The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a Python script (../design-system/scripts/search-slides.py) located in a sibling directory to retrieve copywriting formulas, layouts, and slide strategies. The instructions also note that these scripts interact with project files like brand guidelines and design tokens.
[EXTERNAL_DOWNLOADS]: The HTML slide template in references/html-template.md includes a script tag that loads the Chart.js library from the JSDelivr CDN (https://cdn.jsdelivr.net/npm/chart.js@4.4.1/dist/chart.umd.min.js). This is a standard and safe method for including well-known open-source libraries. Additionally, example layout patterns reference background images from the reputable stock photo service Pexels.
[INDIRECT_PROMPT_INJECTION]: The skill's create command takes user-provided arguments and places them inside a <task> tag within the prompt context.
Ingestion points: User input provided via the $ARGUMENTS variable in references/create.md.
Boundary markers: The skill uses <task> tags to separate user-provided instructions from the skill's system instructions.
Capability inventory: The skill can execute local scripts and write HTML files to the project directory.
Sanitization: There is no explicit sanitization step described for the user-provided arguments before they are processed by the agent.

slides