The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the muapi CLI for image generation and editing (muapi image generate, muapi image edit). These commands are necessary for the skill's purpose of creating platform-optimized ad creatives.
[EXTERNAL_DOWNLOADS]: The skill includes a fallback mechanism using curl to interact with api.muapi.ai. This is used to communicate with the service backend when CLI aliases are unavailable.
[CREDENTIALS_UNSAFE]: The instructions correctly advise the user to manage secrets using an environment variable ($MUAPI_API_KEY) and the muapi auth configure command, which is a secure and standard practice for API integration.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data.
Ingestion points: Inputs product_or_service, target_audience, and tone are ingested from the user in SKILL.md.
Boundary markers: None identified; user inputs are interpolated directly into prompts.
Capability inventory: The skill can execute shell commands via the muapi CLI and curl (SKILL.md).
Sanitization: No explicit sanitization or escaping of user-provided strings is performed before interpolation into the image generation prompts.

muapi-ad-creative