The Agent Skills Directory

[COMMAND_EXECUTION]: The skill orchestrates several local Python scripts including compose.py, finalize.py, and showcase.py for image compositing and processing. It also executes a bash-based CLI tool named pixeltamer to perform AI-driven image enhancement. These executions are integral to the skill's stated purpose of generating marketing assets.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the Pillow library via pip and the @houtini/gemini-mcp package via npm. It also relies on the pixeltamer tool, which is a resource provided by the vendor (gabelul) and hosted on GitHub.
[INDIRECT_PROMPT_INJECTION]: The skill implements a 'Benefit Discovery' phase that reads and analyzes the application's codebase, including UI files, models, and metadata. This functionality creates an indirect prompt injection surface where contents of the codebase could influence the agent's logic or the instructions passed to image generation backends.
Ingestion points: The skill analyzes UI files, view controllers, and project metadata in the Benefit Discovery phase within SKILL.md.
Boundary markers: No explicit delimiters or instructions are used to separate the analyzed codebase content from the agent's internal reasoning.
Capability inventory: The skill has the capability to execute shell commands, run localized Python scripts, and interact with external image models via specialized backends.
Sanitization: No specific sanitization or filtering is performed on data extracted from the codebase before it is used to generate marketing headlines or enhancement prompts.

aso-appstore-screenshots