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 m3taz-ahmed/ai-globals --skill arabic-dialect-lordgit clone --depth 1 https://github.com/m3taz-ahmed/ai-globalsWrote 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/m3taz-ahmed/ai-globals/arabic-dialect-lord)<a href="https://agentmods.dev/skills/m3taz-ahmed/ai-globals/arabic-dialect-lord"><img src="https://agentmods.dev/badge/skills/m3taz-ahmed/ai-globals/arabic-dialect-lord/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/m3taz-ahmed/ai-globals/arabic-dialect-lord"><img src="https://agentmods.dev/badge/skills/m3taz-ahmed/ai-globals/arabic-dialect-lord.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00049 | $0.01463 |
| Opus 5 | $0.00024 | $0.00732 |
| Sonnet 5 | $0.00010 | $0.00293 |
| Haiku 4.5 | $0.00005 | $0.00146 |
Grade A, and why
arabic-dialect-lord 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 12d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arabic Dialect Lord
[OBJ] Arabic dialect-aware governance for AI coding assistants targeting MENA developers.
Problem
50% AI adoption in MENA, yet 28% of users who tried Arabic responses switched back to English permanently. MSA-only platforms score 24 percentage points lower on Gulf/Egyptian dialect intent detection. Code-switched Gulf/English drops to 51% accuracy on MSA-only models. This is a competitive gap no AI governance tool addresses.
Rules
- [REQ] Dialect detection first. Before generating Arabic output, detect target dialect from: explicit user request, project locale (
ar-SA,ar-EG,ar-AE,ar-PS,ar-MA), or user profile. Default to MSA only when no signal. - [REQ] Dialect registry. Support five dialect families:
gulf(ar-SA, ar-AE, ar-QA, ar-BH, ar-KW, ar-OM) — خليجيegyptian(ar-EG) — مصريlevantine(ar-PS, ar-JO, ar-LB, ar-SY) — شاميmaghrebi(ar-MA, ar-DZ, ar-TN) — مغربيmsa(ar) — فصحى
- [REQ] No dialect mixing. A single response must stay in ONE dialect. Mixing Gulf vocabulary with Egyptian grammar = reject. Flag as
DIALECT_MIX. - [REQ] Code-switching rules. When Arabic+English code-switching is detected (common in MENA dev workflows), preserve technical terms in English (e.g., "API", "deploy", "commit") and wrap in Arabic grammar. Never translate established technical terms to invented Arabic equivalents.
- [REQ] Cultural context. Gulf dialect expects formal business register for client-facing content; Egyptian allows casual register for internal docs. Match register to audience.
- [REQ] RTL layout. Any UI text in Arabic must use RTL (
dir="rtl"). Mixed Arabic/English UI must usedir="auto"per element. Never force LTR on Arabic content. - [REQ] Number formatting. Arabic-Indic digits (٠١٢٣) only when locale explicitly requests; default to Western Arabic numerals (0123) for technical/code content. Currency in SAR/AED uses Western numerals per regional convention.
- [REQ] Date/time. Use Hijri calendar only when explicitly requested (
calendar=islamic); default Gregorian with Arabic month names for dialect output. - [REQ] Tone calibration. Gulf: respectful, indirect, honorific (حضرتك/فضلتك). Egyptian: direct, warm, colloquial (يا باشا/بعد إذنك). Levantine: balanced, polite. MSA: formal, neutral.
- [REQ] Error messages. User-facing error messages must be in the detected dialect. Stack traces/logs stay in English (technical convention). Never translate stack traces.
- [REQ] Documentation. README/CHANGELOG bilingual: Arabic dialect section + English section. Never machine-translate — dialect requires native phrasing.
- [REQ] AI slop detection for Arabic. Reject: unnatural MSA in dialect context, literal translations of English idioms (e.g., "hit the ground running" → "ضرب الأرض وهو يجري" = reject), dialect-inappropriate formality.
- [REQ] Testing. Arabic output must be tested with dialect-native speakers or a dialect classifier. MSA-only QA = insufficient for dialect-tagged output.
- [REQ] Fallback. If dialect confidence < 0.7, fall back to MSA and inform user. Never guess a dialect silently.
- [REQ] Privacy. Dialect preference is PII-adjacent (reveals region/origin). Never log dialect in audit trail without redaction. Store preference as opaque locale code only.
- [PROHIBIT] Generating Arabic in a dialect the user did not request or the system did not detect.
- [PROHIBIT] Mixing dialects within a single response or file.
- [PROHIBIT] Translating established technical terms to invented Arabic equivalents (e.g., "framework" → "إطار عمل" is accepted; "framework" → "هيكلية برمجية تفاعلية" = reject as invented).
- [PROHIBIT] Using Arabic-Indic digits in code samples or technical configuration.
- [PROHIBIT] Machine-translating dialect content. Dialect requires native or fine-tuned generation.
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.
- 12d ago First seen · 86 lines · 49 tokens per session scan A dfebc670bda5
arabic-dialect-lord is a skill published in the GitHub repository m3taz-ahmed/ai-globals (5 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 1,463 once invoked, about $0.0002 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
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
azure-ai-translation-text-py
Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.