Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/cjms-managerial-insights
Use when writing the managerial insights and countermeasure suggestions of a 《中国管理科学》 (Chinese Journal of Management Science) manuscript — turning model and experiment results into condition-decision-effect rules instead of policy slogans. Shapes the payoff section; it does not generate new results.
Passed 13 of 22 test cases with the skill, and 7 of 22 without it.
and 8 more in the full report
7 fixed7 passed either way9 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
My platform antitrust draft contains: '监管部门应进一步完善体制机制，多方协同推进平台反垄断治理。' Please rewrite this policy recommendation to specify observable thresholds, regulatory lever settings, and quantifiable market impact, and record the slogan audit result.
| Checked | Without skill | With skill |
|---|---|---|
| Response eliminates slogan text from policy recommendations. | Passed | Passed |
| Response outputs section tag 【口号检查】. | Missed | Passed |
The instructions your model reads when the skill loads.
本刊自华罗庚创刊起的立身之本是"方法要用到管理实践中去"。管理启示是审稿硬指标，标准只有一条：每条启示都能指认支撑它的命题、实验或实证结果。指认不出来源的句子删掉。
当 <可观测条件，来自参数区域或市场状态>，
决策者应 <可执行动作，对应决策变量的取值方向>，
可望 <量级或方向性效果，来自实验/实证数字>。
示例（供应链契约类，形态示范）："当零售商公平关切系数高于阈值（对应实验中的逆转区域）时，制造商应放弃单一批发价合同、改用收益共享，仿真显示渠道效率损失可收窄——效果量以本文算例为准。"
同一结果对不同主体含义不同，分行写：
| 对象 | 启示落点 |
|---|---|
| 企业决策者 | 决策变量怎么调、何时调（阈值、优先序） |
| 平台/链主 | 机制与规则设计（契约菜单、定价规则） |
| 监管/政策方 | 参数校准型建议（限额、费率、补贴的区间依据） |
政策建议只允许"参数校准型"——给出方向与依据区间；"完善顶层设计"式空话在本刊是负分。
启示节必须带适用条件：模型假设不成立（如需求分布突变、主体非风险中性）时哪些结论失效。报告边界不削弱贡献，掩盖边界会在外审被反问。
test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.