seed-protocol-design

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

Designs reproducible random seed strategies for experiments

  • Solves the problem of ensuring reproducibility in experiments with random components
  • Relies on system architecture analysis and randomness source identification
  • Uses experiment design and repetition requirements to allocate seeds systematically
  • Returns a seed allocation table and reproducibility plan for execution

SKILL.md

.github/skills/seed-protocol-designView on GitHub ↗
---
name: seed-protocol-design
description: "SOP: design random seed strategy for reproducibility"
version: 1.0.0
category: experiment-execution
type: sop
execution: subagent
prompt: ./prompt.md
used-by:
  - reproducibility-protocol
input: "Experiment design + list of randomness sources + repetition requirements"
output: "Seed allocation strategy + seed value table + reproducibility guarantee plan"
---

# SOP: Seed Protocol Design

Design random seed strategy to ensure experiment reproducibility while quantifying variance from randomness through multi-seed runs.

## Execution

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

## Why Subagent

Seed strategy requires identifying all randomness sources in the system (initialization, data sampling, dropout, etc.) and designing a consistent seed propagation scheme — demands deep understanding of system architecture.

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.