Campaign Concepts and Copy
Writes paid-ad campaign concepts and copy from your validated brand profile, and never invents a testimonial, certification or price to make the pitch land.
Overview
Campaign Concepts and Copy is a creative-production skill in the Claude Ads suite. It loads a validated setup/brand profile and objective, then generates materially distinct campaign concepts rather than cosmetic rewrites of the same idea.
What it covers
- Separates factual claims, operator-approved claims and creative hypotheses before writing copy.
- Defines insight, promise, proof, hook, narrative, CTA, objections and platform adaptations per concept.
- Validates copy limits and policy against current platform creative-spec references (Google, Meta, YouTube, LinkedIn, TikTok, Microsoft).
- Returns a versioned creative brief and copy deck inside the run directory.
- Never invents testimonials, certifications, scarcity, prices or regulated claims; human review is required before production.
Part of Claude Ads
This skill is dispatched automatically by the main ads conductor for /ads create
requests. See the full Claude Ads entry for installation.
Installation
This worker skill installs automatically as part of the Claude Ads plugin, there's no separate step for it.
- Install the plugin once, from inside Claude Code:
/plugin marketplace add AgriciDaniel/claude-ads /plugin install claude-ads@ai-marketing-hub-claude-ads - This skill runs on its own whenever the
/adsconductor needs it; you don't call it directly. - See the Claude Ads entry for the full setup and platform list.
Related assets
Frontend Design
Generates distinctive, production-grade UI that avoids generic "AI slop," with bold typography, cohesive color, and precise motion, implemented as real code.
Graphify
Turns a codebase, plus its docs, PDFs, images, and video, into a queryable knowledge graph that a coding agent can traverse instead of grepping raw files, and never guesses silently: every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS so you know what was found versus inferred.
Caveman
Makes your coding agent answer in a stripped down, high signal style that keeps every technical fact and cuts filler, saving output tokens on chat style questions.