alternative-scoring
Alternative Scoring evaluates multiple candidate options against defined criteria to generate a comprehensive scoring matrix. Use this skill when comparing alternatives in decision-making processes that require systematic evaluation, such as vendor selection, design option assessment, or resource allocation. The subagent independently scores each alternative across all criteria with supporting rationales, ensuring consistency and preventing evaluation bias.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/alternative-scoring && cp -r /tmp/alternative-scoring/skills/alternative-scoring ~/.claude/skills/alternative-scoringSKILL.md
# Alternative Scoring Score candidate alternatives against each criterion to produce a complete scoring matrix (alternatives x criteria). ## Execution Subagent receives candidate list, criteria definitions, and weight vector, scores each alternative on each criterion, and outputs the scoring matrix. ## Why Subagent Scoring requires analyzing each alternative individually, involves significant workload and needs consistent scoring standards; independent execution prevents score drift. ## HARD-GATE Scoring matrix must have no empty values, each score must include a brief rationale (1 sentence), and quantitative criteria must use actual data.
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