Ali66611/glskill / gl-thesis-variable-selection
gl-thesis-variable-selection
Verified帮助中国高校经管类本科生和硕士生审查普通 AI 给出的变量答案,并把已确定的论文题目转成可执行的变量设计。用于 AI 变量方案纠错、核心解释变量和被解释变量衡量、主口径与替代口径选择、熵值法或主成分分析判断、数据可得性评分、10篇文献控制变量筛选、控制变量矩阵和变量表生成;不用于从零选题、直接下载最终数据、运行回归或为显著性倒推变量。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.6 KB |
| agents/interface.yaml | config | 771 B |
| agents/openai.yaml | config | 341 B |
| assets/控制变量文献矩阵模板.xlsx | binary | 33.7 KB |
| evals/semantic_config.json | config | 3.5 KB |
| evals/trigger_cases.json | config | 2.2 KB |
| manifest.json | config | 475 B |
| references/ai-answer-audit.md | markdown | 3.2 KB |
| references/control-variable-selection.md | markdown | 3.2 KB |
| references/core-variable-measurement.md | markdown | 3.3 KB |
| references/data-feasibility-scoring.md | markdown | 2.8 KB |
| references/output-contract.md | markdown | 2.6 KB |
evals/semantic_config.json
View on GitHub{
"optimizer_hints": {
"capability": "确定并核验经管论文变量、数据可得性和控制变量",
"inputs": [
"论文题目",
"实证文献",
"变量定义",
"数据来源"
],
"trigger_actions": [
"确定变量衡量方式",
"筛选控制变量",
"生成控制变量矩阵",
"评估数据可得性",
"判断综合指数方法"
],
"exclusions": [
"从零选题",
"直接跑回归",
"只下载数据",
"问卷量表",
"论文润色"
]
},
"fallback_positive_concepts": [
"variable_measurement",
"control_selection",
"data_feasibility",
"composite_method"
],
"positive_concepts": {
"variable_measurement": {
"weight": 0.5,
"phrases": [
"变量怎么衡量",
"变量衡量方式",
"核心解释变量和被解释变量衡量",
"核心变量口径",
"被解释变量和核心解释变量",
"主衡量方式",
"替代衡量方式",
"确定被解释变量",
"确定核心解释变量",
"变量定义表",
"审查ai变量方案",
"普通ai给出的变量答案",
"gemini给我的变量答案",
"变量答案能不能直接用"
]
},
"control_selection": {
"weight": 0.5,
"phrases": [
"筛选控制变量",
"控制变量矩阵",
"控制变量名称",
"每列一篇文献",
"10篇文献控制变量",
"size和lev",
"size 和 lev",
"必须控制",
"控制变量频次"
]
},
"data_feasibility": {
"weight": 0.5,
"phrases": [
"数据可得性评分",
"数据可得性",
"变量数据来源",
"是否需要换指标",
"数据能不能拿到",
"数据闸门"
]
},
"composite_method": {
"weight": 0.5,
"phrases": [
"熵值法还是主成分分析",
"熵值法",
"主成分分析法",
"单指标",
"综合指数",
"变量合成"
]
}
},
"negative_concepts": {
"topic_selection": {
"weight": 0.6,
"exclusive": true,
"phrases": [
"从零想题目",
"想十个毕业论文题目",
"帮我选题",
"寻找研究方向"
]
},
"regression_execution": {
"weight": 0.6,
"exclusive": true,
"phrases": [
"跑基准回归",
"稳健性检验",
"用stata跑",
"直接运行回归"
]
},
"data_download_only": {
"weight": 0.6,
"exclusive": true,
"phrases": [
"登录国泰安",
"下载全部数据",
"只给我数据源清单",
"一般从哪里下载"
]
},
"questionnaire": {
"weight": 0.6,
"exclusive": true,
"phrases": [
"李克特量表",
"信效度分析",
"问卷设计"
]
},
"writing": {
"weight": 0.6,
"exclusive": true,
"phrases": [
"润色论文",
"降低ai味",
"实证结果文字"
]
},
"literature_only": {
"weight": 0.6,
"exclusive": true,
"phrases": [
"暂时不做变量提取",
"只搜索文献"
]
},
"full_research_design": {
"weight": 0.6,
"exclusive": true,
"phrases": [
"设计完整研究方案",
"包括理论假设、识别策略"
]
}
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |