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 decompose-and-or-goal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。
decompose-and-or-goal
Purpose
Recursively decompose a goal into an AND/OR DAG whose leaves are executable or testable subgoals.
Input contract
yaml
required: [top_goal, constraints]
optional: [actor_profile, obstacle_report, existing_subgoals]
constraints: [branch semantics, dependencies, and leaf criteria must be explicit]Procedure
- Split the goal into necessary AND conditions and alternative OR paths.
- Recurse until each leaf has an observable result or executable action.
- Attach actors, dependencies, constraints, and unresolved feasibility to each branch.
- Preserve shared subgoals as DAG nodes rather than duplicating them.
If the AND/OR decomposition is complete enough to test necessity and coverage, consider validate-goal-tree as the next tactic.
Output contract
yaml
produces: [goal_dag, branch_semantics, executable_leaves, dependency_edges, feasibility_questions]
delta_fields: [findings, hypothesis_updates, uncertainties, open_questions]Quality gates
- Every leaf traces to the top goal.
- AND/OR labels and dependency directions are unambiguous.
- Cycles and duplicate shared nodes are flagged.
Failure and counterexamples
Do not split prose into labels without changing testability, and do not treat alternatives as simultaneous requirements.
Provenance map
resolved: north-star-crystallization-and-or-decompose
