使用方法
- 复制安装命令，在自己的智能体环境安装前先检查源码包。
- 从原始文档核对所需工具、凭据和支持的宿主。
- 说明输入材料与期望交付物，并对照来源检查输出。
npx skills add https://github.com/yogsoth-ai/de-anthropocentric-research-engine --skill extract-empirical-regularity开始前需了解
- 安装不包含模型订阅、API 额度或访问文件的权限。
- 仓库星数和安装量反映活跃情况，不等于独立质量或安全测试。
仓库原始内容
按源仓库内容呈现，保留标题、案例、代码、表格、链接以及原文引用的演示图片。
extract-empirical-regularity
Purpose
Extract a repeatable empirical pattern from records while preserving conditions, exceptions, and uncertainty.
Input contract
yaml
required: [observations, variable_schema, condition_schema]
optional: [replication_records, measurement_uncertainty]
constraints: [regularity claims require multiple comparable observations or an explicit single-case limitation]Procedure
- Normalize observations, units, and conditions.
- Identify repeated associations, trends, or invariants.
- Test exceptions, alternative explanations, and measurement artifacts.
- State the regularity with scope and uncertainty boundaries.
If the regularity is stable enough to express through measurable factors and outcomes, consider identify-variables as the next tactic.
Output contract
yaml
produces: [regularity_statement, supporting_records, exception_set, scope_conditions]
delta_fields: [findings, evidence_updates, uncertainties, open_questions]Quality gates
- Conditions and exceptions accompany every regularity.
- Correlation is not labeled mechanism without supporting evidence.
Failure and counterexamples
Do not generalize a pattern across changed populations or protocols without a comparability check.
Provenance map
resolved: extract-empirical-regularity
