How huggingface/skills works
Hugging Face Skills is a collection of installable, self-contained AI/ML workflow instructions and scripts for agents. The main user-to-result path is an agent selecting a task skill, following its instructions, and running its scripts or connecting to the relevant Hugging Face or cloud service. The sampled runtime includes SageMaker deployment modes, model-training and evaluation examples, paper management, and two dataset-backed leaderboard apps. Many README-listed skills have no implementation excerpts here, so their internal flows are not expanded.
Main entry points: deploy_async.py Async endpoint · deploy_ic.py Scale-to-zero endpoint · deploy.py Real-time endpoint · _common.py Shared deployment helpers
Components 21
Cloud deployment
- Async endpoint
skills/hf-cloud-sagemaker-production-defaults/scripts/deploy_async.py - Scale-to-zero endpoint
skills/hf-cloud-sagemaker-production-defaults/scripts/deploy_ic.py - Real-time endpoint
skills/hf-cloud-sagemaker-production-defaults/scripts/deploy.py - Shared deployment helpers
skills/hf-cloud-sagemaker-production-defaults/scripts/_common.py - Python environment setup
skills/hf-cloud-python-env-setup/scripts/setup_env.py - IAM role preflight
skills/hf-cloud-sagemaker-iam-preflight/scripts/create_role.py
Model workflows
- LLM training examples
skills/huggingface-llm-trainer/scripts/unsloth_sft_example.py - Vision training
skills/huggingface-vision-trainer/scripts/image_classification_training.py - Sentence-transformer training
skills/train-sentence-transformers/scripts/train_cross_encoder_listwise_example.py - Community evaluation
skills/huggingface-community-evals/scripts/inspect_eval_uv.py
Hub utilities
- Paper management
skills/huggingface-paper-publisher/scripts/paper_manager.py - Hub API examples
skills/huggingface-tool-builder/references/baseline_hf_api.py
Leaderboards
- Evaluation collector
apps/evals-leaderboard/collect_evals.py - Evaluation leaderboard
apps/evals-leaderboard/app.py - Engagement collector
apps/hackers-leaderboard/collect_points.py - Hackers leaderboard
apps/hackers-leaderboard/app.py
Other components
- AI agent / user
- AWS services
- Hugging Face Hub
- Evaluation dataset
- Engagement dataset
Connections 23
- AI agent / user → Async endpoint: runs
skills/hf-cloud-sagemaker-production-defaults/scripts/deploy_async.py - AI agent / user → Scale-to-zero endpoint: runs
skills/hf-cloud-sagemaker-production-defaults/scripts/deploy_ic.py - AI agent / user → Real-time endpoint: runs
skills/hf-cloud-sagemaker-production-defaults/scripts/deploy.py - Async endpoint → Shared deployment helpers: uses helpers
skills/hf-cloud-sagemaker-production-defaults/scripts/deploy_async.py - Scale-to-zero endpoint → Shared deployment helpers: uses helpers
skills/hf-cloud-sagemaker-production-defaults/scripts/deploy_ic.py - Real-time endpoint → Shared deployment helpers: uses helpers
skills/hf-cloud-sagemaker-production-defaults/scripts/deploy.py - Async endpoint → AWS services: creates resources
skills/hf-cloud-sagemaker-production-defaults/scripts/deploy_async.py - Scale-to-zero endpoint → AWS services: creates resources
skills/hf-cloud-sagemaker-production-defaults/scripts/deploy_ic.py - Real-time endpoint → AWS services: creates resources
skills/hf-cloud-sagemaker-production-defaults/scripts/deploy.py - AI agent / user → Python environment setup: runs
skills/hf-cloud-python-env-setup/scripts/setup_env.py - AI agent / user → IAM role preflight: runs
skills/hf-cloud-sagemaker-iam-preflight/scripts/create_role.py - AI agent / user → LLM training examples: runs
skills/huggingface-llm-trainer/scripts/unsloth_sft_example.py - AI agent / user → Vision training: runs
skills/huggingface-vision-trainer/scripts/image_classification_training.py - AI agent / user → Sentence-transformer training: runs
skills/train-sentence-transformers/scripts/train_cross_encoder_listwise_example.py - AI agent / user → Community evaluation: runs
skills/huggingface-community-evals/scripts/inspect_eval_uv.py - AI agent / user → Paper management: runs
skills/huggingface-paper-publisher/scripts/paper_manager.py - Paper management → Hugging Face Hub: manages papers
skills/huggingface-paper-publisher/scripts/paper_manager.py - AI agent / user → Hub API examples: runs
skills/huggingface-tool-builder/references/baseline_hf_api.py - Hub API examples → Hugging Face Hub: queries models
skills/huggingface-tool-builder/references/baseline_hf_api.py - Evaluation collector → Evaluation dataset: writes scores
apps/evals-leaderboard/collect_evals.py - Evaluation leaderboard → Evaluation dataset: reads rows
apps/evals-leaderboard/app.py - Engagement collector → Engagement dataset: writes points
apps/hackers-leaderboard/collect_points.py - Hackers leaderboard → Engagement dataset: reads rows
apps/hackers-leaderboard/app.py