and-or-decompose
The and-or-decompose skill recursively breaks down a top-level goal into a directed acyclic graph (GoalTree) using KAOS-style decomposition. AND nodes represent sub-goals that must all be achieved, while OR nodes indicate alternative paths where completing any one suffices. It accepts a confirmed goal, actor profile, and obstacle report as input, spawning a subagent to generate actionable leaf-node sub-goals suitable for further planning and execution.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/and-or-decompose && cp -r /tmp/and-or-decompose/skills/and-or-decompose ~/.claude/skills/and-or-decomposeSKILL.md
# AND/OR Decompose Recursively decompose the top goal into a structured GoalTree. ## Execution Subagent — spawned via `subagent-spawning/spawn-agent` skill. ## Input - Confirmed top goal - ActorProfile - ObstacleReport ## Output GoalTree — DAG with AND/OR nodes, leaf nodes representing actionable sub-goals.
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