Audit ad accounts across six platforms
A Claude Code skill runs parallel subagents performing 190 audit checks across ad platforms and produces a prioritized action plan.
Done withClaude Code
- What they did
- The Claude Ads skill is run via one command that launches six parallel subagents. They execute 190 checks (74 on Google, 46 on Meta, plus the rest on YouTube, LinkedIn, TikTok, and Microsoft Ads), apply the 3x Kill Rule to flag campaigns, enforce per-platform budget rules, run compliance checks for housing/credit/finance/healthcare, and pull from 11 industry templates. The user grants ad-account access and executes the command; subagents produce the consolidated output autonomously.
- How it went
- It outputs a single Ads Health Score and revenue-impact-ranked action plan that replaced a $4,000/month agency. No performance metrics or shortfalls are stated.
- Worth knowing
- Free, open-source MIT project with 714 GitHub stars.
Try it yourself with Claude Code
I run ads on [list of platforms, e.g. Google, Meta, LinkedIn]. Using the exports or reports in [folder path], check each account for wasted spend, weak targeting, missing tracking and poor creative performance. Finish with a single prioritized action plan ranked by likely impact, with a short reason for each item. Do not change anything in the accounts; this is read-only.
Source: X · Apr 10, 2026
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
Turn tickets into merged pull requests
Pulls tasks from GitHub Issues or Linear, then runs Claude Code or Codex in isolated Kubernetes pods to carry each one through to a PR.
Run content research and sponsor outreach with Claude computer use
The author tested Claude computer use in Cowork and Claude Code over two days on six workflows including research, sponsor outreach and product listings.
Build and balance a live Telegram RPG
A non-coding PM had Claude Code write a Telegram RPG bot, deploy it over SSH, and run tens of thousands of test fights to rebalance classes.
- Custom agent
Sell services through an agent that takes payment and delivers
An agent runs a transaction flow, creates Stripe checkout links, verifies payment before delivering a service, and asks the owner on Telegram to approve refunds or disputes.
Run voice and chat support assistants with memory
AT&T deploys Gemini-based voice and chat assistants with 60-day memory, reporting 20% more inquiries fully automated.
Run browser-heavy business tasks and trip outfit picks
Commenters use Claude in Chrome for cPanel listings, X growth, testing, outreach and investor research, and to pick trip outfits from grouped clothing tabs.