The Agent Skills Directory

[COMMAND_EXECUTION]: The skill generates Python scripts (build_thumbnail.py and build_excalidraw.py) locally and executes them using the python3 command to generate images and JSON diagrams.\n- [COMMAND_EXECUTION]: The skill performs shell-based interactions with Git, such as git add and git commit, to manage assets in the local repository.\n- [COMMAND_EXECUTION]: The skill accesses the local filesystem using hardcoded absolute paths specific to the author (e.g., /Users/reymerekar/Desktop/...) to read brand configuration and write output.\n- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Pillow package from the Python Package Index (PyPI).\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests data from local configuration and philosophy files to influence the generation of executable Python code.\n
Ingestion points: Reads branding and style context from files located in branding/ and existing issue folders.\n
Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between trusted instructions and data read from the local files.\n
Capability inventory: The skill possesses the capability to write to the local filesystem, execute Python scripts via shell, and perform Git operations.\n
Sanitization: No sanitization or validation is applied to the content of ingested files before it is used in the script generation process.

one-stack-newsletter-assets