← Browse
train-recipe
misobalogh ★ 0
This Agent Skill guides users through Andrej Karpathy's ML training recipe, enforcing a six-stage process (data understanding → skeleton → overfit → regularize → tune → optimize) with gate-verified measurements before each progression. It supports both deep learning and tabular ML, maintains an experiment log, and works across multiple agents (Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, Windsurf) in the open Agent Skills format.
Install
> /plugin marketplace add misobalogh/train-recipe
> /plugin install train-recipe
What it's made of
1 skill
- Commands
- 0
- Agents
- 0
- Skills
- 1
- MCP servers
- 0
- Hooks
- 0
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
- none
- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (misobalogh).