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 select-critical-case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。
select-critical-case
Purpose
Select most-likely, least-likely, or otherwise inference-maximizing cases that can decisively support or refute a claim.
Input contract
yaml
required: [claim, case_universe, selection_logic]
optional: [likelihood_model, boundary_conditions]
constraints: [case selection rule and inference purpose must be explicit]Procedure
- Define the eligible case universe and selection objective.
- Rank cases under the declared logic.
- Select and justify the critical case, including excluded cases.
Output contract
yaml
produces: [critical_case, selection_rationale, excluded_cases, inference_role]
delta_fields: [findings, evidence_updates, uncertainties, decisions]Quality gates
- Selected case must be traceable to the stated selection logic.
Failure and counterexamples
Do not call a convenient case critical without comparing it to the declared universe.
Provenance map
- resolved: critical-case-design
- resolved: counterexample-heuristics
