design-synthesis

$npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/design-synthesis

Synthesizes complete experiment design report with feasibility and risk assessment

  • Aggregates upstream design outputs into a unified experiment plan
  • Relies on subagent-spawning and upstream SOP results for input
  • Analyzes consistency, completeness, and practical constraints of the design
  • Generates final report with feasibility assessment and risk inventory

SKILL.md

.github/skills/design-synthesisView on GitHub ↗
---
name: design-synthesis
description: "SOP: synthesize complete experiment design report"
version: 1.0.0
category: experiment-execution
type: sop
execution: subagent
prompt: ./prompt.md
used-by:
  - experiment-design
input: "All upstream SOP outputs (variables, levels, matrix, metrics, sample size, seeds, environment, config)"
output: "Complete experiment design report + feasibility assessment + risk inventory"
---

# SOP: Design Synthesis

Synthesize all upstream design SOP outputs into a complete experiment design report, perform consistency checks, assess feasibility, and identify potential risks.

## Execution

Subagent — spawned via subagent-spawning/spawn-agent skill.

## Why Subagent

Design synthesis requires a global perspective to review all design decisions for consistency and completeness — serves as the final quality gate of the experiment design phase, requiring independent critical thinking space.

More from yogsoth-ai/de-anthropocentric-research-engine

SkillDescription
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.