The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to manage environment prerequisites, including checking for Graphviz with command -v dot and installing it via brew install graphviz if missing.
[COMMAND_EXECUTION]: It installs the required Python library using uv pip install --system diagrams or pip install diagrams to ensure the diagramming environment is ready.
[DYNAMIC_EXECUTION]: The skill follows a workflow of writing user-defined diagram logic to a .py file and then executing it via python3 <file>.py to render the image output.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes user requirements to generate executable Python code.
Ingestion points: User-provided architecture descriptions are processed to generate Python scripts in SKILL.md.
Boundary markers: No specific delimiters or safety instructions are defined to separate user input from the code generation prompt.
Capability inventory: The skill possesses file-writing (Write, Edit) and restricted command execution (Bash) capabilities as defined in the frontmatter of SKILL.md.
Sanitization: No specific sanitization or validation of the diagram description is performed before interpolation into the generation process.

diagrams-as-code