ask-decomposition-validation
This Claude Code skill presents a decomposed goal tree to users for structured validation, asking three sequential questions about decomposition reasonableness, missing elements, and priority ordering among sub-goals. Use it after goal decomposition to ensure the breakdown captures all necessary components, aligns with user intent, and reflects actual priorities before proceeding to execution planning.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/ask-decomposition-validation && cp -r /tmp/ask-decomposition-validation/skills/ask-decomposition-validation ~/.claude/skills/ask-decomposition-validationSKILL.md
# Ask Decomposition Validation Get user confirmation of the goal decomposition. ## Execution Dialogue — inline, no subagent. ## What to Present - GoalTree (simplified visual) - Validation results (from validate-leaves) - Feasibility assessment (from feasibility-check) ## What to Ask (one at a time) - Does this decomposition look reasonable to you? - Is there anything missing — a sub-goal I haven't captured? - Among these sub-goals, what's your priority order? What would you tackle first? ## Output User-confirmed GoalTree + priority ordering.
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