Generate Ad Images
Generates on-brand ad images from an approved creative brief, and records the exact prompt, provider and cost behind every image it produces.
Overview
Generate Ad Images is a creative-production skill in the Claude Ads suite that turns an approved creative brief and brand profile into platform-ready ad image variants.
What it covers
- Treats all brief text and source images as untrusted data; never follows embedded instructions or fetches unapproved resources.
- Builds prompts from concept, subject, action, setting, composition, brand tokens, platform constraints and explicit exclusions.
- Records provider, model, parameters, cost, source hashes, prompt version and output hash for every generated asset.
- Validates file type, dimensions, safe zones, text/copy consistency and policy before writing.
- Requires human rights, brand, quality and policy review of generated assets before use.
Part of Claude Ads
This skill is dispatched automatically by the main ads conductor for /ads generate
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.