The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches project documentation, starter files, and test definitions from the author's official GitHub repository (rohitg00/ai-engineering-from-scratch) when local files are not available.
[COMMAND_EXECUTION]: Utilizes python3 to run a local script scripts/project_test.py for workspace initialization and automated project grading.
[INDIRECT_PROMPT_INJECTION]: The skill processes external markdown and JSON files containing project lessons and requirements, which are interpolated into the agent's context. This presents an attack surface where malicious content in those files could influence agent behavior.
Ingestion points: Documentation from projects/<id>/stages/<stage-id>/docs/en.md and configuration from projects/<id>/project.json (SKILL.md).
Boundary markers: Absent. There are no explicit delimiters or instructions used to separate external lesson content from the agent's system prompts.
Capability inventory: The skill can write to the local file system (PROJECTS-LEARNING.md) and execute shell commands (python3 scripts/project_test.py).
Sanitization: No sanitization or validation of the ingested lesson content is performed before processing.

build-project