Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add skills-il/developer-tools --skill hebrew-llm-eval-suitegit clone --depth 1 https://github.com/skills-il/developer-toolsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/skills-il/developer-tools/hebrew-llm-eval-suite)<a href="https://agentmods.dev/skills/skills-il/developer-tools/hebrew-llm-eval-suite"><img src="https://agentmods.dev/badge/skills/skills-il/developer-tools/hebrew-llm-eval-suite.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 64 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00204 | $0.08311 |
| Opus 5 | $0.00102 | $0.04156 |
| Sonnet 5 | $0.00041 | $0.01662 |
| Haiku 4.5 | $0.00020 | $0.00831 |
Grade A, and why
hebrew-llm-eval-suite scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hebrew LLM Eval Suite
Problem
Israeli product teams pick LLMs blind. There is no standardized Hebrew benchmark that a PM can run in an afternoon to compare Claude against GPT against DictaLM against AI21 Jamba on their actual use case. The HuggingFace Open Hebrew LLM Leaderboard exists but is built for base models and few-shot prompts, not for API-hosted chat models. DictaLM publishes benchmark results but only for its own suite. Teams end up guessing, testing informally, or trusting marketing claims. The result is costly model switches after launch, or shipping Hebrew products on models that silently fail on native speakers.
Instructions
Step 1: Pick the right benchmark set for your task
Different benchmarks test different things. Choose the smallest set that covers your actual use case.
| Benchmark | HuggingFace ID | What it tests | When to use |
|---|---|---|---|
| HeQ (Hebrew Question Answering) | Etelis/HeQ_v1 (HF mirror); canonical at github.com/NNLP-IL/Hebrew-Question-Answering-Dataset |
Reading comprehension, extractive QA on Hebrew Wikipedia and Geektime articles. 30,147 questions | Any product that answers questions over Hebrew text: search, RAG, support, research assistants |
| HebrewSentiment | HebArabNlpProject/HebrewSentiment |
Sentiment classification (positive, negative, neutral). 43,645 rows. License other (not CC-BY-4.0), so check the card before commercial use |
Social media analysis, review classification, product feedback |
| Hebrew Winograd | Community port of Winograd Schema Challenge (cs.ubc.ca/~vshwartz/resources/winograd_he.jsonl) |
Pronoun resolution requiring world knowledge. Reasoning-heavy | Any product that needs nuanced Hebrew understanding |
| NeuLabs-TedTalks (translation) | OPUS NeuLab-TedTalks en-he subset | English to Hebrew and Hebrew to English translation quality | Translation products, multilingual apps |
| HebNLI | HebArabNlpProject/HebNLI |
Natural Language Inference in Hebrew | Classification, content moderation, logical reasoning |
| Hebrew MMLU | CohereLabs/Global-MMLU, config he |
General-knowledge accuracy; the Hebrew split of Global-MMLU. Shipped as the native global_mmlu task in lm-evaluation-harness, so this is the reproducible route. (openai/MMMLU covers 14 languages and Hebrew is NOT among them) |
General-purpose chat/RAG products that need broad world knowledge in Hebrew |
| DictaLM 3.0 Summarization | Dicta benchmark suite (see DictaLM 3.0 technical report) | Abstractive summarization of Hebrew news | Summarization tools, executive briefings |
| DictaLM 3.0 Nikud | Dicta benchmark suite | Adding vowel diacritics to unvocalized Hebrew | Educational tools, TTS preprocessing, religious text tools |
| DictaLM 3.0 Israeli Trivia | Dicta benchmark suite | Knowledge of Israeli culture, geography, history, politics. 300 questions | Consumer products where cultural grounding matters |
| AlephBench | HebArabNlpProject/AlephBench |
11 Hebrew tasks with frozen prompts and per-row model outputs, published by the same body that runs the leaderboard. License CC-BY-4.0 | The closest thing to a reproducible, single-repo Hebrew benchmark. Start here if you want frozen prompts |
| Grounding / abstention | HebArabNlpProject/asmachta, HebArabNlpProject/abstractive-qa-llm-eval |
Attributed QA where a deliberate share of questions is unanswerable, so you measure hallucination-vs-abstention directly | Hebrew RAG and support bots, where a confident wrong answer is the expensive failure |
| Long-context NLI | HebArabNlpProject/LCHAIM |
Hebrew NLI over long contexts | Products that reason over long Hebrew documents |
| Hebrew summarization | HebArabNlpProject/HebSummaries |
Human-annotated Hebrew summarization | Downloadable alternative to the DictaLM Summarization task, whose data is not published as a dataset |
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evidence.json 19 KB
- metadata.json 2.4 KB
- optimization-log.json 2.6 KB
- references/.gitkeep 0 B
- references/benchmark-catalog.md 8.2 KB
- references/prompt-templates.md 5.6 KB
- scripts/.gitkeep 0 B
- scripts/make_scorecard.py 7.9 KB runs code
- scripts/run_eval.py 11 KB runs code
- scripts/score_results.py 8.7 KB runs code
- SKILL_HE.md 40 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 302 lines · 204 tokens per session scan A 0517a1a8ec7c
hebrew-llm-eval-suite is a skill published in the GitHub repository skills-il/developer-tools (10 stars, last pushed 6d ago), licensed MIT. It adds 204 tokens to every session and 8,311 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
cli-eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
darwinian-evolver
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
validate
Validate Semantica pipelines, extraction quality, graph schemas, and ontology consistency. Returns structured error/warning checklists. Uses PipelineValidator, PipelineBuilder.validatepipeline(), GraphValidator, and OntologyValidator. Sub-commands: pipeline, step, dependencies, extraction, graph, ontology, performance.
launching-evals
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals…
nemo-automodel-recipe-development
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.