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 khalilbenaz/claude-skills-collection --skill darija-translatorgit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/darija-translator)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/darija-translator"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/darija-translator/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/khalilbenaz/claude-skills-collection/darija-translator"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/darija-translator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.01635 |
| Opus 5 | $0.00044 | $0.00817 |
| Sonnet 5 | $0.00018 | $0.00327 |
| Haiku 4.5 | $0.00009 | $0.00163 |
Grade A, and why
darija-translator 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 9d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Darija Translator
Workflow en étapes
1. Identifier la direction et le registre
| Direction | Exemples déclencheurs |
|---|---|
| FR/EN → Darija | "comment dit-on X en darija ?", "traduis en marocain" |
| Darija → FR/EN | "qu'est-ce que ça veut dire X", "c'est quoi X en français" |
| Darija → Darija | normalisation registre, correction |
Registre à demander ou inférer du contexte :
formel— courriers admin, prise de parole officiellecourant— conversation quotidienne, WhatsApp famille/collèguesfamilier— entre amis proches, jeunes, code-switching FR+darijatechnique— métier (santé, droit, informatique, finance)
2. Conventions de translittération (système numérique marocain)
| Lettre arabe | Code Latin | Exemple |
|---|---|---|
| ع | 3 | 3andek = عندك (tu as) |
| ح | 7 | 7it = حيت (parce que) |
| خ | 5 ou kh | 5obz / khobz = خبز (pain) |
| ق | 9 | 9al = قال (il a dit) |
| غ | 8 ou gh | 8alyan / ghalyan = غالي (cher) |
| ش | ch | chkon = شكون (qui) |
| ج | j | juj = جوج (deux) |
Les deux conventions (5/kh, 8/gh) coexistent — préciser ou utiliser la plus lisible selon l'audience.
3. Format de sortie systématique
Pour chaque traduction, fournir les trois lignes :
[Écriture arabe] : كيداير؟
[Translittération]: Ki dayr?
[Prononciation] : /ki dɛr/ ← si demandé ou ambiguïté
[FR/EN] : Comment tu vas ? (familier)
Exemple complet — "Bonjour, comment allez-vous ?" (formel) :
الدارجة (arabe) : لباس عليكم؟
Translittération : L-bas 3likoum?
Français : Vous allez bien ? / Bonjour, comment allez-vous ?
Note : formule polie, variante féminine inchangée
4. Adaptation culturelle (pas de traduction mot à mot)
Critères de décision :
- L'expression source a-t-elle un équivalent idiomatique en darija ? → utiliser cet équivalent, pas une calque littérale.
- Y a-t-il une connotation religieuse implicite ? → intégrer naturellement (inchallah, hamdullah, bslama…) si le registre le permet.
- Le contexte est-il code-switching FR+darija ? → reproduire le même mélange dans la sortie.
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.
- 9d ago First seen · 128 lines · 88 tokens per session scan A a1cfa1662fcb
darija-translator is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 18d ago), licensed MIT. It adds 88 tokens to every session and 1,635 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
bilingual-doc-sync
Parallel geführte Sprachfassungen eines Dokuments (Paper DE/EN, README + READMEde, SKILL.md + SKILL.en.md, Website-Texte) synchron halten: fehlende Fassung nachziehen, Abschnitts-Parallelität prüfen, Divergenzen beheben — mit klarer Leitsprache-Regel und kontrolliertem Rücktransfer, wenn die Nebenfassung etwas besser…
pptx-translator
This skill should be used when the user needs to translate PowerPoint presentations (.pptx) between languages, preserving formatting and layout. Supports parallel slide-by-slide translation with per-slide validation and retry. Default languages are Portuguese and English but any language pair is supported.
ai-voice-design
Concevez et générez des voix IA pour vos vidéos en utilisant ElevenLabs ou Qwen3-TTS, avec clonage vocal, design par description, et synchronisation lip-sync. Use when: Créer une voix de marque - Définir le ton vocal pour une campagne; Cloner une voix existante - Reproduire une voix avec autorisation; Designer une…
voice-localization
Scale your brand voice across multiple languages using AI voice synthesis, maintaining consistent character and quality for global content. Use when: Expanding video content to new language markets; Creating multilingual courses or training; Localizing ads and marketing videos; Dubbing existing content for…
i18n-localization
Internationalization and localization for web applications. Handles next-intl, react-intl, ICU MessageFormat, RTL layouts, and dynamic locale loading.
frappe-core-translation
Use when implementing translations/i18n in Frappe v14-v16 apps. Covers () in Python, () in JavaScript, CSV translation files, bench commands, string extraction rules, lazy translation lt(), PO/MO files [v15+], RTL support, and custom app translations. Prevents common mistakes with f-strings, concatenation, and…