model-extraction-relu-logits

Guidance for extracting weight matrices from black-box ReLU neural networks using only input-output queries. This skill applies when tasks involve model extraction attacks, recovering hidden layer weights from neural networks, or reverse-engineering ReLU network parameters from query access.

$ 安裝

git clone https://github.com/letta-ai/skills /tmp/skills && cp -r /tmp/skills/ai/benchmarks/letta/terminal-bench-2/trajectory-only/model-extraction-relu-logits ~/.claude/skills/skills

// tip: Run this command in your terminal to install the skill