All Skills

Hebrew LLM Eval Suite

Author: skills-il

Trusted78/100

Benchmark and compare LLMs on Hebrew reasoning, comprehension, sentiment, translation, and Israeli cultural knowledge. Wraps the HuggingFace Open Hebrew LLM Leaderboard tasks (HeQ, HebrewSentiment, Hebrew Winograd, translation) plus DictaLM 3.0 benchmark tasks (Summarization, Nikud, Israeli Trivia) into a reproducible evaluation harness. Runs evals against Claude, GPT, Gemini, AI21 Jamba, DictaLM, Llama, and local HuggingFace models. Produces comparison scorecards in JSON and markdown. Use when choosing an LLM for a Hebrew product, answering procurement questions about Hebrew performance, validating a fine-tuned Hebrew model, or tracking Hebrew regressions after a model upgrade. Do NOT use for Arabic NLP, ASR benchmarking, or general English benchmarks.

Israeli AI Compliance Kit

Author: skills-il

Trusted78/100

Guide Israeli ML teams through the AI governance and compliance stack: Ministry of Innovation December 2023 AI policy principles, Privacy Protection Law (PPL) and Amendment 13 applied to ML training data, sector-specific rules (Bank of Israel Directive 364, Ministry of Health AMAR medical-device AI), and EU AI Act exposure for Israeli exporters. Generates model cards, data statements, and DPIA templates tailored to Israeli context. Use when preparing AI governance docs, answering an enterprise customer's AI risk review, classifying a system under the EU AI Act, or building an internal responsible-AI checklist. Prevents costly compliance gaps when shipping AI to regulated markets. Do NOT use for general PPL policy (use israeli-privacy-shield), web app security (use israeli-appsec-scanner), or SOC/threat triage (use israeli-cybersecurity-ops).