answering-sequence-design
The answering-sequence-design skill optimizes the execution order of sub-questions by analyzing dependencies, identifying parallelizable tasks, and prioritizing high-risk items for early resolution. Use this when decomposing complex research questions into sub-problems and needing to determine the most efficient sequence that respects constraints while minimizing wasted effort from dependency failures.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/answering-sequence-design && cp -r /tmp/answering-sequence-design/skills/answering-sequence-design ~/.claude/skills/answering-sequence-designSKILL.md
# Answering Sequence Design Design the optimal answering order for sub-questions — based on dependency relationships and resource efficiency. ## HARD-GATE <HARD-GATE> Input must contain: sub-question list + dependency graph (from dependency-mapping). </HARD-GATE> ## Pipeline 1. **Precondition check**: is the dependency graph acyclic 2. **Topological sort**: determine the basic order based on dependency relationships 3. **Parallel grouping**: identify sub-questions that can proceed simultaneously 4. **Resource optimization**: adjust the order considering resource constraints 5. **Risk ordering**: prioritize high-risk/high-uncertainty items (fail fast) 6. **Final sequence**: determine the optimal sequence by integrating the above factors 7. **Output**: execution sequence + phased plan + parallelization opportunities ## Output Format ``` Phase 1 (parallel): [SQ1, SQ3] — no mutual dependencies Phase 2 (sequential): [SQ2] — depends on SQ1 Phase 3 (parallel): [SQ4, SQ5] — depend on SQ2 Rationale: [why this order is optimal] Risk note: [which sub-questions, if they fail, will affect subsequent ones] ``` </output>
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