agentleFS
Sign inStart free
h9-tech9-tec/arabic-ai-atlas/skills/arabic-dialect-prompts/SKILL.md

arabic-dialect-prompts

Skill43 starsChanged 29 days agoMITView on GitHub

Use when writing system prompts or few-shot examples for an Arabic-speaking agent in a specific dialect, or when a model answers in formal Arabic (MSA) instead of the requested dialect.

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start the system prompt from that row's example line and adapt tone to the product.

    line 13
  2. Distinctive:

    Add 2 to 3 few-shot exchanges written in the dialect.

    line 14
  3. Very specific:

    Test with a few real user messages.

    line 16
  4. Very specific:

    If the user also needs a model with good coverage of that dialect, call recommend(task="chat", type="llm", dialect="<code>"), or …

    line 20
  5. Distinctive:

    Write the system prompt itself in the target dialect.

    line 24
  6. Distinctive:

    Keep user-facing safety and legal text in clear MSA when accuracy matters more than tone.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Arabic Dialect Prompts

Reference for prompting LLMs in a specific Arabic dialect. The table in ${CLAUDE_PLUGIN_ROOT}/skills/arabic-dialect-prompts/dialects.md covers the 10 dialect codes used across the atlas (msa, egy, gulf, lev, magh, iraqi, sudanese, yemeni, classical, mixed), each with register notes and an example system-prompt line in Arabic.

Procedure

  1. Identify the dialect (ask if unclear) and read its row in dialects.md.
  2. Start the system prompt from that row's example line and adapt tone to the product.
  3. Add 2 to 3 few-shot exchanges written in the dialect. Examples teach the dialect better than instructions alone.
  4. State explicitly what to avoid, for example «لا تستخدم الفصحى».
  5. Test with a few real user messages; if replies drift toward MSA, see "Common failure" in dialects.md.

Picking a model

If the user also needs a model with good coverage of that dialect, call recommend(task="chat", type="llm", dialect="<code>"), or search(query="<dialect> dialect", type="llm"). Report only what the atlas returns.

Rules

  • Write the system prompt itself in the target dialect; an English prompt pulls output toward MSA or English.
  • Dialect support in models is uneven; say so for sudanese, yemeni and magh.
  • Keep user-facing safety and legal text in clear MSA when accuracy matters more than tone.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free