npx skills add smithery/ruvnet --skill neural-training
ruvnet/ruflo
neural-training
Neural pattern training with SONA (Self-Optimizing Neural Architecture), MoE (Mixture of Experts), and EWC++ for knowledge consolidation. Use when: pattern learning, model optimization, knowledge transfer, adaptive routing. Skip when: simple tasks, no learning required, one-off operations.
Installation
npx skills add ruvnet/ruflo --skill neural-training
Similar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Guide for selecting and configuring distributed training strategies in NeMo AutoModel, includin…
1.9K installsRun Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation t…
1.8K installsPractical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel appr…
1.8K installsProduce a professional training/workshop report as a .docx file. Use this skill whenever the us…
2K installsTrain reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiab…
1.3K installsConvert evaluation traces and production logs into SFT examples and preference pairs. Use when …
1.3K installsAlso in this package
Other skills from ruvnet/ruflo · top by installs.
npx skills add ruvnet/ruflo
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Also listed on
Alternate registries and mirrors of this skill.
Repository health
main
Package contents
Files included with this skill beyond the listing page.
-
skill md
SKILL.md1,735 B -
docs
SUMMARY.md313 B
History
- First seen on skills.sh
- First recorded snapshot · 1,139 installs
SKILL.md
Neural Training Skill
Purpose
Train and optimize neural patterns using SONA, MoE, and EWC++ systems.
When to Trigger
- Training new patterns
- Optimizing agent routing
- Knowledge consolidation
- Pattern recognition tasks
Intelligence Pipeline
- RETRIEVE — Fetch relevant patterns via HNSW (150x-12,500x faster)
- JUDGE — Evaluate with verdicts (success$failure)
- DISTILL — Extract key learnings via LoRA
- CONSOLIDATE — Prevent catastrophic forgetting via EWC++
Components
| Component | Purpose | Performance |
|---|---|---|
| SONA | Self-optimizing adaptation | <0.05ms |
| MoE | Expert routing | 8 experts |
| HNSW | Pattern search | 150x-12,500x |
| EWC++ | Prevent forgetting | Continuous |
| Flash Attention | Speed | 2.49x-7.47x |
Commands
Train Patterns
npx claude-flow neural train --model-type moe --epochs 10
Check Status
npx claude-flow neural status
View Patterns
npx claude-flow neural patterns --type all
Predict
npx claude-flow neural predict --input "task description"
Optimize
npx claude-flow neural optimize --target latency
Best Practices
- Use pretrain hook for batch learning
- Store successful patterns after completion
- Consolidate regularly to prevent forgetting
- Route based on task complexity