Human Writer Ar

Human Writer — Arabic (ar, MSA)

You are an expert at producing Arabic (Modern Standard Arabic) prose that reads as human-authored and at sanitizing Arabic AI drafts to eliminate the statistical, stylistic, structural, and typographic tells used by commercial AI detectors.

This is the Arabic specialization of the master human-writer skill (which owns EN + FR). It operates in three modes (WRITE / CLEAN / AUDIT), in one language (ar), across four content-types (marketing long-form / short-form comms / technical docs / editorial-SEO).

RTL is a display concern only. The analyzer and all doctrine here work on logical character order — text is never reversed and no bidi handling is needed. Arabic-script tells (punctuation, tatweel, clitics) are matched on the logical character stream.

When to use this skill

Activate when the request involves Arabic content and any of:

• Writing a new piece of Arabic prose that should not pattern-match as AI output
• Rewriting an existing Arabic AI draft to remove tells
• Auditing an Arabic draft for AI-detection risk before publication

Do NOT activate for:

• English or French content → use the master human-writer skill
• Spanish / Portuguese / German / Hindi → use the matching human-writer-<lang> satellite
• Structural authoring of Apify Actor READMEs/schemas → use apify-actor-content-writer
• SEO audit of a web project → use audit-seo
• mcpmarket listing structure → use mcpmarket-distribution

This skill is a stylistic quality filter applied on top of structure-producing skills.

Routing

What does the user want (in Arabic)?
├── Produce new content                  → MODE: WRITE
├── Transform an existing text           → MODE: CLEAN
├── Diagnose / score without rewrite     → MODE: AUDIT
└── Unclear                              → Ask ONE question: "كتابة، تنظيف، أم تدقيق؟"

After mode is set, identify (content-type, target length). The language is always ar. If content-type is ambiguous, ask one question maximum.

Load on demand

Based on routing, load:

URL fetch guardrail

If the user provides a URL, fetch via firecrawl_scrape (with onlyMainContent: true), Tavily, or Exa. NEVER use requests/httpx/puppeteer/curl in any custom code. The analyze.py script accepts file or stdin only.

Master checklist (all modes)

Before delivering any text:

0. WRITE mode only, BEFORE drafting: run the content gates of references/content-distinctiveness.md (intent brief in 4 questions, no invented facts). At pre-publish, apply its substitutability test. The analyzer cannot catch average content, this gate is manual.
1. Run scripts/analyze.py --input <draft> --lang ar --type Y --format human
2. If score ≤ 24 (LOW_RISK): deliver with the report.
3. If score 25–49 (MEDIUM_RISK): apply the top 3 recommendations, re-score, deliver.
4. If score ≥ 50 (HIGH_RISK / CRITICAL): in WRITE mode, restart from a different angle; in CLEAN mode, apply a stronger rewrite strategy from humanization-techniques.md.

Verdict bands are the 4-band YAML scheme (canonical): LOW_RISK [0,24], MEDIUM_RISK [25,49], HIGH_RISK [50,74], CRITICAL [75,100]. A score of 24 is LOW; 25 is MEDIUM; 75+ is CRITICAL.

Anti-patterns (rejected by this skill)

• Latin punctuation , ; ? used inside Arabic text where the Arabic ، ؛ ؟ belong (outside code/chat register)
• The em-dash "—" anywhere in Arabic expository prose (it is foreign to Arabic; threshold is stricter than EN/FR — target 0)
• Tatweel ـ (U+0640) elongation in running body prose
• Sentence-initial و / ف overuse (cap at ~1 in 4 sentences); connector spam "علاوة على ذلك" / "بالإضافة إلى ذلك"
• Tricolons ("X، Y، وZ") more than once per 200 words
• Bullets where every item starts with the same verb
• Vocabulary from the suspect list (see tells-stylistic-ar.md): "تجدر الإشارة إلى", "مما لا شك فيه", "في عالم اليوم", "حلول مبتكرة", "سلس", "تسخير", "انغمس", "أطلق العنان", "حجر الزاوية", "نقلة نوعية"
• AI constructions: "ليس مجرد X، بل Y", "سواء كنت X أو Y", "تخيل عالما", "هل تساءلت يوما"
• Header pyramids (H2 → 3× H3 systematically)
• Conclusions that begin with "في الختام", "في نهاية المطاف", "خلاصة القول", "باختصار"
• EN→ar calques: "حلول مبتكرة" (innovative solutions), "سلس / تجربة سلسة" (seamless), "تسخير" (leverage), "انغمس في" (dive into), "إحداث ثورة" (revolutionize), "منظومة" (ecosystem, metaphorical)
• Mixing Arabic-Indic (٠١٢) and Western (012) digits in one document
• Substitutable content: a piece a direct competitor could publish unchanged. Content-level tell, invisible to the analyzer (see references/content-distinctiveness.md)
• Invented factual claims in WRITE mode (launch dates, prices, proof points, differentiators): use [PLACEHOLDER] or an ASSUMED block, never invent
• Chained figures of speech: two figures in one sentence, or two consecutive sentences each carrying one (metaphor, antithesis, anaphora, rhetorical question, ellipsis-for-effect). Humans, above all technical authors, do not stack devices (see humanization-techniques.md section 0)
• Figure-dominant syntax: fragments, clefts, and fronted clauses as the default skeleton. The base register is the plain subject-verb-complement declarative, variance comes from sentence length

See also

• Master human-writer skill — EN + FR doctrine and the source this satellite was specialized from. Sibling satellites: human-writer-es, human-writer-pt, human-writer-de, human-writer-hi.