analogy-extraction

@yogsoth-ai · 收录于 5 天前 · 上游提交 2 周前

Extract transferable structural principles from source domains. Orchestrates source identification → abstraction → structural mapping → transfer validation.

场景创意构思知识迁移问题解决

适合你，如果常需要从其他领域借鉴模式来解决新问题

/ 下载安装

https://github.com/yogsoth-ai/de-anthropocentric-research-engine/tree/main/skills/analogy-extraction ↗

/ 通过 npx 安装 校验哈希

npx oh-my-skill add yogsoth-ai/de-anthropocentric-research-engine/analogy-extraction

/ 通过 bash 安装

curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- yogsoth-ai/de-anthropocentric-research-engine/analogy-extraction

/ 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/analogy-extraction

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

~316上下文体积 · 单文件

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

执行四个阶段的流程：识别候选源领域、提取抽象原理、进行结构映射、验证转换深度，最终输出经过验证的深层类比。

什么时候触发

当用户需要从特定源领域提取可迁移的结构原则，或要求进行类比分析时触发。

装好后可以这样说

Claude会启动源识别和抽象提取。

触发结构映射和验证阶段。

调用类比质量评估。

技能原文 SKILL.md作者撰写 · Apache-2.0 · 59ace64

Analogy Extraction

Extract transferable structural principles from source domains.

Stages

Stage 1: Source Identification

Identify candidate source domains using domain-scanning SOP. Evaluate each for structural similarity depth (surface/structural/systemic).

Stage 2: Abstraction

For each promising source, extract the abstract principle using abstraction-extraction or biological-strategy-extraction SOP. Strip domain-specific details to reveal the transferable mechanism.

Stage 3: Structural Mapping

Map source structure to target domain. Identify: corresponding elements, missing elements (gaps), extra elements (opportunities). Use structural-mapping SOP.

Stage 4: Transfer Validation

Assess mapping quality: Is the analogy surface-level (shared labels) or deep (shared relational structure)? Use analogy-quality-assessment SOP. Only deep analogies warrant transfer.

Minimum Yield

| Metric | Floor | |--------|-------| | Source domains scanned | ≥5 | | Abstractions extracted | ≥3 | | Structural mappings completed | ≥3 | | Validated deep analogies | ≥2 |

Available SOPs

| SOP | Role | |-----|------| | domain-scanning | Stage 1 — find candidate source domains | | web-search | Stage 1 — supplement domain search | | paper-overview | Stage 1 — find academic analogies | | abstraction-extraction | Stage 2 — extract abstract principles | | structural-mapping | Stage 3 — map source→target structure | | analogy-quality-assessment | Stage 4 — validate mapping depth | | novelty-scoring | Post — score resulting ideas | | idea-synthesis | Post — synthesize into coherent concepts |

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

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。

…