2.6k
GitHub Stars
3
Bundled Files
2 months ago
Catalog Refreshed
3 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill openclaw/skills --skill landing-page-auditor- _meta.json310 B
- metadata.json81 B
- SKILL.md4.1 KB
Overview
This skill audits landing pages for paid-traffic funnels across Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, and Shopify Ads. It focuses on reachability checks, friction diagnosis, and conversion blockers, producing an owner-ready remediation plan tied to spend risk and recovery speed. Outputs are actionable and channel-aware, not generic marketing advice.
How this skill works
The auditor confirms scope (accounts, campaigns, adsets, ads) and validates data freshness before inspecting page reachability, event/ pixel integrity, form and checkout flows, load performance, and policy compliance signals. It ranks findings by severity and spend exposure, proposes immediate containment or rollback steps, and produces an escalation ticket payload plus a monitoring checklist for follow-up.
When to use it
- Before launching paid campaigns to confirm tracking and conversion readiness
- When spend rises without matching conversion lift (anomaly triage)
- If platform alerts or policy flags threaten delivery
- During account health reviews across multiple ad platforms
- When diagnosing high bounce, low conversion, or checkout failures
Best practices
- Provide minimal required inputs: entity_ids, incident_or_audit_scope, and time_window before audit
- Confirm event freshness; if data is stale, block judgments and request refresh timestamps
- Keep recommendations channel-aware (creative cadence for Meta/TikTok; query intent for Google/Amazon)
- Always include at least one stop-loss or rollback action when spend risk exists
- Separate observed facts from hypotheses and include measurable validation steps
Example use cases
- Pixel breakage pre-launch: detect missing purchase event, propose immediate mitigation and relaunch checklist
- Live spend spike: triage anomalies, contain spend, and emit incident ticket with next-check timing
- Multi-platform readiness audit: produce scorecard, list blocking risks, and owner-level remediation actions
- Policy flag detected on creative: recommend containment, alternate creative, and escalation payload
- Checkout funnel errors on Shopify Ads: identify failure step, propose rollback and monitoring plan
FAQ
Provide entity_ids (account/campaign/adset/ad), the audit scope or incident, and the time_window. If logs are missing, supply recent events or grant data access.
How does the skill handle stale or incomplete data?
If data is stale or incomplete the skill blocks final judgments, lists exactly which timestamps or logs are missing, and returns a minimal request for refresh before further analysis.