The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses dynamic context injection placeholders to execute git and sh commands at load time for automated change detection. It also provides instructions for executing pip3, brew, npm, and python3 to manage environment setup and run diagram generation.
[EXTERNAL_DOWNLOADS]: The skill automates the installation of the diagrams Python package and the graphviz system tool from official package registries and repositories.
[PROMPT_INJECTION]: The skill workflow involves reading application source code to update its own generation logic, creating a surface for indirect prompt injection. 1. Ingestion points: Reads source code from pages/api/.js, lib/.js, and project configuration from package.json. 2. Boundary markers: Absent; the skill does not use specific markers to distinguish codebase data from instructions. 3. Capability inventory: The skill can modify local files, execute shell commands, and run Python scripts. 4. Sanitization: No sanitization is performed on the ingested code before it influences the modification of scripts/generate_diagrams.py.

architecture-diagram