Skip to content
Get packs

Ad Campaign Analyzer

Turns ad performance data into clear cut, scale, and budget-reallocation decisions

Source Download skill
Repository
github/awesome-copilot
Stars
40,703
Licence
MIT
Files
1 file

What it does

Once installed, when you share ad campaign exports or a pasted performance table, the agent reviews your Google, Meta, or LinkedIn results and flags wasted spend, winning ads and keywords, and whether A/B test differences are statistically meaningful. It then recommends what to pause, scale, or test next, and can propose a budget split across channels. It works only from the data you give it, with no connection to your ad accounts.

Great for

  • Founders or small teams running paid ads who want a second opinion on a dashboard
  • Marketers who need a quick diagnostic of which campaigns to cut or scale
  • Anyone deciding how to split a fixed monthly ad budget across channels

Skip it if

  • Campaign planning or creative generation with no performance data, since the skill is designed to trigger only when results are provided
  • High-stakes budget decisions made without checking the math yourself, because benchmarks and thresholds are generic rules of thumb rather than your industry's real figures
  • Small samples: the skill's own minimums (100 clicks or 30 conversions per variant) mean early results may just be noise

Try asking

  • “Analyze my Google and Meta Ads CSV from last month and tell me what to cut”
  • “Where am I wasting ad spend? Here is my campaign table for the last 30 days”
  • “I have $5,000/month for ads. Given these results, how should I split it across channels?”
  • “Is the difference between these two ad variants statistically significant? Here are the clicks and conversions”
Step-by-step guide: how to use Ad Campaign AnalyzerInstall, 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.

    ad-campaign-analyzer.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip ad-campaign-analyzer.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip ad-campaign-analyzer.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

  • Include the date range, monthly budget, and your target CPA or ROAS so the benchmarks are anchored to your goals rather than generic averages.
  • Share funnel data (MQL, SQL, close rates, deal size) if you want channel costs adjusted for lead quality, not just cost per conversion.
  • Treat recommendations as hypotheses: check them against your own dashboard and sample sizes before moving real budget.

What's inside

  • SKILL.md

Redistributed unmodified from github/awesome-copilot 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.