science by brycewang-stanford
问题刻画与模型构建（cjms-model-formulation） brycewang-stanford/cjms-model-formulation
Use when translating a real management setting into the formal model of a 《中国管理科学》 (Chinese Journal of Management Science) manuscript — situational elements into variables, constraints, objectives and defensible assumptions, across optimization, game, and data-driven model families. Builds the model; solving it belongs to cjms-solution-algorithm.
What it changes View full report → Passed 18 of 22 test cases with the skill, and 11 of 22 without it.
Without skill 50%
With skill 82%
Checks it passed that the model alone missed and 9 more in the full report
9 fixed9 passed either way2 still failing2 broke
Pass-rate lift +32 pp
Tokens +34%
Agent turns 0%
Response time -2% Model gemini-3.6-flashMeasured 8/31/2026 v1 18 of 22 cases passed with skill
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-cjms-model-formulation/SKILL.md https://app.decimal.ai/s/brycewang-stanford-cjms-model-formulation/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-cjms-model-formulation, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/brycewang-stanford-cjms-model-formulation/ and pins it in .decimal/skills.lock
$ decimalai skills add brycewang-stanford-cjms-model-formulationCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-cjms-model-formulation/SKILL.md https://app.decimal.ai/s/brycewang-stanford-cjms-model-formulation/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt 正在准备一篇平台供应链契约设计的投稿，涉及制造商与电商平台的博弈。制造商先决定批发价，平台再决定零售价与促销投入，平台消费者具有损失规避倾向，市场需求受促销和随机扰动影响。请帮我梳理建模节并按如下格式输出：明确对应的模型类别；给出包含情境要素到模型着落的关联映射表（需明确指出新增机制结构）；列出核心变量、约束与目标；对行为要素与不确定性给出参数化表达及理由；列出逐条编号的假设并归类辩护，确认是否存在循环论证；最后指明后续算法求解或经验检验的对接模块。
What was checked, without and with the skill Checked Without skill With skill Includes section tag 【模型族】 Categorizes assumptions into categories 技术性, 实质性, or 简化性 Includes downstream path pointer cjms-solution-algorithm
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 85 lines single file
问题刻画与模型构建（cjms-model-formulation）
触发时机
情境写了两页，模型仍是"直接给公式"，读者接不上
审稿意见出现"假设脱离实际 / 模型与问题脱节"
三类模型（优化、博弈、数据驱动）不知道选哪类刻画
核心：情境要素 → 模型要素的显式映射
本刊是应用建模 刊：模型节的评审重点不是数学花样，而是"情境里的每个关键要素在模型里有没有着落 "。写模型前先列情境-模型映射表：
映射表里"新增结构"一行为空，说明模型退化为教科书模板，回 cjms-topic-selection 重审增量。
三类模型族的刻画要点
优化/调度类 ：变量、约束、目标三件套逐条显式；不确定参数说明用随机规划、鲁棒优化还是分布鲁棒，并给不确定集/分布的构造依据。博弈/契约类 ：写清博弈时序（谁先动）、信息结构（谁知道什么）、均衡概念；行为要素（公平关切、损失规避）给参数化形式与文献支撑。数据驱动/预测类 ：明确"模型"指方法管道——分解、特征、学习器、组合权重各环节写成可复述的公式或流程，改进环节单独标出。
假设纪律
每条假设单独编号（A1、A2…）并归类辩护：技术性（保证可解，说明放松的代价）、实质性（刻画情境，给现实或文献依据）、简化性（聚焦核心，说明可扩展）。检查是否存在 循环假设 ——把想证的结论藏进假设。
自检清单
Track record Benchmark 18 / 22
test cases passed, vs 11 / 22 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported brycewang-stanford / awesome-journal-skills
Chinese-Journal-of-Management-Science-Skills/skills/cjms-model-formulation/SKILL.md
View on GitHub ↗ License MITImported 8/10/2026Version v1