The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands to perform its core operations, specifically cloning GitHub repositories via git clone and executing a bundled assembly script build.sh using bash to generate the final index.html file.
[EXTERNAL_DOWNLOADS]: The skill facilitates the download of external codebases from user-provided GitHub URLs into the system's /tmp directory for analysis and processing.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing untrusted data from external codebases.
Ingestion points: The agent reads files (code, comments, and READMEs) from local directories or cloned GitHub repositories as instructed in SKILL.md.
Boundary markers: There are no instructions to use delimiters or 'ignore embedded instructions' warnings when the agent interpolates codebase content into its processing context.
Capability inventory: The agent possesses the capabilities to read and write local files, execute git clone, and run shell scripts via bash (in references/build.sh).
Sanitization: The skill lacks explicit sanitization or filtering logic for the ingested external content, relying on raw code snippets for its 'Code ↔ English Translation' features.

codebase-to-course