EX

extra-rlhf

Manages RLHF pipelines for the ExtraArena environment.

Install

mkdir -p .claude/skills/extra-rlhf && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16539" && unzip -o skill.zip -d .claude/skills/extra-rlhf && rm skill.zip

Installs to .claude/skills/extra-rlhf

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use for anything about the ExtraArena RLHF data-collection & training-orchestration environment (rlhf_env, port 8090, MCP stdio): running semi-synthetic battles, generating training traces, orchestrating the Extra-LR training pipeline, or playing battles as a sub-agent. Routes to three sub-skills — pipeline orchestration, data-generation orchestration, and player.
366 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Advanced

Key capabilities

  • →Orchestrate the full training loop for ExtraArena
  • →Plan and dispatch data-generation series
  • →Monitor and validate datasets
  • →Play one battle as a sub-agent
  • →Register custom models

How it works

This umbrella skill routes user requests to one of three sub-skills (pipeline orchestration, data-generation orchestration, or player) based on the job's scope.

Inputs & outputs

You give it
User request for RLHF pipeline, data generation, or battle play
You get back
Orchestrated training loop, generated dataset, or battle actions

When to use extra-rlhf

  • →Running semi-synthetic battles
  • →Orchestrating training loops
  • →Validating training datasets
  • →Playing as a sub-agent

About extra-rlhf

Automates the collection of training traces and orchestration of the RLHF training pipeline for the ExtraArena game environment.

Use for anything about the ExtraArena RLHF data-collection & training-orchestration environment (rlhf_env, port 8090, MCP stdio): running semi-synthetic battles, generating training traces, orchestrating the Extra-LR training pipeline, or playing battles as a sub-agent. Routes to three sub-skills —

When not to use it

  • →When the task is not related to ExtraArena RLHF
  • →When the task is not related to data-collection or training-orchestration
  • →When the task is not related to playing battles as a sub-agent

Limitations

  • →Limited to ExtraArena RLHF environment
  • →Requires specific sub-skills for different orchestration levels
  • →Focuses on data-collection and training-orchestration

How it compares

This skill provides a structured, multi-level orchestration for RLHF in ExtraArena, allowing for automated data collection and training pipeline management beyond manual execution.

Compared to similar skills

extra-rlhf side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
extra-rlhf (this skill)04moReviewAdvanced
computer-use-agents1010moReviewAdvanced
crewai-developer211moReviewAdvanced
npc09moCautionIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

computer-use-agents

davila7

Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation.

1040

crewai-developer

smallnest

Comprehensive CrewAI framework guide for building collaborative AI agent teams and structured workflows. Use when developing multi-agent systems with CrewAI, creating autonomous AI crews, orchestrating flows, implementing agents with roles and tools, or building production-ready AI automation. Essential for developers building intelligent agent systems, task automation, and complex AI workflows.

213

npc

pipecat-ai

Runs an autonomous AI task agent as a game character. Resolves a character name to its UUID, then launches the `npc-run` script which connects to the game server and executes the given task using a Pipecat + Gemini LLM pipeline.

00

llama-cpp

zechenzhangAGI

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

21471

langchain

zechenzhangAGI

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

26138

llama-factory

zechenzhangAGI

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

15112

Search skills

Search the agent skills registry