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 Numerical Experiments

ASecurity

Use when designing the numerical / simulation study for a 《管理科学学报》 (Journal of Management Sciences in China) manuscript — validating the proven theoretical properties, testing algorithm performance, exploring parameter sensitivity, and extracting managerial insight. The study must serve the theory, not replace it. Use after jmsc-proofs and jmsc-algorithm.

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

Security Analysis

A100/100

Scanned 6/5/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Jmsc Numerical Experiments?

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

Security grade badge for Jmsc Numerical Experiments
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-jmsc-numerical-experiments/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-jmsc-numerical-experiments)

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

Download with Pro
Files
SKILL.md
---
name: jmsc-numerical-experiments
description: Use when designing the numerical / simulation study for a 《管理科学学报》 (Journal of Management Sciences in China) manuscript — validating the proven theoretical properties, testing algorithm performance, exploring parameter sensitivity, and extracting managerial insight. The study must serve the theory, not replace it. Use after jmsc-proofs and jmsc-algorithm.
---

# 数值实验与仿真(jmsc-numerical-experiments)

## 触发时机

- 命题/算法已就位,要设计数值研究来验证
- 实验单薄(一组参数、一张图),说不出洞见
- 审稿质疑"实验没验证理论 / 没管理含义 / 参数随意"
- 想用仿真"代替证明"(方向反了)

## 核心:数值实验是验证 + 洞见,不是证明

本刊的数值实验有**两个任务**:(1) **验证**已证明的理论性质与算法表现;(2) **挖掘洞见**——在什么条件下结论/算法更优,回答"模型告诉我们什么决策规律"。它不替代证明,但能补足证明给不出的定量感。

## 实验设计三问

1. **验证什么**:哪条命题/哪个收敛速率/哪个近似比,要被这组实验照亮?
2. **比什么基准**:与精确解、下界、现有方法、退化策略比,gap 怎么报?
3. **扫什么参数**:哪些参数驱动核心机制?敏感性分析要覆盖其合理范围。

## 实验内容清单

| 目的 | 内容 |
|------|------|
| 验证理论 | 复现命题断言的单调/阈值结构;最优性/唯一性的数值佐证 |
| 算法性能 | 求解时间随规模增长曲线;收敛迭代数;与精确/下界的 gap |
| 敏感性 | 关键参数对最优决策/最优值的影响(趋势 + 拐点) |
| 鲁棒性 | 分布/参数误设下结论是否稳健 |
| 管理洞见 | 从趋势里提炼决策规律(→ jmsc-managerial-insights) |

## 严谨性要点

- 参数设定**有依据**(文献/现实标度),写清取值与来源;不要"随手取"。
- 随机算例要给**重复次数与统计量**(均值、标准差/置信区间),不要单次结果。
- 图表要能让读者"看出"理论性质(如阈值、单调),而不只是堆数。
- 报告**算例规模范围**,说明算法的可扩展边界。

## 自检清单

- [ ] 每组实验对应一条要验证的理论性质或算法指标
- [ ] 有合理基准(精确解/下界/现有方法/退化策略)并报 gap
- [ ] 参数取值有依据、范围合理,敏感性覆盖核心参数
- [ ] 随机实验有重复 + 统计量,不是单点
- [ ] 图表直接支撑命题(看得出单调/阈值/收敛)
- [ ] 从实验提炼出可陈述的管理洞见,而非"结果如图"

## 反模式

- 用仿真"证明"本应解析证明的性质
- 只跑一组参数、一张图,没有敏感性与基准
- 元启发式只报"我比谁好",不与界/最优比
- 实验结论是"验证了模型的有效性"这类空话,没有具体决策规律

## 输出格式

```
【验证目标】<命题/速率/近似比>
【基准】精确 / 下界 / 现有方法 / 退化(gap=…)
【参数】<取值 + 来源依据>;敏感性覆盖<参数>
【随机性】重复 N 次,报<均值/SD/CI>
【图表-命题对应】看得出<单调/阈值/收敛>?是/否
【洞见雏形】<一句话决策规律>
【下一步】jmsc-managerial-insights
```

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 →