abp-vulnerability-classification
This Claude Code skill classifies assumptions along two dimensions, load-bearing importance and vulnerability to falsification, to identify which assumptions most critically need testing. It prioritizes assumptions that carry high explanatory weight while being likely to be false, directing analytical effort toward the highest-risk gaps in reasoning.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/abp-vulnerability-classification && cp -r /tmp/abp-vulnerability-classification/skills/abp-vulnerability-classification ~/.claude/skills/abp-vulnerability-classificationSKILL.md
# ABP Vulnerability Classification Classify assumption vulnerability to prioritize testing. ## Execution Subagent — spawned via subagent-spawning/spawn-agent. ## Budget One unit = one vulnerability classification pass.
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