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 Marketing

ASecurity

Use when transcreating marketing content while preserving brand voice and conversion intent for campaigns, landing pages, calls to action, and cultural adaptation.

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

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-marketing --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Translating Marketing?

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

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

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

Download Zip
Files
SKILL.md
---
name: translating-marketing
description: Use when transcreating marketing content while preserving brand voice and conversion intent for campaigns, landing pages, calls to action, and cultural adaptation.
---

# Translating Marketing

## Overview

Define the persuasion contract for transcreation. Separate the meaning and evidence that must survive from the creative devices that may change for a target audience.

## Capabilities

- `surface:marketing`
- `transcreation`
- `brand-voice`
- `calls-to-action`

## Input Inspection

Inspect the complete campaign and brief before translation:

- source and target locale/market, audience, channel, placement, format, and campaign objective
- proposition, customer problem, approved offer, benefits, proof, qualifications, legal text, and intended emotional effect
- brand voice, prohibited tones, terminology, visual concept, cultural references, humor, metaphor, and calls to action
- next step after the CTA, funnel stage, landing experience, asset/variant IDs, tracking parameters, and measurement event
- length, layout, audio/video timing, accessibility, platform, and regulatory constraints

Mark absent facts and approvals as unresolved. Do not turn desired positioning into evidence.

## Transcreation Surface

Give `translating-core` a creative brief containing the proposition, invariant facts, target audience, brand voice, desired emotional effect, conversion action, protected elements, and adaptable devices. Installed language specialists own linguistic form and locale mechanics.

Headlines, body copy, taglines, calls to action, captions, and image text are translatable. Metaphors, idioms, wordplay, rhythm, cultural references, and examples may be replaced only when the new device preserves the approved meaning, tone, and conversion intent. This skill does not generate target copy or variants.

## Non-Translatable Elements

Preserve exactly unless the authoritative owner approves a change:

- product and brand names, trademarks, legal names, campaign/asset IDs, analytics events, tracking parameters, URLs, promo codes, and structured field keys
- prices, dates, deadlines, quantities, eligibility, availability, product behavior, outcomes, rankings, awards, testimonials, statistics, and substantiation
- required disclosures, claim qualifications, consent language, and the actual next action in the funnel

Never treat transcreation as permission to invent urgency, scarcity, social proof, guarantees, product capabilities, or a stronger promise.

## Marketing Constraints

- Preserve the proposition, proof relationship, qualification, emotional effect, brand voice, and conversion intent while allowing natural target-market form.
- Keep calls to action accurate to the next user action and campaign objective. A clickier verb is not acceptable if it changes commitment, expectation, or funnel behavior.
- Evaluate cultural references and visuals by audience comprehension, relevance, tone, and message fit. Replace a weak device through core/language routing; do not substitute a stereotype, topical joke, or unrelated local symbol merely because it is recognizable.
- Keep headline, body, CTA, image, landing page, offer, and tracking event coherent as one conversion path.
- Preserve claim qualifiers and disclosures in every variant and placement where required. Short formats do not authorize omission.
- Keep asset and experiment identities stable so target variants remain attributable to the intended campaign.

## Targeted Research

Research only current market facts that materially affect this campaign:

- product and offer availability, eligibility, fees, sign-up behavior, and required local disclosures
- current advertising-platform field/format/policy constraints and applicable market regulation
- audience interpretation of a cultural device, category terminology, search/social language, channel convention, or substantiated local proof

Prefer authoritative product/policy sources and dated target-market evidence. State source and observation date. Research may test resonance or substantiate an approved claim; it cannot create product truth, fabricate performance, or replace the approved brief.

## Authority and Conflict Boundary

Follow explicit user requirements, approved product/campaign facts, core semantic fidelity, and brand/legal constraints before stylistic preference. Product owns product truth and funnel behavior; legal/compliance owns claims and disclosures; brand owns voice and protected identity; analytics owns tracking; campaign leadership selects only among compliant variants.

This skill owns the transcreation brief, invariant/adaptable classification, conversion-path constraints, and marketing QA. `translating-core` owns meaning and target copy; installed language specialists own linguistic and cultural mechanics; `reviewing-translations` owns final review. When a creative request conflicts with approved facts, proof, voice, or conversion intent, name the conflict and retain the approved constraint.

## QA Handoff

Pass the source and target campaign, locale/market, approved brief, claim/proof sheet, brand voice, platform constraints, funnel map, visual manifest, tracking inventory, research evidence, sensitive-claim evidence record, and these checks to `reviewing-translations`:

For every regulated, safety, health, financial, quantified, comparative, guaranteed, or otherwise sensitive claim, require one review artifact produced from the returned target copy: either an exact back-translation into the source language or a recorded rationale mapping each target proposition and qualifier to the approved source claim and evidence. Use the rationale when back-translation would obscure a deliberate transcreation choice. This skill requests and preserves that evidence; it does not generate target copy.

- proposition, benefits, proof, qualifications, offer, facts, and required disclosures preserve semantic parity
- brand voice, emotional effect, and cultural adaptation remain suitable without stereotypes or off-brief tone
- CTA describes the actual next action and supports the stated conversion objective
- headline, body, CTA, image/alt text, landing experience, and localized product surface remain coherent
- names, IDs, URLs, tracking values, prices, deadlines, statistics, testimonials, and claims match approved inputs
- every sensitive claim has a back-translation or recorded proposition-and-qualifier rationale tied to the exact target asset, source claim, and evidence ID
- copy fits verified placement, timing, layout, accessibility, and platform requirements without omitting required meaning

Block release for an invented or unsubstantiated claim, false urgency/scarcity, altered tracking identity, inaccurate CTA, prohibited tone, culturally harmful or irrelevant substitution, missing qualification/disclosure, or target copy that changes conversion intent. Route the exact affected field or asset to its responsible installed skill.

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 →