hebrew-nlp-toolkit

Guidance for choosing and using language-processing models for Hebrew text, including models for writing, classification, named-entity recognition, sentiment, grammar, and question answering. Named-entity recognition finds items such as people, places, and dates in text.

In plain words
What is it for?
Use it to process Hebrew text, classify or analyze documents, extract names and places, detect sentiment, study word structure, or build Hebrew question-answering tools.
Why use it?
It reduces the guesswork involved in selecting a Hebrew model for a particular text-processing job and supports choices from small local models to larger ones.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/squadcodercom/squadcoder/hebrew-nlp-toolkit
Any agent
npx skills add squadcodercom/squadcoder --skill hebrew-nlp-toolkit
Clone the repo
git clone --depth 1 https://github.com/squadcodercom/squadcoder

Made for: Claude Code, Codex.

Per session 166 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,109 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 98% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00166 $0.03109
Opus 5 $0.00083 $0.01554
Sonnet 5 $0.00033 $0.00622
Haiku 4.5 $0.00017 $0.00311

Measured 2d ago against content hash 58f6afd165a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hebrew-nlp-toolkit 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/preprocess_hebrew.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

98% identical to hebrew-nlp-toolkit — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.squadcoder/skills/hebrew-nlp-toolkit/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hebrew NLP Toolkit

Instructions

Step 1: Identify the NLP Task

Task Recommended Model HuggingFace ID Size Notes
Text generation (large) DictaLM 3.0 24B Base dicta-il/DictaLM-3.0-24B-Base 24B Best Hebrew generation, built on Mistral-Small-3.1-24B
Text generation (small) DictaLM 3.0 Nemotron Instruct dicta-il/DictaLM-3.0-Nemotron-12B-Instruct 12B Instruction-tuned, smaller footprint
Reasoning / chain-of-thought DictaLM 3.0 24B Thinking dicta-il/DictaLM-3.0-24B-Thinking 24B Emits explicit thinking blocks before answering
Lightweight / edge DictaLM 3.0 1.7B Thinking (GGUF) dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF 1.7B Runs on laptop / CPU via llama.cpp
Classification / fill-mask DictaBERT dicta-il/dictabert 184M Fast, good accuracy
NER DictaBERT NER dicta-il/dictabert-ner 184M Recognizes PER, GPE, TIMEX, TTL
Sentiment DictaBERT Sentiment dicta-il/dictabert-sentiment 184M Hebrew sentiment classification
Morphology DictaBERT Morph dicta-il/dictabert-morph 184M Prefix segmentation and POS
Hebrew QA DictaBERT HeQ dicta-il/dictabert-heq 184M Extractive question answering
Embeddings (modern) NeoDictaBERT Bilingual Embed dicta-il/neodictabert-bilingual-embed 400M Hebrew-English sentence embeddings
Embeddings (legacy) AlephBERT onlplab/alephbert-base 110M Older baseline for similarity
Speech-to-text ivrit.ai Whisper v3 ivrit-ai/whisper-large-v3 1.55B Fine-tuned on the ivrit.ai Hebrew speech corpus (a 22K+ hour dataset)
Speech-to-text (fast) ivrit.ai Whisper v3 Turbo CT2 ivrit-ai/whisper-large-v3-turbo-ct2 809M CTranslate2, ~3x faster inference

Step 2: Install and Load Model

DictaBERT (base model, fill-mask):

from transformers import AutoTokenizer, AutoModelForMaskedLM

tokenizer = AutoTokenizer.from_pretrained("dicta-il/dictabert")
model = AutoModelForMaskedLM.from_pretrained("dicta-il/dictabert")

dicta-il/dictabert is a masked-LM base with NO classification head. Do not load it with AutoModelForSequenceClassification and run inference, that instantiates a randomly-initialised head and returns meaningless predictions. For classification, either fine-tune it on labeled data first, or use a ready task-specific model such as dicta-il/dictabert-sentiment (sentiment) or dicta-il/dictabert-ner (NER).

Read the full file on GitHub · 174 lines

Files

What ships with it

5 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.

Changes

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.

  1. 2d ago First seen · 174 lines · 166 tokens per session scan A 58f6afd165a5

Subscribe to this mod's changes

hebrew-nlp-toolkit is a skill published in the GitHub repository squadcodercom/squadcoder (11 stars, last pushed 2mo ago), licensed MIT. It adds 166 tokens to every session and 3,109 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to hebrew-nlp-toolkit, differing in 2 lines, and is treated as a copy.

Related

Other skills, from other repositories

docker-extend

Use when: User wants to extend Docker with custom tools, personalize the Docker environment, or set up user-specific Docker customization. Triggers: 'extend docker', 'docker-extend', 'add tools to docker', 'customize docker', 'add my tools to the container', 'personalize docker setup', 'docker user setup', 'install…

coleam00/Archon · 118 tokens

write-zot-themes

Help the user create, install, or package zot themes, including theme-only extensions.

patriceckhart/zot · 23 tokens

python-testing

Python testing best practices using pytest including fixtures, parametrization, mocking, coverage analysis, async testing, and test organization. Use when writing or improving Python tests.

mturac/everything-openai-codex · 35 tokens

database-migrations

Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Django, TypeORM, golang-migrate). Use when planning or implementing database schema changes.

mturac/everything-openai-codex · 61 tokens

docker-patterns

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration. Use when setting up containerized development environments or reviewing Docker configurations.

mturac/everything-openai-codex · 40 tokens

python-patterns

Python-specific design patterns and best practices including protocols, dataclasses, context managers, decorators, async/await, type hints, and package organization. Use when working with Python code to apply Pythonic patterns.

mturac/everything-openai-codex · 45 tokens