The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes operating system shell commands to perform its primary functions. It uses open (macOS), xdg-open (Linux), and start (Windows) to automatically launch generated HTML presentations in the default web browser. It also invokes python3 to execute scripts for PowerPoint content extraction.
[EXTERNAL_DOWNLOADS]: The skill suggests the installation of the python-pptx library if it is not already available on the user's system to support the PowerPoint conversion workflow.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes untrusted data from external files.
Ingestion points: The skill reads and extracts content from user-provided .ppt and .pptx files, as well as existing HTML slide files during the conversion and enhancement workflows.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are implemented when the agent processes the extracted content.
Capability inventory: Across its scripts and instructions, the skill has the capability to write files to the local file system (e.g., in .ecc-design/slide-previews/ and the root directory) and execute shell commands to run Python scripts or open files.
Sanitization: There are no instructions to sanitize, escape, or validate the content extracted from external sources before it is used to generate the final executable HTML/JavaScript presentation code.

frontend-slides