Hugging Face Skills is a collection of packaged instructions, scripts, and resources that teach AI agents how to perform tasks in the Hugging Face ecosystem, such as managing models and datasets, training models, and running evaluations. It is for coding agents that need to use Hugging Face Hub and machine-learning workflows. The catalogue entries are the project's own skills and integrations for agent clients.
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.
git clone --depth 1 https://github.com/huggingface/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/huggingface/skills/skills)<a href="https://agentmods.dev/plugins/huggingface/skills/skills"><img src="https://agentmods.dev/badge/plugins/huggingface/skills/skills/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/huggingface/skills/skills"><img src="https://agentmods.dev/badge/plugins/huggingface/skills/skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 today.
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.
What it actually says
{
"name": "huggingface-skills",
"description": "Core Hugging Face Hub operations through the hf CLI, including skill installation, repo management, jobs, datasets, models, Spaces, and discovery.",
"version": "1.0.36",
"author": {
"name": "Hugging Face"
},
"homepage": "https://github.com/huggingface/skills",
"repository": "https://github.com/huggingface/skills",
"license": "Apache-2.0",
"keywords": [
"huggingface",
"machine-learning",
"hub",
"cli",
"skills",
"jobs",
"llm"
]
}
What it installs
The manifest is a name and a version. 26 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 3,014 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill huggingface-lora-space-builder A 187 tokens
- Skill huggingface-vision-trainer A 194 tokens
- Skill hf-cloud-sagemaker-production-defaults A 150 tokens
- Skill huggingface-gradio A 37 tokens
- Skill transformers-js A 89 tokens
- Skill hf-cloud-serving-image-selection A 234 tokens
- Skill huggingface-zerogpu A 205 tokens
- Skill huggingface-papers A 78 tokens
- Skill hf-cloud-sagemaker-deployment-planner A 216 tokens
- Skill hf-cloud-sagemaker-iam-preflight A 131 tokens
- Skill hf-cloud-python-env-setup A 128 tokens
- Skill huggingface-best A 146 tokens
- Skill hf-mcp A 52 tokens
- Skill huggingface-datasets A 43 tokens
- Skill huggingface-trackio A 63 tokens
- Skill trl-training A 56 tokens
- Skill hf-mem A 32 tokens
- Skill huggingface-local-models A 59 tokens
- Skill huggingface-spaces B 106 tokens
- Skill huggingface-community-evals C 71 tokens
- Skill hf-cloud-aws-context-discovery C 132 tokens
- Skill hf-cli C 217 tokens
- Skill huggingface-llm-trainer A 133 tokens
- Skill huggingface-paper-publisher A 42 tokens
- Skill train-sentence-transformers A 146 tokens
- Skill huggingface-tool-builder A 67 tokens
- MCP server huggingface-skills A not measured
What ships with it
2 files beside plugin.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.
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.
- today Changed 90c27ce8da34
- 15d ago Changed 4695789cc26c
- 22d ago Changed 9bb2baf83245
- 29d ago Changed 31dbd60ddc96
- 1mo ago Changed 6387af59041b
- 1mo ago Changed 1946e00cc85d
- 1mo ago Changed d6f6045911df
- 1mo ago First seen · 21 lines scan A d4feec084b76
huggingface-skills is a plugin published in the GitHub repository huggingface/skills (11,203 stars, last pushed yesterday), licensed Apache-2.0. 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.
Other plugins, from other repositories
tao-skill-bank
NVIDIA TAO skill bank with generated capability discovery for model training, data processing, application workflows, AutoML, and platform execution.
clip-aware-embeddings
Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matching. NOT for counting objects, fine-grained classification (celebrities, car models), spatial reasoning, or compositional queries. Activate on "CLIP", "embeddings", "image similarity", "semantic…
twelvelabs
TwelveLabs video AI integration. Index, search, and analyze videos using TwelveLabs' multimodal AI platform.
databricks
Databricks skills for the CLI, Apps, Lakebase, Model Serving, Lakeflow Jobs, Spark Declarative Pipelines, Declarative Automation Bundles (DABs), and classic-to-serverless migration.
classifier
Text classification CLI using Bayesian, LSI, KNN, Logistic Regression, and TF-IDF algorithms.
sql-database-pipeline
Build SQL database pipelines with dlt: connect to any SQL source, load tables to a destination, tune performance with backends.