‹ 首页

answering-sequence-design

@yogsoth-ai · 收录于 5 天前 · 上游提交 2 周前

SOP: Design the optimal answering order for sub-questions

适合你,如果需要为复杂问题规划子问题的回答顺序

/ 通过 npx 安装 校验哈希
npx oh-my-skill add yogsoth-ai/de-anthropocentric-research-engine/answering-sequence-design
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- yogsoth-ai/de-anthropocentric-research-engine/answering-sequence-design
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify yogsoth-ai/de-anthropocentric-research-engine/answering-sequence-design
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
388GitHub stars
~280最小装载
~280含声明引用
~472文本包总量
索引托管

怎么用

商店整理自技能原文 · 版本 59ace64 · 表述以原文为准
它做什么

Claude会分析你提供的子问题列表和依赖关系,设计出最优的回答顺序:哪些子问题可以同时做,哪些必须按顺序,并优先处理高风险项。

什么时候触发

当你有一组需要回答的子问题,并已梳理出它们之间的依赖关系时,可以请求Claude规划执行顺序。

装好后可以这样说
Claude会基于依赖图输出分阶段计划。
Claude会识别出无依赖关系的子问题。
Claude会调整顺序先解决高不确定性项。
技能原文 SKILL.md作者撰写 · Apache-2.0 · 59ace64

Answering Sequence Design

Design the optimal answering order for sub-questions — based on dependency relationships and resource efficiency.

HARD-GATE

<HARD-GATE> Input must contain: sub-question list + dependency graph (from dependency-mapping). </HARD-GATE>

Pipeline
  1. Precondition check: is the dependency graph acyclic
  2. Topological sort: determine the basic order based on dependency relationships
  3. Parallel grouping: identify sub-questions that can proceed simultaneously
  4. Resource optimization: adjust the order considering resource constraints
  5. Risk ordering: prioritize high-risk/high-uncertainty items (fail fast)
  6. Final sequence: determine the optimal sequence by integrating the above factors
  7. Output: execution sequence + phased plan + parallelization opportunities
Output Format
Phase 1 (parallel): [SQ1, SQ3] — no mutual dependencies
Phase 2 (sequential): [SQ2] — depends on SQ1
Phase 3 (parallel): [SQ4, SQ5] — depend on SQ2
Rationale: [why this order is optimal]
Risk note: [which sub-questions, if they fail, will affect subsequent ones]

</output>

按 Apache-2.0 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。