ev-sys

Train Local — AI skill for Claude Code

AI community

You are helping the user train an LLM locally using the evsys-sdk.

How to install Train Local

Installs to ~/.claude/commands/ev-sys-evsys-sdk-train-local.md

Terminal

mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/ev-sys/evsys-sdk/HEAD/.claude/commands/train-local.md -o ~/.claude/commands/ev-sys-evsys-sdk-train-local.md

Restart Claude Code, or start a new session, for it to be picked up.

What Train Local does

You are helping the user train an LLM locally using the evsys-sdk. Follow these steps carefully.

Step 1 — Check dependencies

Run:

python -c "import trl, peft, transformers, torch, datasets; print('OK')"

If it fails, tell the user to install local extras first:

pip install -e ".[local]"

Then stop and wait for them to install before continuing.

Step 2 — Gather training parameters

Ask the user for the following (use sensible defaults if they don't specify):

| Par

Alternatives in AI

Opencodex — Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama… 12.3k ★
Model Config — /model-config — Choose the model you follow 705 ★
LLM Council Skill — A skill to claude code that enables brainstorming with other LLMs (ChatGPT, Gemini) before presenting the impl 416 ★