localization
CLAUDE.md26 starsChanged 9 months agoMITView on GitHub
This is a Skills IL category repository containing AI agent skills for Hebrew localization, RTL layout, and cultural adaptation. Each subdirectory is a self-contained skill following the open Agent Skills standard. Every skill is a folder containing a SKILL.md file. The folder name MUST be kebab-case. These rules are enforced by CI on every PR: See CONTRIBUTING.md for the full guide.
In this repository13 other files it gives its agents.
- hebrew-ai-text-humanizerSkill
- hebrew-content-writerSkill
- hebrew-document-generatorSkill
- hebrew-i18nSkill
- hebrew-nlp-toolkitSkill
- hebrew-ocr-formsSkill
- hebrew-rtl-best-practicesSkill
- hebrew-tailwind-presetSkill
- israeli-accessibility-complianceSkill
- israeli-apartment-huntingSkill
- israeli-ui-design-systemSkill
- israeli-wedding-plannerSkill
- shabbat-aware-schedulerSkill
The file
We split this CLAUDE.md into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
Every skill is a folder containing a SKILL.md file.
- Distinctive: line 55
No skill names containing "claude" or "anthropic"
- Distinctive: line 68
All skill folders use kebab-case naming
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CLAUDE.md
This file provides guidance to Claude Code when working in this repository.
Project Overview
This is a Skills IL category repository containing AI agent skills for Hebrew localization, RTL layout, and cultural adaptation. Each subdirectory is a self-contained skill following the open Agent Skills standard.
Repository Structure
localization/
├── .github/ # CI workflows, issue/PR templates
├── hebrew-rtl-best-practices/ # Skill: Hebrew RTL Best Practices
│ ├── SKILL.md # Required skill definition
│ └── references/ # Optional documentation
├── hebrew-nlp-toolkit/ # Skill: Hebrew NLP Toolkit
│ └── SKILL.md
├── CLAUDE.md # This file
├── LICENSE # MIT
└── README.md # Category overviewSkill Format (CRITICAL)
Every skill is a folder containing a SKILL.md file. The folder name MUST be kebab-case.
SKILL.md Structure
---
name: skill-name-in-kebab-case # Required, must match folder name
description: >- # Required, <1024 chars, no XML tags
[What it does]. [When to use it — include trigger phrases].
[Key capabilities]. [Optional: Do NOT use for X].
license: MIT # Optional
metadata: # Optional
author: github-username
version: 1.0.0
category: localization
tags: [hebrew, rtl, nlp]
---Validation Rules
These rules are enforced by CI on every PR:
- File must be exactly
SKILL.md(case-sensitive) - YAML frontmatter must have
---delimiters on both sides namefield: kebab-case only, must match folder namedescriptionfield: present, under 1024 chars, no XML angle brackets, must include WHAT + WHEN- SKILL.md body must be under 5,000 words
- No
README.mdinside skill folders - No skill names containing "claude" or "anthropic"
- No hardcoded secrets
See CONTRIBUTING.md for the full guide.
Commands
./scripts/validate-skill.sh <skill-folder>/SKILL.mdConventions
- All skill folders use kebab-case naming
- Bilingual content should use
{ he: "...", en: "..." }when applicable - Israeli-specific context should reference official sources
- Org-level files are inherited from skills-il/.github
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

