Ad Creative
v1.0.0When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising plat...
⭐ 0· 103·0 current·0 all-time
byMario Karras@mariokarras
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description (generate/iterate ad creative) match the SKILL.md content and included references (platform specs, generative tool guidance). The skill asks for ad/product/context and performance data — all appropriate for ad creative tasks.
Instruction Scope
Runtime instructions are focused on ad creative. They explicitly instruct the agent to read agent-local context files (.agents/product-marketing-context.md and .agents/brand-voice-guide.md) when present — this is expected for voice/marketing context. The references include API examples and tool recommendations (e.g., Gemini curl example using $GEMINI_API_KEY), but the SKILL.md itself does not instruct any unexpected file reads, credential harvesting, or transmission to unknown endpoints.
Install Mechanism
No install spec and no code files are present (instruction-only skill), so nothing will be written to disk or downloaded during install. This is the lowest-risk install posture.
Credentials
The skill declares no required environment variables or credentials, which is conservative. However, the included references/docs show examples that use API keys (e.g., GEMINI_API_KEY) and list many third-party services (ElevenLabs, Runway, etc.). If the agent is later configured to call those services, corresponding credentials will be needed — the skill does not request them up-front, which is reasonable but worth noting.
Persistence & Privilege
always:false and default invocation settings are used. The skill only reads agent-local context files when present and does not request system-wide config changes or credentials belonging to other skills. No elevated persistence is requested.
Assessment
This skill appears coherent and focused on ad creative tasks. Before installing or using it, consider: 1) The skill will read agent-local context files (.agents/product-marketing-context.md or brand-voice-guide) if present — ensure you don't store secrets or unrelated credentials in those files. 2) The references recommend many third-party generative tools and include example calls that use API keys (e.g., GEMINI_API_KEY). Those keys are not requested by the skill itself, but you will need to supply them in your environment if you want the agent to call those services; only provide keys you trust and avoid exposing unrelated secrets. 3) The skill correctly defers strategy-level tasks to a paid-ads skill; verify that attribution to other skills is honored in your agent setup. 4) Always review generated creative for compliance with platform policies and legal/disclosure requirements before launching. If the skill later adds code that contacts external endpoints or asks for unrelated credentials, re-evaluate (that would change the risk profile).Like a lobster shell, security has layers — review code before you run it.
latestvk97a3vq71y9276a8mn7wprfw65835mmh
License
MIT-0
Free to use, modify, and redistribute. No attribution required.