
Competitor Ad Intelligence
Analyze competitors' Meta and Google ads and produce a strategic teardown with counter-plays
- Repository
- github/awesome-copilot
- Stars
- 40,703
- Licence
- MIT
- Files
- 1 file
What it does
Once installed, the agent can research a competitor's publicly visible paid ads on Meta (Facebook/Instagram) and Google, using web search and public ad libraries. It groups the ads by hook type, format and call-to-action, then checks the landing pages they point to and summarizes the messaging bets, weak spots and possible counter-ads. The output is a structured strategy write-up rather than a raw list of ads.
Great for
- Marketing teams preparing a new paid campaign who want evidence of what competitors are already running
- Founders or growth leads benchmarking a competitor's ad messaging and landing pages
- Creative strategists looking for new angles to test
Skip it if
- Organic or SEO competitor research, which the skill explicitly excludes; it will not handle that well by design
- Scraping at scale: the skill itself notes Meta scraping tools are unreliable and relies on web search, so results may be incomplete or stale
- Using competitor ad copy directly in your own ads, which can raise trademark or copyright concerns
Try asking
- “What ads is apollo.io running on Meta right now? Give me a teardown.”
- “Reverse-engineer clay.run's paid funnel and their landing page message match.”
- “Find ad angles we haven't tried, based on what our two main competitors are running on Google.”
- “Which hooks and formats dominate our category on Meta and Google?”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
competitor-ad-intelligence.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip competitor-ad-intelligence.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip competitor-ad-intelligence.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 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 competitor domains and your own product category up front so the hook and positioning analysis is framed correctly.
- Choose Standard depth for a quick scan; Deep adds historical comparison, funnel reconstruction and counter-plays.
- Treat the output as a starting hypothesis and verify key ads directly in the Meta Ad Library or Google Ads Transparency Center, since web-search-based collection can miss or misdate ads.
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.