Skip to content
Get packs

Paid Advertising Audit

Runs a structured, evidence-cited audit across ad platforms and writes a JSON bundle plus report.

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

What it does

This skill teaches an AI agent to audit paid advertising accounts (such as Google, Meta, LinkedIn, TikTok and others) from exports, screenshots, manual metrics or authenticated reads. The agent first builds a versioned JSON audit bundle, scores platforms with a deterministic process, and then writes a readable report, action plan and measurement plan. It is strict about coverage: if a platform's data or worker is missing, the audit is marked partial or insufficient rather than claiming a complete result.

Great for

  • Marketing managers reviewing paid media accounts across several ad platforms
  • Agencies or analysts who want a repeatable, source-cited audit format
  • Teams that need to know which data gaps limit an audit's conclusions

Skip it if

  • Making live changes to ad accounts: the skill produces drafts of proposed mutations, not executed edits, and the reasoning is only as good as the supplied data
  • Legal or regulatory compliance sign-off: it flags regulatory exposure but is not a substitute for a qualified advisor
  • Accounts whose data you cannot share with an AI tool, since exports and metrics are processed by the agent

Try asking

  • “Run a full paid-advertising audit across our Google and Meta accounts using these CSV exports.”
  • “Audit our LinkedIn and TikTok spend and tell me which findings are supported by data and which are missing.”
  • “Check our conversion tracking setup and list the prioritized risks and opportunities.”
  • “Produce a report.md and action-plan for last quarter's ad spend, noting any platforms with insufficient evidence.”
Step-by-step guide: how to use Paid Advertising AuditInstall, 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-audit.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

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

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip ads-audit.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 clean exports with dates, currency and timezone so the manifest is accurate.
  • Expect a partial result if any requested platform fails authentication; check the missing-data list before acting on the report.
  • Treat proposed mutations as drafts and review them yourself before making changes in any ad account.

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.