Skip to content
Get packs

Paid Media Optimization

Diagnose ad campaigns and draft evidence-based optimizations, applying changes only when explicitly enabled.

Source Download skill
Repository
AgriciDaniel/claude-ads
Stars
10,667
Licence
MIT
Files
1 file

What it does

When installed, this skill makes an AI agent handle paid advertising work more carefully. It reviews campaign data, recent decisions, experiment status and cost constraints before suggesting changes such as budget moves, bid changes, pausing ads, or rotating creatives. By default it only drafts recommendations with confidence levels and success measures; it is designed to apply changes to a live account only when that exact operation is explicitly enabled and the remote account still matches the draft. It also refuses permanent deletion of campaigns or other account objects and offers reversible alternatives like pausing or archiving.

Great for

  • Marketers managing paid search or social campaigns who want structured, evidence-based optimization suggestions
  • Analysts who want ranked recommendations with stated confidence rather than rule-of-thumb CPA or ROAS changes
  • Teams that want a rollback and audit trail before any account change is made

Skip it if

  • Anyone expecting the agent to change live ad spend automatically without reviewing drafts: the skill defaults to draft mode and the file does not show how apply mode is enabled, so account changes are not safe to assume
  • Users needing permanent campaign deletion: the skill explicitly refuses it, citing it as outside the supported contract
  • Situations lacking a search terms report or conversion data: the skill will request that evidence rather than invent negative keywords

Try asking

  • “Review last month's campaign performance and draft budget reallocation recommendations with confidence levels”
  • “Analyze my search terms report and tell me which terms need negative keywords, with business-relevance checks”
  • “Suggest whether to pause or archive underperforming ads, leaving a retention review date”
  • “Draft a creative rotation plan to improve CPA without changing anything live”
Step-by-step guide: how to use Paid Media OptimizationInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    ads-optimize.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip ads-optimize.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip ads-optimize.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Keep the agent in --draft mode and review every recommendation before enabling any mutation
  • Provide conversion lag, economics and experiment history so the recommendations account for learning and opportunity cost
  • Ask for reversible actions such as pausing or archiving, and set a later review date for each

What's inside

  • SKILL.md

Redistributed unmodified from AgriciDaniel/claude-ads under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.