Meta Video Ad Deconstructor

Deconstruct video ad creatives into marketing dimensions using Gemini AI. Extracts hooks, social proof, CTAs, target audience, emotional triggers, urgency tactics, and more. Use when analyzing competitor ads, generating creative briefs, or understanding what makes ads effective.

This skill appears to do what it says (analyze ad creatives with Gemini) but the SKILL.md requires a Google service-account JSON (GOOGLE_APPLICATION_CREDENTIALS) while the registry metadata claims no env vars — that's an inconsistency you should clear up before installing. If you decide to use it: 1) provide a least-privilege Vertex AI service account (avoid broad project/editor roles), 2) review the prompts/marketing_analysis.md and the scripts locally to confirm there are no unexpected external endpoints or data-sending logic, and 3) be aware that the skill will send transcript/scene/text data to Google Gemini (so do not feed sensitive or proprietary video content unless the service account/project policy and data residency are acceptable). If the registry maintainer cannot explain the missing credential declaration, treat the omission as a risk and proceed cautiously.

Type: OpenClaw Skill Name: meta-video-ad-deconstructor Version: 1.0.0 The skill is designed to deconstruct video ad creatives using Gemini AI, which aligns with its stated purpose. It requires standard Google Cloud credentials (`GOOGLE_APPLICATION_CREDENTIALS` and `project-id`) for Vertex AI, which are configured by the user and not maliciously accessed or exfiltrated by the skill. The Python code handles prompt management, data formatting, and interaction with the Gemini API. File system access is limited to reading local markdown prompt files, and network activity is confined to the legitimate Gemini API endpoint. There is no evidence of data exfiltration, malicious execution, persistence, or prompt injection against the OpenClaw agent.