Agent Skills

TRL Training on Hugging Face Jobs

claude-skill-registry

Train and fine-tune language models on Hugging Face Jobs using TRL (SFT, DPO, GRPO) with Trackio monitoring and automated Hub push. Includes scripts, cost estim

Hugging Face Evaluation Manager

skillattack

Extract, import, and add structured model evaluation results to Hugging Face model cards; run or import benchmark evaluations and generate model-index YAML for

ML Intern — Hugging Face Workflow Orchestrator

claude-ml-intern-skill

Autonomous ML intern that researches, implements, trains, verifies, and publishes ML experiments using the Hugging Face ecosystem, with budgeted retry loops and

TRL LLM Fine-Tuning & Alignment

argentos-core

Comprehensive guide for fine-tuning LLMs using TRL, covering SFT, DPO, PPO, and GRPO for human preference alignment.

AEON Bench LLM Evaluation

aeon-bench-pod

Execute end-to-end LLM benchmarks using AEON Bench Pod. From model verification to leaderboard submission.

Transformers.js ML Integration

opencode-skills-collection

Run state-of-the-art ML models for text, image, and audio directly in JavaScript/Node.js without a separate Python backend.

Transformers.js (JavaScript ML)

openskynet

Run Hugging Face models natively in JavaScript/TypeScript (browser or Node) using Transformers.js for text, vision, and audio tasks with WebGPU/WASM fallbacks.