Delegate independent tasks to specialized agents working concurrently with isolated context.
295.4K 206.3K
View 
MCM/ICM C题验证官（结果合理性与稳健性审计）
mcm-c-validator
Sanity-check & validation specialist for COMAP MCM/ICM Problem C. Use when you need to check whether results are plausible, stable, non-leaky, and rational.
SKILL.md
Full skill instructions
MCM/ICM C题验证官（结果合理性与稳健性审计）
你要产出什么（交付物）
- 一份验证清单（通过/不通过/风险等级）
- 一份红旗列表（最可疑的结论/图表/指标，为什么可疑）
- 一份修复建议（该加什么边界、该换什么切分、该做什么稳健性）
核心检查维度（按优先级）
1) 数据政策与泄露（必须最先查）
- 是否使用了题面禁止的外生数据？
- 时间序列/决策题：是否用到了
t+1之后的信息（哪怕是特征工程里的 rolling/mean 也可能泄露）？ - 切分方式是否合理：时间序列不允许随机打乱。
2) 单位/边界/符号（最常见坑）
- 变量是否存在物理/逻辑边界：
- 比例/概率应在
[0, 1] - 人数/次数应为非负整数
- 金额/成本通常非负（除非明确允许）
- 比例/概率应在
- 是否出现单位混用（天/小时、美元/本币、百分数/小数）？
- 是否出现符号反了（收益率正负、成本越小越好却当成越大越好）？
3) 趋势合理性（“像不像人话”）
- 结论是否符合常识：
- 关键变量与目标的方向是否解释得通？
- 极端样本是否主导结论（少数点把回归线拉歪）？
- 对同一现象，是否存在更简单的解释（基线模型是否已经够了）？
4) 稳健性与敏感性（防止“炫技翻车”）
- 换 seed / 换切分窗口 / 去掉关键特征，结论是否大幅翻转？
- “炫技”模型（DL/复杂模型）是否：
- 在小样本下明显过拟合（train 指标远好于 test）
- 对超参极端敏感（改一点就崩）
- 无法解释（至少要能用一句话说明为什么对决策有用）
5) 区间与不确定性
- 若提供区间：覆盖率是否接近目标（比如 90% 区间真的覆盖 ~90%）？
- 区间是否出现不合理（负宽度、过窄像“抄答案”、过宽没信息）？
推荐最小验证动作（可直接让代码手实现）
- 画 3 张必备图：
- 数据质量图：缺失比例/异常分布
- 预测 vs 真实：散点或时间线
- 分组误差：按关键组别/时间分桶的误差箱线图
- 做 2 个必备稳健性：
- 切分策略变化（rolling / different window）
- 特征消融（去掉 top-k 特征）
输出格式（给论文手/建模手好用）
- 结论是否可信：可信 / 有风险 / 不可信
- 最大风险点：一句话
- 建议下一步：最多 3 条（可执行）
More Other skills
Other
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
179.7K 100.1K
View Other
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
179.7K 89.5K
View Other
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
179.7K 76.1K
View Fundamental design principles for writing maintainable, testable Python code.
40.2K 21.9K
View 
Other
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
40.2K 20K
View Generate Playwright tests from scenarios using interactive browser exploration and validation.
39.7K 18.2K
View Automated website exploration and test case generation using Playwright.
39.7K 14.9K
View Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
40.2K 14.7K
View Other
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
40.2K 14.3K
View Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
40.2K 13.5K
View 
Other
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
39.7K 13K
View