ablation-execution
The ablation-execution skill systematically removes individual components from a system and documents the resulting changes or impacts. Use this technique when diagnosing system dependencies, identifying critical components, understanding feature importance, or evaluating which elements contribute meaningfully to overall system performance or behavior.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/ablation-execution && cp -r /tmp/ablation-execution/skills/ablation-execution ~/.claude/skills/ablation-executionSKILL.md
# Ablation Execution Systematically remove components from a system one by one and record the resulting changes. ## Execution Subagent — spawned via subagent-spawning/spawn-agent skill. ## Why Subagent Ablation requires careful, systematic removal of each component while tracking cascading effects. Benefits from dedicated context to maintain the full system model during iterative removal.
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