huggingface-skills

A collection of nine add-ons for Hugging Face Hub, a platform for sharing machine-learning models, datasets, research papers, and related tools.

In plain words
What is it for?
Use it for Hugging Face tasks such as dataset creation, model training, model evaluation, paper publishing, and tool building.
Why use it?
It brings together separate workflows for preparing data, training and evaluating models, building tools, and publishing research.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add patchy631/ai-engineering-hub
agentmods
npx agentmods add plugins/patchy631/ai-engineering-hub/marketplace
Clone the repo
git clone --depth 1 https://github.com/patchy631/ai-engineering-hub

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

huggingface-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

hugging-face-skills/.claude-plugin/marketplace.json · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "huggingface-skills",
  "owner": {
    "name": "Hugging Face"
  },
  "metadata": {
    "description": "Agent Skills for AI/ML tasks including dataset creation, model training, evaluation, and research paper publishing on Hugging Face Hub",
    "version": "1.0.0"
  },
  "plugins": [
    {
      "name": "hugging-face-model-trainer",
      "source": "./skills/hugging-face-model-trainer",
      "skills": "./",
      "description": "Train or fine-tune language models using TRL on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes hardware selection, cost estimation, Trackio monitoring, and Hub persistence."
    },
    {
      "name": "hugging-face-paper-publisher",
      "source": "./skills/hugging-face-paper-publisher",
      "skills": "./",
      "description": "Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles."
    },
    {
      "name": "hugging-face-datasets",
      "source": "./skills/hugging-face-datasets",
      "skills": "./",
      "description": "Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation."
    },
    {
      "name": "hugging-face-evaluation",
      "source": "./skills/hugging-face-evaluation",
      "skills": "./",
      "description": "Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom evaluations with vLLM/lighteval."
    },
    {
      "name": "hugging-face-tool-builder",
      "source": "./skills/hugging-face-tool-builder",
      "skills": "./",
      "description": "Build reusable scripts for Huggi

Read the full file on GitHub · 67 lines

Files

What ships with it

1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 67 lines scan A b8bcde1594c4

Subscribe to this mod's changes

huggingface-skills is a plugin published in the GitHub repository patchy631/ai-engineering-hub (37,278 stars, last pushed 6d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.