assumption-criticality
The assumption-criticality skill systematically identifies and ranks assumptions in research by their impact on conclusions. It extracts stated assumptions, negates each one individually, re-derives conclusions under those altered conditions, and measures the sensitivity of results to each assumption change. Use this when evaluating research robustness, validating argument strength, or identifying which foundational claims most critically determine outcomes across web and academic sources.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/assumption-criticality && cp -r /tmp/assumption-criticality/skills/assumption-criticality ~/.claude/skills/assumption-criticalitySKILL.md
# Assumption Criticality Rank assumptions by their impact on conclusions. ## Budget | Base SOP | Target | ±10% Range | |----------|--------|------------| | web-search | 30 | 27–33 | | web-research | 10 | 9–11 | | paper-overview | 30 | 27–33 | | paper-search | 20 | 18–22 | | paper-research | 10 | 9–11 | ## State Ledger ``` <HARD-GATE> | SOP | Done | Target | % | |-----|------|--------|---| | web-search | ? | 30 | ? | | web-research | ? | 10 | ? | | paper-overview | ? | 30 | ? | | paper-search | ? | 20 | ? | | paper-research | ? | 10 | ? | Budget Gate: OPEN/CLOSED (>=80% required to exit) </HARD-GATE> ``` ## Available Tactics - assumption-perturbation ## Available SOPs **Import:** web-search, web-research, paper-overview, paper-search, paper-research **Subagent:** assumption-extraction, negation-definition, re-derivation, conclusion-sensitivity-measurement ## Execution Guidance Extract assumptions, define negation for each, re-derive conclusions under negated assumption, measure how much the conclusion changes. Rank by conclusion sensitivity.
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