claude-ui-rtl
CLAUDE.md0 starsChanged 8 months agoMITView on GitHub
A skill for Claude (desktop and web) that renders Hebrew, Arabic, and Persian/Farsi responses as inline HTML artifacts with proper RTL layout, instead of plain LTR chat text. Users download SKILL.md, open Claude (desktop or web), go to Customize → Upload Skill, and select the file. The skill triggers automatically on Hebrew (U+0590–U+05FF) and Arabic/Farsi (U+0600–U+06FF, U+FB50–U+FDFF, U+FE70–U+FEFF) input.
In this repositoryOne other file it gives its agents.
- rtlSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Keep the skill minimal — it runs on nearly every prompt so token count matters.
- Distinctive: line 23
No examples in the skill file — kept to template + rules only.
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 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 RTL Skill — Session Notes
Project summary
A skill for Claude (desktop and web) that renders Hebrew, Arabic, and Persian/Farsi responses as inline HTML artifacts with proper RTL layout, instead of plain LTR chat text.
Key files
SKILL.md— the installable skill file (uploaded via Customize → Upload Skill)README.md— install and usage instructionsassets/— before/after screenshots
Install flow
Users download SKILL.md, open Claude (desktop or web), go to Customize → Upload Skill, and select the file. The skill triggers automatically on Hebrew (U+0590–U+05FF) and Arabic/Farsi (U+0600–U+06FF, U+FB50–U+FDFF, U+FE70–U+FEFF) input.
Skill design decisions
- Skill must be a
.mdfile — NOT a ZIP. Claude's upload skill UI accepts.mddirectly. - The skill must say do NOT use file tools — otherwise Claude creates an artifact as a separate file instead of rendering inline.
- Keep the skill minimal — it runs on nearly every prompt so token count matters.
- Supported languages narrowed to Hebrew, Arabic, Farsi only (removed Urdu, Yiddish, Syriac, etc.).
- No examples in the skill file — kept to template + rules only.
Rendering rules (in SKILL.md)
direction: rtl; text-align: righton outer containerline-height: 1.7for Hebrew,1.9for Arabic/Farsipadding-rightfor list indentation- Inline LTR content wrapped in
<span style="direction: ltr; display: inline-block;"> - Colors via CSS variables only (
var(--color-text-primary), etc.)
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.

