New Checked the same way as MCP servers
Agent Skills, and what they let an agent do
Read straight from each publisher's repository. For every skill: what it allows the agent to do, the scripts it ships, and what fixed checks matched. Nothing is run.
Skills from Hugging Face10
Clear filters- hf-cloud-python-env-setupHugging Face · 2 scriptsSet up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run …OfficialDestructive commandsReaches the network1 high finding
- hf-cloud-sagemaker-iam-preflightHugging Face · 2 scriptsEnsure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a…OfficialRuns commands
- hf-cloud-sagemaker-production-defaultsHugging Face · 6 scriptsCreate a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or…OfficialRuns commands
- hf-cloud-serving-image-selectionHugging Face · 1 scriptPick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "hos…OfficialReaches the networkRuns commands
- huggingface-community-evalsHugging Face · 3 scriptsRun evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results public…OfficialRuns commands
- huggingface-llm-trainerHugging Face · 8 scriptsTrain or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guida…OfficialReaches the networkRuns commands3 high findings
- huggingface-paper-publisherHugging Face · 1 scriptPublish 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.OfficialReaches the networkRuns commands
- huggingface-tool-builderHugging Face · 6 scriptsUse this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusab…OfficialDestructive commandsReaches the network1 high finding
- huggingface-vision-trainerHugging Face · 5 scriptsTrains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transfo…OfficialReaches the networkRuns commands
- train-sentence-transformersHugging Face · 14 scriptsTrain or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for t…OfficialReaches the networkRuns commands
Labels come from the skill's own files, read on the date shown: the tools its frontmatter allows and the scripts it ships. They are not a safety rating, and no finding is not a safety guarantee. How skills are checked.