The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files which could contain instructions intended to influence the content generation process. • Ingestion points: The skill reads docs/chapters/*/index.md and docs/course-description.md to drive the generation of chapter text. • Boundary markers: The skill does not employ explicit delimiters or safety instructions to distinguish between consumed data and instructions in the input files. • Capability inventory: The agent has the ability to read existing files and perform file-write operations to update chapter content. • Sanitization: No sanitization or validation logic is defined for the input content before it is processed.
[DYNAMIC_EXECUTION]: The skill generates behavioral logic and technical specifications for interactive components intended for processing by downstream tools. • Evidence: The skill instructs the agent to create detailed specifications for p5.js simulations (MicroSims), vis-network graph models, and Chart.js visualizations. These specifications include algorithmic logic, interaction controls, and state behavior descriptions designed to be interpreted and executed by rendering engines or other AI agent skills.

chapter-content-generator