ads-competitor-research
Skill1 starsChanged 24 days agoMITView on GitHub
Competitor ad research from legal public sources - Meta Ad Library (via the official Ads MCP ads_library_search), Google Ads Transparency Center - covering messaging themes, offers, creative styles, CTA patterns, ad longevity and format trends, turned into differentiated test ideas. Use for "what are competitors running", "spy on", "ad library", "competitor ads".
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- ads-auditSkill
- ads-budgetingSkill
- ads-client-onboardingSkill
- ads-communitySkill
- ads-coreSkill
- ads-creative-analysisSkill
- ads-landing-pageSkill
- ads-optimizationSkill
- ads-portfolioSkill
- ads-reportingSkill
- ads-strategySkill
- ads-trackingSkill
- google-adsSkill
- meta-adsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Do not scrape behind logins, bypass rate limits, or use paid scraping services the user has not approved.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Competitor research
Workflow: workflows/competitor-analysis.md.
Sources (legal, public)
| Source | Access | Covers |
| Meta Ad Library | official MCP ads_library_search (by keyword / Page); or the public site | active ads on Facebook/Instagram, start dates, formats; spend/reach only for political/social-issue ads (and EU) |
| Google Ads Transparency Center | public site (adstransparency.google.com), read in the browser | advertiser's Search/Display/YouTube ads by region |
| Competitor websites/landing pages | browser | offers, proof, forms |
Do not scrape behind logins, bypass rate limits, or use paid scraping services the user has not approved.
What to extract
Per competitor: number of active ads, oldest still-running ad (longevity ≈ likely winner - HEURISTIC, not proof), formats (static/video/carousel, UGC vs polished), hooks, offers (free consult, % off, financing), proof (reviews, years, awards), CTAs, landing page type, geographic signals, seasonality.
Turn it into action
- Themes table: what most competitors say (table stakes) vs what nobody says (differentiation space).
- 3-5 test ideas for the client, each as a creative brief with a hypothesis, in the client's own voice and offer.
- Never copy competitor ads verbatim or imitate their branding. Inspiration only.
- Label claims: "running 140+ days" is observed; "this is their best ad" is inference.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.