yogsoth-ai/de-anthropocentric-research-engine

represent-mechanism-edge

Represent a directed mechanism edge with pathway, sign/direction, assumptions, falsifier, strength, and evidence provenance.

查看源码

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 represent-mechanism-edge

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。

represent-mechanism-edge

Purpose

Represent a directed mechanism edge with pathway, sign, assumptions, falsifier, strength, and evidence provenance.

Input contract

yaml

required: [source_entity, target_entity, mechanism_pathway, direction, evidence_register]
optional: [edge_type, strength_scale, assumptions, falsifier]
constraints: [source and target are typed; direction, pathway, evidence, and falsifier are explicit]

Procedure

Type the source and target entities and select the relation/edge type.
State the mechanism pathway and direction, including enabling conditions and assumptions.
Attach supporting and contradicting evidence, assign strength on the declared scale, and define a falsifier.
Emit the edge record with provenance and unresolved mechanism questions.

If a mechanism edge is typed but its support and contradiction records are not linked, consider attach-evidence-to-relation as the next tactic.

Output contract

yaml

produces: [mechanism_edge, evidence_links, assumption_list, falsifier, unresolved_questions]
delta_fields: [findings, evidence_updates, hypothesis_updates, assumption_updates, uncertainties, open_questions]

Quality gates

Every edge states HOW the source can affect the target, not only that they co-occur.
Strength is bounded by the evidence and includes both supporting and contradicting records when available.