The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses python3 to execute a local script scripts/project_test.py for initializing project workspaces, running stage-specific graders, and generating completion reports.
[EXTERNAL_DOWNLOADS]: Fetches curriculum documents, code skeletons, and test configurations from the author's GitHub repository (fancyboi999/ai-engineering-from-scratch-zh) when the local project repository has not been cloned.
[INDIRECT_PROMPT_INJECTION]: The skill ingests markdown and JSON files from the projects/ directory to guide its tutoring behavior and determine project stages.
Ingestion points: Loads data from project.json and zh.md files within the project subdirectories.
Boundary markers: The instructions do not define specific delimiters or warnings to ignore potential instructions embedded within the lesson content.
Capability inventory: Can execute shell commands through the project's testing script and write progress logs to PROJECTS-LEARNING.md.
Sanitization: No explicit validation or escaping is applied to the content of the curriculum files before the agent processes them.

build-project