
HF's official 18-skill ML bundle dropped today — spotlight: LLM trainer for GPU fine-tuning via Claude Code
huggingface/skills — Hugging Face's official 18-skill bundle for AI/ML workflows, dropped today. The spotlight skill, huggingface-llm-trainer, teaches your coding agent to submit GPU training jobs on Hugging Face Jobs infrastructure, choose the right hardware tier, and handle the critical pitfall every new user hits: the default timeout that silently kills your run. 1| Field | Value |
|---|---|
| Repo | huggingface/skills |
| Maintainer | Hugging Face (official) |
| License | Apache 2.0 |
| Stars / forks | 10.7K stars / 703 forks (16 hours post-launch) |
| Supported agents | Claude Code, OpenAI Codex, Google Gemini CLI, Cursor |
| Total skills | 18 (hf-cli, huggingface-llm-trainer, huggingface-datasets, huggingface-spaces, and 14 more) |
| Today's spotlight | huggingface-llm-trainer |
| Prerequisites | HF Pro / Team / Enterprise account + HF_TOKEN env variable |
huggingface/skills gives coding agents structured knowledge of the Hugging Face ecosystem across 18 task-specific SKILL.md files. Each file is a YAML-fronted Markdown document that tells the agent which HF tools exist, when to reach for each one, and how to call them correctly — without requiring the agent to hallucinate API surface area from training data.hf-cli for Hub operations, huggingface-datasets for loading and querying datasets, huggingface-spaces for deploying Gradio apps, huggingface-papers for searching arXiv-adjacent research, huggingface-zerogpu for ZeroGPU-specific programming rules, transformers-js for browser-side inference, and train-sentence-transformers for embedding model fine-tuning. 2hf-cli, which is generated directly from the locally installed hf CLI binary and stays in sync with whatever version you have. That means the skill's command inventory doesn't drift from your actual tool — a small but meaningful design decision. 2huggingface/skills launched roughly 16 hours ago and has already accumulated 10.7K stars and 703 forks — a faster initial trajectory than either the Microsoft Azure Skills release (601 stars after two days) or NVIDIA's SkillSpector (2.5K stars at 18 hours). 1 It's the third official platform skills release after Google's Android Skills and Microsoft's Azure Skills, and the first focused on ML/AI workflows specifically.
huggingface-llm-trainer SKILL.md — left panel shows the skill's file tree including estimate_cost.py and dataset_inspector.py; right panel shows the YAML frontmatter declaring four supported agents and Apache 2.0 license. AI-generated illustration based on the actual SKILL.md structure. 3huggingface-llm-trainer teaches your agent to run SFT (supervised fine-tuning), DPO (direct preference optimization), GRPO (group relative policy optimization), and Reward Modeling jobs on Hugging Face Jobs GPU infrastructure — entirely through an async job submission pattern your agent handles inside a normal chat session. 3| GPU | Approx. cost | Best for |
|---|---|---|
t4-small | ~$0.75/h | Demos, <1B params, sanity checks |
a10g-large | ~$5/h | 3-7B production fine-tunes |
a100-large | ~$10-20/h | 13B+ models |
hf_jobs("uv", {...}). The skill includes cost-estimating (estimate_cost.py), a dataset validator (dataset_inspector.py — runs on CPU for about $0.01), and a benchmark model search helper (hf_benchmarks.py) to find a good starting checkpoint. 3hf CLI installed locally (pip install huggingface_hub[cli]); and HF_TOKEN set in your environment.# Step 1: add the HF skills registry
/plugin marketplace add huggingface/skills
# Step 2: install the HF CLI skill first (always start here)
/plugin install hf-cli@huggingface/skills
# Step 3: install the LLM trainer spotlight
/plugin install huggingface-llm-trainer@huggingface/skillscp -r path/to/skills/skills/huggingface-llm-trainer .agents/skills/gemini extensions install huggingface/skillsagentsmd/AGENTS.md to your project root — it serves as a plain Markdown reference that any agent can read without skills infrastructure.huggingface-llm-trainer is installed, you prompt Claude Code roughly like this:"Fine-tuneQwen/Qwen2.5-3B-Instructon my dataset atusername/my-sft-datasetusing SFT. Use an a10g-large GPU, set timeout to 3 hours, and push the result tousername/my-finetuned-qwen. Validate the dataset format first before submitting."
dataset_inspector.py on CPU (~$0.01) to confirm the dataset has the correct messages column formatestimate_cost.py to surface the expected job cost before committinghf_jobs("uv", {script: "...", flavor: "a10g-large", timeout: "3h", secrets: {HF_TOKEN: "$HF_TOKEN"}})push_to_hub=True plus the HF_TOKEN secret are non-negotiable — otherwise the trained model is gone when the container terminates. The SKILL.md puts this in capitals:"The Jobs environment is temporary. All files are deleted when the job ends. If the model isn't pushed to Hub, ALL TRAINING IS LOST." 3
"Skills in CC have been a bit frustrating for me. They don't trigger reliably, and sometimes it just continues to go into the next step." 4
"place things that you need to happen into tooling and harnessing, and place things that would be nice for the agent to conceptualize into skills." 4
Making the skill "call this script with these parameters" rather than a complex reasoning task reduces failure modes. 4
CLAUDE.md increased how often the agent actually used it. 4huggingface-llm-trainer and the newer trl-training skill have overlapping scope, and asking Hugging Face to clarify deprecation or coordination intent. That's unresolved. 6dataset_inspector.py first is not optional for production use. 3huggingface-llm-trainer vs trl-training. Two skills cover overlapping territory. Issue #163 asks for clarification; currently unresolved. 6CLAUDE.md is a practical workaround. 4huggingface-llm-trainer if:trl library works fine without the skill.huggingface-llm-trainer if:hf-cli is the right starting point — the HF docs explicitly call it out as the recommended first install, and it provides the broadest surface area (Hub uploads, model searches, dataset queries) with no paid-account requirement. 8# Claude Code — install hf-cli first, then the LLM trainer
/plugin marketplace add huggingface/skills
/plugin install hf-cli@huggingface/skills
/plugin install huggingface-llm-trainer@huggingface/skills
# Then set your token:
export HF_TOKEN=hf_xxxxgithub.com
raw.githubusercontent.com
raw.githubusercontent.com
news.ycombinator.com
github.com
huggingface.co
This story was produced automatically by a channel. One sentence is all it takes for Neodrop to keep producing for you.