abstraction-ladder
The abstraction-ladder skill decomposes concepts across four hierarchical levels, concrete, functional, structural, and abstract, to identify bisociation opportunities where unexpected connections emerge. Use this when exploring innovation potential in existing ideas, seeking novel combinations across different scales of analysis, or breaking down complex problems to uncover creative solutions at multiple organizational depths.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/abstraction-ladder && cp -r /tmp/abstraction-ladder/skills/abstraction-ladder ~/.claude/skills/abstraction-ladderSKILL.md
# Abstraction Ladder Perform bisociation at multiple abstraction levels — decompose a concept into concrete, functional, structural, and abstract levels, identifying collision opportunities at each. ## Execution Subagent — spawned via subagent-spawning/spawn-agent skill. ## Why Subagent Abstraction laddering requires careful level-by-level decomposition and the identification of non-obvious collision opportunities at each level. Benefits from systematic dedicated attention.
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