constraint-tree-building
$
npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/constraint-tree-buildingBuilds constraint trees from UDEs to identify root causes and conflicts
- Analyzes system underperformance by mapping undesirable effects to root causes
- Uses undesirable-effect-listing, causal-chain-tracing, and core-conflict-extraction
- Iterates until all UDEs connect to root causes expressed as constraints or conflicts
- Delivers a structured Current Reality Tree with prioritized root causes
SKILL.md
.github/skills/constraint-tree-buildingView on GitHub ↗
--- name: constraint-tree-building description: "Build Current Reality Tree from UDEs through causal chains to core conflicts" version: 1.0.0 category: experiment-execution type: tactic used-by: constraint-analysis orchestrates: - undesirable-effect-listing - causal-chain-tracing - core-conflict-extraction --- # Tactic: Constraint Tree Building ## Orchestration Pattern 1. **List UDEs** → spawn `undesirable-effect-listing` - Collect all observable symptoms of system underperformance - Ensure each UDE is specific, observable, and evidenced - Minimum 5 UDEs for a meaningful tree 2. **Trace Causal Chains** → spawn `causal-chain-tracing` - Input: UDE list from step 1 - For each UDE, trace backward: IF [cause] THEN [effect] BECAUSE [assumption] - Connect UDEs that share common causes - Identify convergence points (multiple chains meeting at one cause) 3. **Extract Core Conflict** → spawn `core-conflict-extraction` - Input: convergence points from step 2 - If root cause is a dilemma, express as Evaporating Cloud - If root cause is a single constraint, express as binding constraint statement ## Decision Criteria - **When to iterate**: If the tree has disconnected components (UDEs not linked to any chain), return to step 2 with those UDEs - **When to stop**: All UDEs connect to at most 3 root causes, and root causes are expressed as constraints or conflicts - **When to escalate**: If >10 UDEs found, prioritize top-5 by severity before tracing - **Quality gate**: Every causal link must have a BECAUSE clause (the underlying assumption)
More from yogsoth-ai/de-anthropocentric-research-engine
- abductive-hypothesis-generationStrategy: 面对异常的最佳解释推理
- ablation-brainstormRemove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.
- ablation-component-mappingMap system architecture to ablatable units for ablation studies
- ablation-designDesign ablation studies to isolate component contributions in ML systems
- ablation-executionRemove components one by one from a system, record the response/impact of each removal.
- abp-vulnerability-classificationClassify assumptions on 2 axes — load-bearing (how much conclusion depends on it) × vulnerable (how likely to be false). Focuses attention on High-Load × High-Vulnerable quadrant.
- abstraction-extractionExtract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms.
- abstraction-ladderPerform bisociation at multiple abstraction levels
- abstraction-ladderingMove between concrete and abstract framings — 3 levels up (Why?) and 3 levels down (How?) to find the most productive research level.
- abstraction-to-designAbstract biological principle to design principle. Bridge from biology to engineering.