round-decision
$
npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/round-decisionDecide whether to continue or stop Delphi rounds based on consensus metrics
- Determines if another iteration is needed using consensus score, round number, and stability
- Takes structured inputs from the structured-consensus process
- Evaluates stopping criteria and generates a rationale for the decision
- Returns a clear JSON decision object with next steps for orchestration
SKILL.md
.github/skills/round-decisionView on GitHub ↗
--- name: round-decision description: Decide whether to continue iterating or stop based on consensus score, round number, and stability. execution: subagent prompt: ./prompt.md input: consensus_score, round_n, stability used-by: structured-consensus --- # Round Decision Decide whether to run another Delphi round or stop the iteration. Uses consensus score, current round number, and stability (whether scores changed from prior round) to make the continue/stop decision. ## Execution Spawn a subagent that evaluates the stopping criteria and returns a clear continue/stop decision with rationale. ## Why Subagent - Decision logic is a pure function of three inputs - Rationale documentation is important for audit trail - Keeps orchestration logic clean ## HARD-GATE Output MUST contain: `decision` (continue/stop), `reason` (string), and `next_action` (what to do next). Decision must be exactly one of "continue" or "stop".
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.