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 build-failure-chain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。
build-failure-chain
Purpose
Build cause -> failure mode -> effect chains and identify cascades and shared roots.
Input contract
yaml
required: [functions_or_process, failure_modes, observed_effects]
optional: [causal_evidence, dependency_graph]
constraints: [each edge needs a mechanism or evidence note]Procedure
- Place causes, failure modes, and effects in typed levels.
- Connect edges and record mechanism/evidence.
- Mark cascades, shared roots, and unresolved links.
Output contract
yaml
produces: [failure_chain, cascade_map, shared_root_report]
delta_fields: [findings, evidence_updates, uncertainties, decisions]Quality gates
- Every effect has a traceable upstream path or is marked unexplained.
- Cycles and unsupported edges are flagged.
Failure and counterexamples
Do not collapse correlation into a causal chain without an evidence or mechanism note.
Provenance map
- resolved: failure-chain-construction
- resolved: failure-clustering
