Paid Media Optimization
Diagnoses underperforming campaigns from causal evidence, not a single metric in isolation, and refuses to permanently delete anything, offering pause or archive instead.
Overview
Paid Media Optimization is the account-mutation skill behind /ads optimize in the
Claude Ads suite, defaulting to --draft like campaign launches.
What it covers
- Loads the latest normalized snapshot, prior decisions, monitoring results, experiment state and platform capability manifest.
- Identifies the decision and causal evidence first; never optimizes a metric in isolation.
- Compares no-change, experiment and mutation options, including learning-phase and opportunity-cost effects.
- Refuses permanent deletion of campaigns, ad groups, ads or audiences; offers pause, archive, label or backup/export instead.
- Requires a search terms report and overblocking review before any search-term or negative-keyword action.
Part of Claude Ads
This skill is dispatched automatically by the main ads conductor for /ads optimize
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.