abstraction-extraction
The abstraction-extraction skill identifies transferable principles and mechanisms from specific domain examples by systematically removing domain-specific details. Use this when analyzing concrete cases from different fields to uncover underlying patterns that apply across domains, enabling pattern recognition and cross-domain knowledge transfer. The skill runs as a dedicated subagent to ensure careful layered reasoning from concrete details through functional description to abstract relational structure.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/abstraction-extraction && cp -r /tmp/abstraction-extraction/skills/abstraction-extraction ~/.claude/skills/abstraction-extractionSKILL.md
# Abstraction Extraction Extract abstract principles from concrete domain cases. ## Execution Subagent — spawned via subagent-spawning/spawn-agent skill. ## Why Subagent Abstraction requires careful layered reasoning — moving from concrete details through functional description to pure relational structure. Benefits from dedicated attention to avoid premature abstraction or under-abstraction.
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