Skip to content
Get packs

Paid Ad Monitoring

Checks paid-ad accounts for pacing, performance drops, tracking and policy issues without changing them.

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

What it does

Once installed, the agent can review snapshots of paid advertising accounts (such as daily or weekly exports) and explain what changed, separating real problems from normal noise like learning periods, seasonality, or reporting delays. It checks budget pacing, delivery, conversion quality, cost economics, creative fatigue, tracking health, and policy status, then reports observations, confidence levels, likely causes, and suggested next steps. It is designed to observe only: it states it should not modify the account, and it saves a versioned monitoring record that can be linked to follow-up tasks.

Great for

  • Marketers who run paid campaigns and want a structured daily or weekly health check
  • Analysts reviewing whether a spend or conversion change is meaningful or just noise
  • Teams verifying a campaign after launch or investigating an anomaly

Skip it if

  • Teams expecting the agent to automatically change bids, budgets or ads: the skill is written to avoid mutating accounts, and the reason is that it is only for monitoring and analysis
  • Anyone without normalized, comparable data exports: the instructions require compatible account, timezone, currency and attribution definitions, so messy or mismatched data will produce weak conclusions

Try asking

  • “Run a daily pacing and delivery check on last week's snapshots and flag anything unexplained”
  • “Compare this week's campaign performance to last week and tell me if the cost-per-conversion change is real or noise”
  • “Check whether tracking or policy issues appeared in the account since the last export”
  • “Verify that the campaigns we launched yesterday are delivering as expected”
Step-by-step guide: how to use Paid Ad MonitoringInstall, 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-monitor.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

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

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip ads-monitor.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

  • Provide two or more snapshots covering comparable periods, with the same currency and timezone, so comparisons are valid
  • Tell the agent about planned changes or known seasonality so it can separate them from anomalies
  • Review the agent's confidence levels; it is instructed to say when evidence cannot distinguish noise from a real change

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.