Paid Media Setup
Sets up the client, brand and guardrail profile every other Claude Ads skill reads from, and refuses to ever store your API keys or secrets in it.
Overview
Paid Media Setup is the onboarding skill behind /ads setup in the
Claude Ads suite, creating the profile every other skill
in the plugin reads from.
What it covers
- Collects business model, offer, geography, regulated categories, objective, conversion taxonomy, economics and active platforms.
- Records data-source type and whether credentials are present, but never stores credential values, cookies, tokens or raw exports.
- Creates and validates a
data-lifecycle.json(classification, retention, access roles, deletion method) before persisting anything. - Declares mutation authority, approvers, budget/policy ceilings and rollback owner up front.
- Refuses
curl | bash-style remote installs and refuses to store API keys/tokens in the profile, only presence plus an environment/keychain reference.
Part of Claude Ads
This skill is dispatched automatically by the main ads conductor for /ads setup
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 is usually the first skill you run: call
/ads setupyourself right after installing the plugin to create your profile. - 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.