The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches configuration files, lesson documentation, and quizzes from the author's GitHub repository (rohitg00/ai-engineering-from-scratch). These resources are used to define the learning path and content.
[COMMAND_EXECUTION]: To verify the learner's environment and execute lab exercises, the skill runs system commands such as node --version, python3 --version, and npx. It also monitors the exit codes and paths of scripts executed during lessons.
[DYNAMIC_EXECUTION]: The skill is designed to run code samples located in the code/ directory of the downloaded repository to demonstrate practical applications of agent skills.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill processes external data from remote files (agent-skills.json, docs/en.md, quiz.json) and a local progress tracking file (AGENT-SKILLS-LEARNING.md).
Boundary markers: The instructions do not specify strict delimiters or markers to isolate content from these external files from the agent's core instructions.
Capability inventory: The agent has the capability to read/write local files, execute shell commands, and run Python/Node.js scripts.
Sanitization: There is no evidence of content sanitization or validation for the data retrieved from the remote repository before it is processed or executed.

learn-agent-skills