Meta Video Ad Deconstructor
v1.0.0Deconstruct 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.
⭐ 5· 2k·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The code (deconstructor, prompt manager, models) implements marketing-dimension analysis and calls a Gemini generative model; that aligns with the skill's name and description. Requesting access to Gemini/Vertex AI is appropriate for this functionality.
Instruction Scope
SKILL.md explicitly instructs the user to set GOOGLE_APPLICATION_CREDENTIALS and to pip install vertexai. Those instructions are scoped to using Vertex AI / Gemini and to loading local prompt templates. However, SKILL.md requires a service-account credential that is not declared in the registry metadata, and the skill's runtime will read prompt files from disk (prompts/) — both are runtime behaviors not reflected in the declared requirements.
Install Mechanism
There is no install spec in the registry (no automatic download or archive). SKILL.md suggests installing the public vertexai Python package via pip, which is proportionate and expected for using Vertex AI. No high-risk download URLs or archive extraction are present.
Credentials
The skill requires Google service account credentials to call Vertex AI (GOOGLE_APPLICATION_CREDENTIALS) per SKILL.md, which is appropriate for Gemini usage — but the registry lists no required env vars. That mismatch is concerning because a user could install the skill without realizing they must provide a service account JSON (which grants project-level access). No other unrelated credentials are requested.
Persistence & Privilege
always is false and the skill does not request persistent or system-wide privileges. The code only reads local prompt files and uses the provided Gemini model object; it does not modify other skills or global agent configuration.
What to consider before installing
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.Like a lobster shell, security has layers — review code before you run it.
latestvk97a5thzz9hk883a6ctt6vm4a980gxc7
License
MIT-0
Free to use, modify, and redistribute. No attribution required.