analogical-transfer
The analogical-transfer skill applies Gentner's structure-mapping theory to systematically identify relational correspondences between domains and transfer higher-order constraints from source to target problems. Use this when solving novel problems by discovering distant domains sharing similar abstract relational structures, extracting their deep structural patterns, and adapting those principles to new contexts while filtering for substantive rather than superficial analogies.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/analogical-transfer && cp -r /tmp/analogical-transfer/skills/analogical-transfer ~/.claude/skills/analogical-transferSKILL.md
# Analogical Transfer Systematic structure-mapping from source to target domain following Gentner's structure-mapping theory. Prioritize relational similarity over surface similarity. ## State Ledger | Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 25 | 0 | 0% | | web-research | 10 | 0 | 0% | | paper-overview | 30 | 0 | 0% | | paper-search | 20 | 0 | 0% | | paper-research | 8 | 0 | 0% | ## HARD-GATE Cannot exit strategy until ≥80% of each budget line is consumed OR yield targets are met with justification for remaining budget. ## Available Tactics | Tactic | Role | |--------|------| | analogy-extraction | Core tactic — extract and validate structural analogies | | domain-divergence | Find distant source domains with high structural similarity | | bridge-validation | Validate mapping depth before transfer | ## Available SOPs | SOP | Role | |-----|------| | domain-scanning | Find candidate source domains | | abstraction-extraction | Extract abstract relational structure | | structural-mapping | Map source→target correspondences | | analogy-quality-assessment | Rate analogy depth (surface/structural/systemic) | | transfer-adaptation | Adapt transferred principle to target constraints | | cross-domain-synthesis | Synthesize transfer outputs | ## Execution Guidance 1. **Functionalize target**: Restate target problem in relational terms (not object terms) 2. **Source search**: Use domain-scanning to find domains with similar relational structure 3. **Abstract source**: Extract relational structure from source using abstraction-extraction 4. **Map structure**: Use structural-mapping to align source→target correspondences 5. **Assess depth**: Apply analogy-quality-assessment — only proceed with STRUCTURAL or SYSTEMIC matches 6. **Transfer**: Carry over higher-order relational constraints from source to target 7. **Adapt**: Use transfer-adaptation to fit transferred principles to target constraints 8. **Validate**: Confirm transferred solution respects target domain physics/logic
Experiment-specific - summarize the DARE executor's research design into a clean research_result report, forced to write back into the spec file produced by formated-specs.
Experiment-specific - replaces writing-specs, emits DARE's 4-layer call plan as a clean research_graph schema. Last step forces load formated-result.
loss-1 judge - read a sample's full dialogue and decide whether the user simulator semantically enacted its Policy Card. check-blind.
loss-2 judge - pairwise quality comparison across the n rungs within one topic; decide monotonicity and endpoint separation. check-blind, D1-D5 only.
Strategy: 面对异常的最佳解释推理
Remove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.
Map system architecture to ablatable units for ablation studies
Design ablation studies to isolate component contributions in ML systems