メニュー
Per-language calibration anchors for detecting AI-slop and translationese in Arabic (ar) target text — auto-loads alongside content-locale-humanize when the target language is Arabic.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Turn raw data into a decision-ready report a human actually reads — structured by the Minto Pyramid (answer first), every number traced to the data, the right chart for each question, and delivered as a self-contained HTML document that opens in any browser and prints to clean PDF with no dependencies. Format-flexible; grounded, never fabricated.
How modern applicant tracking systems rank resumes in 2026 and how to tailor a resume per job posting so it clears them — keyword strategy grounded in the candidate's real experience, job-title placement, coverage targets, parser-safe formatting, and the anti-stuffing rules that current ATS actively penalize. Truthful tailoring only.
The dimensions of a deep code review — correctness, security, concurrency, performance, design/maintainability, tests — what each lens hunts for, and the adversarial verification discipline that keeps a multi-reviewer pass from multiplying false positives. Consensus is not correctness; every finding must be refuted before it is trusted.
Translate and localize documents, code comments, UI strings, and structured content while preserving formatting, adapting to domain-specific terminology, and maintaining consistency across large files via batching.
Write a cover letter that a hiring manager actually reads — grounded in the candidate's real experience, tailored to the specific posting and company, structured for a 30-second skim, and free of the generic AI-template phrasing that gets letters discarded. Truthful, specific, and human.
Operate the local computer's native UI — macOS, Linux, or Windows — via the desktop-automation MCP server. Covers OS accessibility / screen-recording permissions, pixel-anchor targeting (no semantic UI tree), region-capture discipline under the MCP response cap, window focus and multi-monitor handling, keyboard / mouse / clipboard sequencing, and the safety boundary around destructive desktop actions and screen-lock / biometric bypass. Activate when the user wants to drive a native desktop app or the OS shell at the GUI layer. Pairs with the device:operator agent which carries the shared snapshot → verify → record discipline; this skill carries the desktop-specific tooling and rules and pulls the device-computer capability automatically.
| name | content-locale-humanize-ar |
| title | Arabic Native-Fluency Calibration |
| description | Per-language calibration anchors for detecting AI-slop and translationese in Arabic (ar) target text — auto-loads alongside content-locale-humanize when the target language is Arabic. |
| license | Apache-2.0 |
| compatibility | Extends content-locale-humanize's AI-Slop & Translationese dimension. Load both together — this file has no rubric of its own. |
| domains | content |
| rules | ["content(arabic)","match(\\bar-(SA|EG|AE)\\b)","match(\\bArabic\\b)","match(العربية)","semantic(check if this Arabic translation sounds native)","semantic(eliminate translationese from this Arabic text)"] |
Sourced calibration anchors for Arabic, feeding content-locale-humanize's AI-Slop & Translationese dimension. This is a calibration aid, not the checklist — reason natively beyond it (see the core skill's "why structure, not word lists" section).
Sourcing confidence: the weakest of any language checked. Most published Arabic AI-word lists are direct translations of the English canon, not independently observed findings — treat any finding here as a starting hypothesis, not a confirmed tell.
Stock phrases: "في الختام" ("in conclusion"), "لا شك أن" ("there's no doubt that").
Beyond this thin list, lean harder on the structural checks in content-locale-humanize (interference, connector density, rhythm clustering) than on vocabulary matching — the vocabulary evidence for Arabic specifically is not solid.
One Al Jazeera piece naming a handful of phrases; otherwise mostly translated-from-English lists.
