# Evidence Network Construction

> Build evidence network graph for network meta-analysis — nodes, edges, geometry assessment

- Skill: `yogsoth-ai/evidence-network-construction` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add yogsoth-ai/evidence-network-construction`
- Raw SKILL.md: https://api.skillmd.com/api/skills/yogsoth-ai/evidence-network-construction/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: yogsoth-ai (https://skillmd.com/u/yogsoth-ai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/yogsoth-ai/evidence-network-construction

---


# Evidence Network Construction SOP

Build and assess the evidence network graph for network meta-analysis, mapping treatment nodes, direct comparison edges, and evaluating network geometry.

## When to Use

- During network-comparison strategy
- When assessing feasibility of network meta-analysis
- When checking network connectivity and transitivity

## Input

- `treatment_comparisons`: All pairwise comparisons available in included studies
- `study_arms`: Study arm-level data (treatments, sample sizes)

## Output

Complete network geometry description with connectivity assessment, comparison matrix, and transitivity evaluation.

<!-- BEGIN available-tables (generated) -->

## Available SOPs

Optional, no fixed order; the final leaf is always a sop.

| SOP | When to use |
| --- | --- |
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |

<!-- END available-tables (generated) -->