The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill relies on uvx --from agent-slides to perform core tasks such as extraction, rendering, and auditing. This pattern downloads and executes code from a remote package registry at runtime.
[COMMAND_EXECUTION]: The skill uses shell commands to manage the environment, including mkdir for directory creation and find for project discovery.
[EXTERNAL_DOWNLOADS]: The use of uvx involves downloading the agent-slides package from external repositories during execution.
[INDIRECT_PROMPT_INJECTION]: The skill acts as a pipeline that ingests and processes untrusted user data, including presentation briefs and PowerPoint templates, which are then used to generate rendering 'ops' and slide content.
Ingestion points: User-provided brief/topic and .pptx template files (processed in Steps 1 and 2).
Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the content being processed.
Capability inventory: The skill has the capability to execute shell commands via uvx, create directories, and write JSON/PPTX files to the local disk.
Sanitization: There is no evidence of sanitization or validation of the content extracted from user briefs or templates before it is passed to rendering tools.

slides-full