 / 风险调整收益 / 成本 / 社会福利…;明确是 max 还是 min、对谁而言。
4. **假设**:分布假设、凸性/单调性、信息结构、参数取值范围——**每条单独编号**。

## 假设的三类与辩护

| 假设类型 | 例子 | 辩护方式 |
|----------|------|----------|
| 技术性(保证可解) | 凸性、连续、紧致 | 说明放松后会失去什么性质 |
| 实质性(刻画情境) | 风险中性、信息对称 | 对应现实管理情境,给文献支撑 |
| 简化性(聚焦核心) | 两期、两主体、线性需求 | 说明可扩展,且不改变核心机制 |

> 危险信号:实质性假设被当成"显然"不加辩护;或假设强到把结论"假设进来了"。

## 自检清单

- [ ] 决策变量、参数、定义域、量纲齐全且区分清楚
- [ ] 约束写成显式数学表达,可行域非空
- [ ] 目标函数明确(max/min、对谁、是否期望/风险调整)
- [ ] 每条假设单独编号,并说明类型与辩护理由
- [ ] 没有"循环假设"(把要证的结论藏在假设里)
- [ ] 模型与第一步的决策问题五要素一一对应
- [ ] 特例/退化情形(如单期、对称)能从模型自然得到

## 反模式

- 目标函数和约束都有,唯独漏掉关键假设(分布/信息)
- 假设强到结论几乎平凡,方法贡献被掏空
- 参数与变量混用,导致后续证明含混
- 模型比问题复杂得多,加了一堆与核心机制无关的装饰

## 输出格式

```
【变量/参数】<符号: 定义, 定义域, 量纲>
【约束】<显式表达,可行域非空?>
【目标】max/min <目标>(对<主体>,期望/风险调整)
【假设】A1<…,类型,辩护> A2<…> …
【循环假设检查】无 / 有 <哪条>
【与问题对应】完整 / 缺 <项>
【下一步】jmsc-proofs
```

Attribution

brycewang-stanfordbrycewang-stanford
View sourceMore from brycewang-stanford →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →