/trl-fine-tuning
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace
$ npx -y skills add braxtonROSE4/zorro-agent --skill trl-fine-tuning --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/trl-fine-tuning
Context preview
The summary Claude sees to decide when to auto-load this skill.
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace
A self-evolving CLI agent. Most agents treat memory as an afterthought — a flat text file that grows until it's useless.
Other skills on zorro-agent.
- /apple-notes
Manage Apple Notes via the memo CLI on macOS (create, view, search, edit).
Open skill - /apple-reminders
Manage Apple Reminders via remindctl CLI (list, add, complete, delete).
Open skill - /findmy
Track Apple devices and AirTags via FindMy.app on macOS using AppleScript and screen capture.
Open skill - /imessage
Send and receive iMessages/SMS via the imsg CLI on macOS.
Open skill - /claude-code
Delegate coding tasks to Claude Code (Anthropic's CLI agent). Use for building features, refactoring, PR reviews, and iterative coding. Requires the claude CLI installed.
Open skill - /codex
Delegate coding tasks to OpenAI Codex CLI agent. Use for building features, refactoring, PR reviews, and batch issue fixing. Requires the codex CLI and a git repository.
Open skill