The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute standard shell commands including mkdir -p and git mv for directory and file management. It also executes pnpm ai-hero-cli internal lint to perform validation on the created content.
[PROMPT_INJECTION]: The skill defines a workflow that ingests an external 'plan' to determine the scaffolding structure, which represents a surface for indirect prompt injection.
Ingestion points: The workflow parsed a 'plan' to extract sections, exercises, and variant types (SKILL.md).
Boundary markers: Absent. No delimiters or instructions to ignore embedded directives within the plan are provided.
Capability inventory: The agent has the ability to create directories, move files, and execute shell commands via pnpm.
Sanitization: Absent. The instructions do not specify any validation or escaping of the content parsed from the plan.

scaffold-exercises