Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Translating Rtl

ASecurity

Use when applying right-to-left script and bidirectional UI rules for Arabic, Hebrew, Persian, Urdu, or mixed RTL/LTR product content.

4 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgoexpress

Works with

cli

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add BrunoMiguens/translating-products-skill --skill translating-rtl --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Translating Rtl?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Translating Rtl
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brunomiguens-translating-rtl/badge)](https://www.skillsdirectory.com/skills/brunomiguens-translating-rtl)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: translating-rtl
description: Use when applying right-to-left script and bidirectional UI rules for Arabic, Hebrew, Persian, Urdu, or mixed RTL/LTR product content.
---

# Translating RTL

## Overview

Revise and validate script direction, layout, and bidirectional behavior after `translating-core` drafts the copy. Preserve meaning, glossary decisions, placeholders, markup, identifiers, and protected values exactly.

This skill owns RTL mechanics. It does not own Arabic, Hebrew, Persian, Urdu, or other language wording. Route wording and grammar to the installed language specialist.

## Capabilities

- `script:rtl`
- `bidi`
- `mirroring`
- `mixed-direction`

## Entry Contract

Require the approved project context, core draft, product surface, and an explicit target locale or variant. A script name such as “Arabic” is not a locale. If the locale is missing, return one focused question through the orchestrator and withhold target copy.

Use project context, glossary, protected terms, and pinned knowledge first. Research only a specific unresolved current platform behavior or market convention; record the source and decision through the orchestrator. Never browse for routine grammar or every string, and never install or download another skill at runtime.

## Inspect Directional Runs

For each string, identify:

- the base paragraph direction and every embedded LTR run: names, product terms, URLs, email, code, reference IDs, versions, and measurements
- placeholders and runtime values, including numeral system, decimal/grouping rules, currency ownership, and expected examples
- punctuation at run boundaries and whether copying, selection, speech, or search must preserve the raw value
- the rendering surface and its native isolation, formatting, accessibility, and layout primitives

Do not change words, currency placement, punctuation style, or numeral conventions as a script-level “fix.” Return linguistic questions to the relevant language specialist.

## Apply Mechanics

- Use the locale or content to establish base direction. Do not reverse strings or reorder source data manually.
- Isolate embedded runs with the surface's semantic or native mechanism, such as `<bdi>` for user-supplied web text. Preserve the underlying value.
- Prefer locale-aware number and currency formatting. Treat an opaque identifier as verbatim data, not a number to localize.
- Use logical start/end properties for spacing, alignment, constraints, and positioning.
- Mirror only directional meaning: navigation arrows, progress, or movement when the interaction reverses. Do not mirror logos, text, media controls, clocks, maps, charts, or culturally fixed symbols without product evidence.
- Keep visible and spoken values consistent. Give decorative directional icons no duplicate accessible name; verify reading and focus order separately from visual order.
- Add Unicode directional controls only when a reproduced ordering defect remains after native semantics are applied and the exact control boundary is justified. Record code points, reason, surface, and copy/paste result. Never add controls by guesswork or hide them inside approved wording.

## Product UI and Long Form

For product UI, test compact labels, icons, lists, forms, tables, selection, truncation, focus movement, and responsive or device layouts. Keep actions and state understandable without relying on visual placement alone.

For long-form content, preserve paragraph direction, headings, lists, quotations, code blocks, links, footnotes, and inline LTR spans. Avoid wrapping an entire document in a direction override when blocks have distinct semantics.

## Common Literal and Layout Failures

- reversing characters or arrays to make text “look RTL”
- translating or reformatting IDs, URLs, placeholders, or protected product terms
- mirroring every icon or failing to mirror directional navigation
- forcing Arabic or Hebrew wording changes during the mechanics pass
- using physical left/right properties where logical start/end expresses intent
- inserting directional marks pre-emptively, causing invisible copy/paste or maintenance defects
- assuming visual order proves screen-reader, keyboard, or focus order

## QA Handoff

Pass the annotated runs, chosen isolation mechanisms, unchanged core draft, surfaces, and evidence to `reviewing-translations`. Verify:

- placeholders, glossary decisions, protected values, links, code, and raw copied identifiers are unchanged
- mixed names, numerals, currency, punctuation, URLs, and IDs render in the intended order at wrap boundaries
- only directionally meaningful assets mirror and layout uses logical start/end behavior
- keyboard, selection, copy/paste, screen-reader reading order, announcements, and focus order remain coherent
- narrow and wide screens, text scaling, supported browsers, operating systems, and representative devices expose no clipping or reordered content
- any directional controls have a reproduced defect, explicit code-point inventory, and before/after device evidence

Block the affected segment on unresolved mixed-run order, corrupted raw values, unjustified controls, incorrect mirroring, inaccessible focus/reading order, or a wording change introduced by this skill. Route the smallest failure to the responsible surface or language specialist; do not regenerate unrelated copy.

Attribution

BrunoMiguensBrunoMiguens
View sourceMore from BrunoMiguens →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →