ads-landing-page
Skill1 starsChanged 24 days agoMITView on GitHub
Evaluates the full path from ad to offer to landing page to form/call to follow-up - message match, CTA, trust, speed, mobile UX, form friction, offer clarity and tracking - and recommends fixes ranked by expected impact on conversion rate. Use for "landing page", "why don't clicks convert", "CVR is low", "review the page the ads send to".
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-competitor-researchSkill
- ads-coreSkill
- ads-creative-analysisSkill
- ads-optimizationSkill
- ads-portfolioSkill
- ads-reportingSkill
- ads-strategySkill
- ads-trackingSkill
- google-adsSkill
- meta-adsSkill
The file
Files
Landing page and conversion path
AD -> OFFER -> LANDING PAGE -> FORM / CALL -> FOLLOW-UPA low conversion rate with healthy CTR is almost never a targeting problem.
Gather
- The ads' final URLs (with UTMs) from the platform; open each in the browser (mobile viewport first).
- Page speed: PageSpeed Insights / CrUX if a connector is available; otherwise note load time observed.
- The CRM/follow-up process from the profile (
crm) or by asking: speed to lead, who calls back, hours.
Evaluate (score each 1-5, with evidence)
| Area | Questions |
| Message match | Does the headline repeat the ad's promise/keyword/location? Same offer, same words? |
| Offer clarity | Is it obvious what you get, what it costs (or that it is free), and what happens next? |
| CTA | One primary action above the fold; button text says the outcome ("Book my free design consult") |
| Trust | real reviews, photos of real work, license/insurance only if verified, local address, guarantees only if real |
| Speed | LCP on mobile; heavy sliders/video; layout shift |
| Mobile UX | tap targets, sticky call button, readable text, no intrusive popups |
| Form friction | number of fields (name, phone, email, zip, project type is often enough), required fields, multi-step vs single |
| Tracking | form submit and call clicks fire Meta/Google/GA4 events; thank-you state; no double firing |
| Follow-up | response time, call-back process, lead-to-appointment rate |
Output
Top fixes ranked by expected impact x ease, each labeled BEST PRACTICE / HEURISTIC / EXPERIMENT, with a suggested A/B test where uncertain. Page edits are made by the client's web team or the user - this plugin does not change websites.
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.

