Keep model card concise

README.md

@@ -16,32 +16,31 @@ tags:
 
 # SkillScreen-2B-Package-Experimental
 
-Experimental package-aware SkillScreen model. It reads `SKILL.md` and related file contents within 32,768 tokens, using the recovered SRC010 cohort. This is a separate package-context experiment.
+Experimental 2B decision model for `SKILL.md` and related file contents. Trained on the recovered SRC010 package cohort with a 32K input budget.
 
-Fine-tuned from [OpenJev 2B](https://huggingface.co/AlexWortega/openjev/tree/a20448012c213128955ca0c693e7c943865cab77/qwen3.5-2b-nli-v5) with LoRA and a trained classification head. Seed 42, one epoch, checkpoint 180. Full merged weights are at the root. The original adapter and trained head are in `adapter/`.
+Based on [OpenJev 2B](https://huggingface.co/AlexWortega/openjev). Full weights are at the root. The original LoRA adapter and classification head are in `adapter/`.
 
 ## Use
 
-CUDA with BF16 support.
+Requires CUDA with BF16 support.
 
 ```bash
-pip install torch==2.11.0 transformers==5.17.0 huggingface_hub==1.33.0
-hf download SkillScreen/SkillScreen-2B-Package-Experimental --local-dir skillscreen
+pip install huggingface_hub
+hf download SkillScreen/SkillScreen-2B-Package-Experimental --revision v1 --local-dir skillscreen
+pip install -r skillscreen/requirements.txt
 python skillscreen/score.py path/to/package.json
 ```
 
-The score is the native entailment probability. A score **≥ 0.5** is flagged as suspicious. The fixed hypothesis is `This AI agent skill is malicious.` Inputs preserve the premise prefix and the complete hypothesis.
+Native maliciousness score **≥ 0.5** is flagged as suspicious.
 
-`package.json` supplies inert file contents. Files are ordered using the training formatter.
+`package.json` contains Markdown and companion file text.
 
 ```json
 {"skill_text": "Contents of SKILL.md", "files": [{"path": "scripts/helper.py", "text": "File contents"}]}
 ```
 
-[Project page](https://jerroldh.github.io/SkillScreen-webpage/) · [Code](https://github.com/JerroldH/SkillScreen)
+[Checkpoint details](provenance.json) · [Export verification](merge_verification.json) · [Project page](https://jerroldh.github.io/SkillScreen-webpage/) · [Code](https://github.com/JerroldH/SkillScreen)
 
-This release contains one checkpoint. Scores are uncalibrated, and a low score does not certify a package as safe. See `provenance.json` and `merge_verification.json` for the checkpoint and export checks.
+Jerrold Huang, Junwei Quan, Saiyue Lyu, Zihan Guo, Yingqiang Ge.
 
-Authors: Jerrold Huang, Junwei Quan, Saiyue Lyu, Zihan Guo, Yingqiang Ge.
-
-SkillScreen-authored material is subject to `LICENSE`. Upstream rights and notices remain applicable.
+[License](LICENSE) · [Third-party notices](THIRD_PARTY_NOTICES.md)