Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

求解与算法设计（cjms-solution-algorithm） · brycewang-stanford | DecimalAI

documentationby brycewang-stanford

求解与算法设计（cjms-solution-algorithm）

brycewang-stanford/cjms-solution-algorithm

Source brycewang-stanford/awesome-journal-skills ↗License MIT

Use when choosing the solution route and delivering the algorithm section of a 《中国管理科学》 (Chinese Journal of Management Science) manuscript — exact vs heuristic vs learning-based, with pseudocode, property analysis, and baseline comparison. Covers solving the model; the experiments that showcase it belong to cjms-numerical-experiments.

SkillScore91Maintained

Automatic

Research pack

Last verified 9/1/2026

What it changes

Passed 20 of 22 test cases with the skill, and 12 of 22 without it.

Without skill55%

With skill91%

Checks it passed that the model alone missed

Uses the output tag 【路线判定】.
Uses the output tag 【对比设计】.
Uses the mandatory tags 【路线判定】 and 【伪代码】.

and 11 more in the full report

9 fixed11 passed either way1 still failing1 broke

Pass-rate lift: +36 pp
Tokens: +43%
Agent turns: 0%
Response time: -2%

Model gemini-3.6-flashMeasured 9/1/2026v120 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

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-solution-algorithm/SKILL.md https://app.decimal.ai/s/brycewang-stanford-cjms-solution-algorithm/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-cjms-solution-algorithm, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/brycewang-stanford-cjms-solution-algorithm/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-cjms-solution-algorithm

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-cjms-solution-algorithm/SKILL.md https://app.decimal.ai/s/brycewang-stanford-cjms-solution-algorithm/SKILL.md

Raw file: /s/brycewang-stanford-cjms-solution-algorithm/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-cjms-solution-algorithm.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

审稿人质疑我们处理大规模双层车辆路径问题时为何自提遗传算法而非直接使用求解器，并认为对比缺乏说服力。请帮我设计符合管理科学学术标准的算法节规范，明确交代路线判定的考量、给出伪代码结构提纲（包含输入、输出及停止条件）、给出性质分析（如复杂度或收敛性）的要点、设计涵盖消融版与外部基线的方法对比矩阵，并指明下一步数值实验的接续步骤。

What was checked, without and with the skill
Checked	Without skill	With skill
Uses the output tag 【路线判定】.	Missed	Passed
Uses the output tag 【对比设计】.	Missed	Passed
Uses the tag 【下一步】 with cjms-numerical-experiments.	Missed	Passed

case-01 · gemini-3.6-flash · 9/1/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md83 linessingle file

求解与算法设计（cjms-solution-algorithm）

触发时机

模型建好了，只写"用 Gurobi 求解"一句话
自设计算法没有伪代码、没有性质分析、没有对比对象
审稿意见出现"算法创新性不足 / 为什么不用现成求解器"

核心：求解路线决策表

先答一个审稿人必问的问题：**这个模型为什么不能用现成方法直接解？**答案决定路线：

模型情形	求解路线	交付底线
可转化为 LP/MIP/SOCP 且规模可解	商用求解器（Gurobi/CPLEX）	转化过程 + 规模上限实测；算法不是贡献点
有特殊结构（可分解、单调、凸）	精确算法（分支定界、列生成、L-shaped、DP）	结构性质引理 + 收敛/最优性论证
NP-难且实例大	启发式/元启发式（遗传、变邻域、ALNS）	与精确解（小规模）和 ≥1 个已发表算法对比
序贯决策、环境可模拟	近似 DP / 强化学习	状态-动作-奖励设计依据 + 与规则策略对比
闭式可解	解析求解	解的结构性质（单调性、阈值形式）与比较静态

"因为想用某算法所以设计某模型"是倒置——路线必须由模型结构推出。

算法节交付底线（缺一即弱）

伪代码：编号 Algorithm 1，输入/输出/终止条件齐全，与正文记号一致。
性质分析：精确算法给最优性/收敛性；启发式给复杂度与关键算子的设计依据；不做性质分析的算法在本刊只能作为工具而非贡献。
基线对比：至少一个"不改进的自己"（去掉新算子的消融版）+ 一个已发表方法；只跟随机解比是无效对比。
可复述性：参数设置（种群、步长、温度……）全部列表，他人可复现。

改进型算法的命名纪律

对既有元启发式的改进，逐个改动点回答"针对本模型哪个结构、解决什么失效"；凑数式混合（"遗传 + 模拟退火 + 禁忌"三合一）没有结构理由时是减分项。

自检清单

回答了"为什么现成方法不够"，路线与模型结构匹配
伪代码完整、记号一致、可独立复述
性质分析到位（最优性/收敛/复杂度三选其适）
对比含消融版与已发表方法，实例规模覆盖小/中/大
全部算法参数列表化，随机种子与实现环境写明

Track record

Benchmark

20 / 22

test cases passed, vs 12 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

brycewang-stanford / awesome-journal-skills

Chinese-Journal-of-Management-Science-Skills/skills/cjms-solution-algorithm/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

求解与算法设计（cjms-solution-algorithm）

触发时机

核心：求解路线决策表

算法节交付底线（缺一即弱）

改进型算法的命名纪律

自检清单

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills