assumption-challenging
The assumption-challenging skill systematically examines the validity of underlying assumptions through structured questioning, classifying them as well-founded, fragile, or likely false. Use this skill when analyzing arguments, strategies, or research findings across multiple frameworks to identify weak foundational premises that may undermine conclusions or limit solution discovery.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/assumption-challenging && cp -r /tmp/assumption-challenging/skills/assumption-challenging ~/.claude/skills/assumption-challengingSKILL.md
# SOP: Assumption Challenging Challenge each assumption's validity using systematic questioning. Determine which assumptions are well-founded, which are fragile, and which are likely false. Subagent — spawned via subagent-spawning/spawn-agent skill. Shared: This SOP is used across multiple strategies (assumption-constraint, conflict-resolution, constraint-breaking) and campaigns.
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