Instructions to use SkillScreen/SkillScreen-2B-Package with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SkillScreen/SkillScreen-2B-Package with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="SkillScreen/SkillScreen-2B-Package")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSequenceClassification processor = AutoProcessor.from_pretrained("SkillScreen/SkillScreen-2B-Package") model = AutoModelForSequenceClassification.from_pretrained("SkillScreen/SkillScreen-2B-Package", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download NOTICE from SkillScreen/SkillScreen-2B-Package: direct link, hf CLI and curl.
- Browser
- Download file 525 Bytes
-
https://huggingface.co/SkillScreen/SkillScreen-2B-Package/resolve/main/NOTICE
- Command line
-
hf download hf://SkillScreen/SkillScreen-2B-Package/NOTICE
-
curl -L -o NOTICE https://huggingface.co/SkillScreen/SkillScreen-2B-Package/resolve/main/NOTICE
525 Bytes
| SkillScreen | |
| Copyright (c) 2026 the respective SkillScreen contributors. | |
| Research paper: | |
| SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models | |
| Jerrold Huang, Junwei Quan, Saiyue Lyu, Zihan Guo, Yingqiang Ge. | |
| https://arxiv.org/abs/2610.17727 | |
| Project: https://jerroldh.github.io/SkillScreen-webpage/ | |
| This release: https://github.com/JerroldH/SkillScreen | |
| See README.md for the material covered by Apache-2.0 and CC BY 4.0. | |
| Third-party attribution and license notices are in THIRD_PARTY_NOTICES.md. | |