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
  • Authors
  • 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.

ProTermsPrivacyRefunds
Back to skills

Accurate Format Preserving Translation

ASecurity

Translate text accurately — preserve formatting, handle plurals, and adapt tone per locale.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgoexpressapi

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill accurate-format-preserving-translation --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Accurate Format Preserving Translation?

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

Security grade badge for Accurate Format Preserving Translation
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-accurate-format-preserving-translation/badge)](https://www.skillsdirectory.com/skills/rondoflow-accurate-format-preserving-translation)

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

Download with Pro
Files
SKILL.md
---
name: accurate-format-preserving-translation
description: "Translate text accurately — preserve formatting, handle plurals, and adapt tone per locale."
category: "Content & Writing"
author: community
version: "1.0.0"
icon: pencil
---

# Translate

Master accurate translation that preserves meaning, formatting, and cultural context.

## Formatting Preservation
- Never translate content inside code blocks, HTML tags, or markdown syntax
- Preserve placeholders like `{name}`, `{{variable}}`, `%s`, `$1` exactly as-is
- Keep markdown structure intact: headers, links, bold/italic formatting
- Maintain JSON/XML structure and keys — translate only values where appropriate

## Content Rules
- Don't translate: proper nouns, brand names, technical terms, URLs, email addresses
- Don't translate: code snippets, CSS classes, API endpoints, file extensions
- Preserve numbers, dates, and IDs in their original format unless locale conversion needed
- Keep consistent terminology throughout — create a glossary for repeated terms

## Language-Specific Handling
- **Plurals**: Use correct plural forms per target language rules (not English patterns)
- **Gender**: Ensure noun-adjective agreement in gendered languages (Spanish/French/German)
- **Formality**: Choose appropriate register (tu/vous, tú/usted, du/Sie) based on context
- **RTL languages**: Consider text direction for Arabic/Hebrew but keep LTR elements (URLs, numbers)

## Cultural Adaptation
- Adapt idioms and expressions rather than literal translation
- Convert units when culturally appropriate (miles↔km, Fahrenheit↔Celsius)
- Adjust date formats to locale standards (MM/DD vs DD/MM vs DD.MM)
- Use local currency symbols and number formatting (, vs . for decimals)

## Context Awareness
- Disambiguate based on context: "bank" (financial vs river), "mouse" (animal vs computer)
- Maintain document tone: formal business vs casual blog vs technical manual
- Consider target audience: children's content vs academic paper vs marketing copy
- Preserve original intent and emotional nuance, not just literal meaning

## Quality Control
- Read full context before translating to understand meaning
- Check that translated text flows naturally in target language
- Verify all formatting elements remain functional after translation
- Ensure consistent voice and terminology across the entire document

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
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".

1074701 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', ...

693621 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.

691 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 →