# Neural Train

> Train SONA neural patterns from successful task completions, view learned patterns, and optimize the intelligence pipeline

- Skill: `neronain/neural-train` (Agent Skill)
- Install (CLI): `npx skillmds@latest add neronain/neural-train`
- Raw SKILL.md: https://api.skillmd.com/api/skills/neronain/neural-train/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: neronain (https://skillmd.com/u/neronain)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/neronain/neural-train

---


# Neural Training

Train and manage SONA neural patterns for self-learning.

## When to use

After completing a successful task, use this skill to capture what worked and train the intelligence system so future tasks benefit from learned patterns.

## Steps

1. **Check current neural status** — call `mcp__claude-flow__neural_status` to see active patterns and training state
2. **Start a trajectory** — call `mcp__claude-flow__hooks_intelligence_trajectory-start` with the task context
3. **Record steps** — for each significant action, call `mcp__claude-flow__hooks_intelligence_trajectory-step`
4. **End trajectory** — call `mcp__claude-flow__hooks_intelligence_trajectory-end` with outcome (success/failure)
5. **Train patterns** — call `mcp__claude-flow__neural_train` with `--pattern-type coordination --epochs 10`
6. **Store patterns** — call `mcp__claude-flow__hooks_intelligence_pattern-store` to persist learnings
7. **Verify** — call `mcp__claude-flow__neural_patterns` to confirm patterns were stored

## CLI alternative

```bash
npx @claude-flow/cli@latest neural train --pattern-type coordination --epochs 10
npx @claude-flow/cli@latest neural patterns --list
npx @claude-flow/cli@latest neural status
npx @claude-flow/cli@latest hooks pretrain --model-type moe --epochs 10
```

## SONA adaptation

For real-time micro-adaptation (<0.05ms), use:
- `mcp__claude-flow__ruvllm_sona_create` to initialize a SONA instance
- `mcp__claude-flow__ruvllm_sona_adapt` to adapt weights based on feedback