analogy-quality-assessment
The analogy-quality-assessment skill evaluates analogies across three depth levels (surface, structural, systemic) to determine whether they merit further development and knowledge transfer. Use this skill when comparing conceptual relationships across domains to objectively classify analogy quality and decide whether to invest cognitive resources in exploring or applying the analogy further.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/analogy-quality-assessment && cp -r /tmp/analogy-quality-assessment/skills/analogy-quality-assessment ~/.claude/skills/analogy-quality-assessmentSKILL.md
# Analogy Quality Assessment Assess analogy depth (surface/structural/systemic). ## Execution Subagent — spawned via subagent-spawning/spawn-agent skill. ## Why Subagent Quality assessment requires rigorous, unbiased evaluation of analogy depth. Benefits from a dedicated evaluator role that is not invested in the analogy's success and can apply strict classification criteria without creative bias. <!-- BEGIN available-tables (generated) --> ## Available SOPs Optional, no fixed order; the final leaf is always a sop. | SOP | When to use | | --- | --- | | spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. | <!-- END available-tables (generated) -->
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: Inference to the best explanation in the face of anomalies
Remove components one by one, observe system changes to reveal hidden
Map system architecture to ablatable units for ablation studies
Design ablation studies to isolate component contributions in ML systems