The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script (generate_chart.py) to manage API communication and image processing. It also uses the system open command to preview generated images, which is standard behavior for its intended functionality.
[EXTERNAL_DOWNLOADS]: The skill performs network requests to https://api.labnana.com to generate chart images. This external communication is a core part of the skill's documented behavior.
[PROMPT_INJECTION]: The skill processes user-provided descriptions and interpolates them into prompts for the image generation model.
Ingestion points: User input for chart types, contents, and styles are captured in SKILL.md and passed to the execution script.
Boundary markers: No specific delimiters are used to separate user-provided content from the prompt templates.
Capability inventory: The skill can execute local scripts, perform network operations, and write files to the specific local directory /Users/ugreen/Documents/obsidian/09image/.
Sanitization: The skill relies on the agent's logic to extract information and does not implement explicit sanitization before passing data to the generation script.

chart-image