arabic-terminal-rtl
Skill3 starsChanged 5 months agoMITView on GitHub
Use when writing Arabic in Windows Terminal, OpenCode, Codex, or any non-BiDi terminal; reverses Arabic word characters and Arabic segment word order by default.
In this repository4 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
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
- Distinctive: line 14
Use this skill by default whenever a reply contains Arabic-script prose in OpenCode, Codex, Windows Terminal, or any terminal that does not …
- Distinctive: line 16
Do not wait for the user to remind you once the environment or instructions indicate Arabic terminal mode.
- Very specific: line 55
Keep English/code/numbers unchanged.
- Distinctive: line 72
If Arabic appears inside machine-readable content that must remain exact or executable, preserve it verbatim and explain outside the code …
- Distinctive: line 76
Keep punctuation attached to its token during reversal.
- Distinctive: line 87
Do not explain this rule unless asked.
- Distinctive: line 88
Do not apologize for transformed Arabic looking unusual.
- Distinctive: line 89
Do not output normal Arabic prose when Arabic terminal mode is active.
- Distinctive: line 94
Every Arabic word reversed character-by-character?
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
Arabic Terminal RTL
Purpose
Windows Terminal and some CLI surfaces can render Arabic RTL/BiDi text incorrectly. This skill makes Arabic-script prose readable in left-to-right, non-BiDi terminals.
Activation
Use this skill by default whenever a reply contains Arabic-script prose in OpenCode, Codex, Windows Terminal, or any terminal that does not reliably support RTL/BiDi rendering.
Do not wait for the user to remind you once the environment or instructions indicate Arabic terminal mode.
Required Output Rule
For every Arabic-script prose segment, apply both transformations before sending:
- Reverse the character order inside each Arabic-script word.
- Reverse the word order of that Arabic segment.
Examples:
Intended logical Arabic: الحمد لله
Terminal-safe output: هلل دمحلا
Intended logical Arabic: السلام عليكم ورحمة الله
Terminal-safe output: هللا ةمحرو مالسلا مكيلعو
Intended logical Arabic: لا إله إلا الله
Terminal-safe output: هللا ال هلإ الScope
Apply to:
- Arabic answers
- Arabic headings
- Arabic bullets
- Arabic confirmations
- Arabic questions
- Arabic explanations
- inline Arabic phrases
- single Arabic words
Mixed Arabic and non-Arabic segments:
- Reverse token order inside the Arabic-containing segment.
- Reverse characters only inside Arabic-script tokens.
- Keep English/code/numbers unchanged.
Preserve Exactly
Do not transform:
- code blocks
- shell commands
- file paths
- URLs
- JSON/YAML/TOML
- identifiers
- package names
- English text
- numbers
- slash commands
If Arabic appears inside machine-readable content that must remain exact or executable, preserve it verbatim and explain outside the code block if needed.
Punctuation
Keep punctuation attached to its token during reversal.
Example:
Intended logical Arabic: الحمد لله.
Terminal-safe output: .هلل دمحلاBehavior
- Do not explain this rule unless asked.
- Do not apologize for transformed Arabic looking unusual; it is intentional.
- Do not output normal Arabic prose when Arabic terminal mode is active.
- Apply even to short replies.
Self-Check Before Sending
- Every Arabic word reversed character-by-character?
- Arabic word order reversed per segment?
- English/code/URLs/paths/commands untouched?
- Slash commands untouched?
- Machine-readable content preserved?
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.

